WO2024169984A1

WO2024169984A1 - Method for determining burning properties of a polymer

Info

Publication number: WO2024169984A1
Application number: PCT/CN2024/077391
Authority: WO
Inventors: Volker SETTELS; Stefan Ortgies; Sonja Schmidt; Bianca KRAEMER
Original assignee: BASF Polyurethane Specialties China Co Ltd; BASF SE
Current assignee: BASF Polyurethane Specialties China Co Ltd; BASF SE
Priority date: 2023-02-17
Filing date: 2024-02-18
Publication date: 2024-08-22
Anticipated expiration: 2025-08-17
Also published as: WO2024170788A1; WO2024169983A1; WO2024170789A1

Abstract

Method for determining burning properties of a polymer is disclosed. A digital representation of the polymer indicative of characterizing parameters is provided. A digital representation of burning test conditions is provided. A burning property model is provided based on the provided burning test conditions, wherein the burning property model is adapted to determine one or more burning properties of a polymer with respect to the respective burning test method. The burning property model is a datariven model parameterized with respect to the respective burning test method to determine one or more burning properties of a polymer based on the characterizing parameters and the burning test parameters. The burning properties of the polymer are determined based on the provided burning property model, the burning test conditions and the digital representation of the polymer.

Description

Method for determining burning properties of a polymer

FIELD OF THE INVENTION

The invention relates to a method, an apparatus and a computer program product for de-termining burning properties usable for validating a burning behavior of a polymer. Moreo-ver, the invention refers to a training method, training apparatus and training computer program product for training a data-driven burning property model usable for determining the burning properties of a polymer. Furthermore, the invention refers to an interface method, interface apparatus and interface computer program product for providing an in-terface for interfacing with any of the above methods, apparatuses and computer program products.

BACKGROUND OF THE INVENTION

Generally, polymers are widely used in industrial and/or daily use products due to their broad range of application properties. The use of polymers encompasses amongst others coatings, furniture, automotive applications, lubricants, packages and foams for insulation. However, in many of these applications, in addition to the application properties, also se-curity considerations have to be taken into account. In particular, the burning behavior of a polymer can play a crucial role in the safety of the product utilizing the polymer during its daily use. In particular, in most applications it is crucial that the used products are not easily inflammable or even show a retarding burning behavior. Thus, there is not only a need for polymers with desired burning behaviors but also a need to take into account knowledge about the burning behaviors of a polymer in early stages of a product design process.

SUMMARY OF THE INVENTION

It is an object of the present invention to provide a method, an apparatus and a computer program product that allow for an accurate determination of burning properties of a polymer that is computationally inexpensive and can robustly be applied to new polymers. Moreover, it is further an object of the invention to provide a training method, a training apparatus and a training computer program product that allow to provide a burning property model that is usable in the method, apparatus and computer program product and that can be trained to provide a good determination accuracy by utilizing less computational resources.

In a first aspect of the present invention, a computer-implemented method for determining burning properties usable for validating a burning behavior of a polymer is presented, wherein the method comprises a) providing a digital representation of the polymer indica-tive of or associated with characterizing parameters of the polymer, wherein the character-izing parameters are indicative of characteristics of a polymer and/or are derivable from one or more characteristics of the polymer, b) providing a digital representation of burning test conditions indicative of or associated with a burning test method and burning test pa-rameters, wherein the burning test method is indicative of a standardized test method for determining experimentally a respective burning property of a polymer and wherein the test parameters are indicative of a specific test procedure of the burning test method, c) provid-ing a burning property model based on the provided burning test conditions, wherein the burning property model is adapted to determine one or more burning properties of a poly-mer with respect to the respective burning test method, wherein the burning property model is a data-driven model parameterized with respect to the respective burning test method to determine one or more burning properties of a polymer based on the characterizing param-eters and the burning test parameters, and d) determining the one or more burning prop-erties of the polymer based on the provided burning property model, the burning test con-ditions and the digital representation of the polymer.

Since the burning property model is configured to determine one or more burning properties of a polymer based on provided burning test conditions and based on a digital representa-tion of the polymer, the burning properties of the polymer with respect to the burning test can be determined very accurately. Moreover, since the burning property model can spe-cifically be trained for a specific burning test method with respective burning test parame-ters, less training data becomes necessary for training and the burning property model becomes more flexible with respect to determining the burning properties of new polymers not being part of the training dataset. Thus, the method allows for an accurate determina-tion of burning properties that is computationally inexpensive and can be applied flexible also to new polymers. Further, the currently most widely used standard burning test meth-ods often require large amounts of materials, are complex and time-consuming to perform. In contrast thereto, utilizing the described method above allows to avoid the huge material usage that also produces huge amounts of waste and provides results essentially immedi-ately. Thus, not only the technical requirements for the burning behavior determination can be reduced, but also the time required for designing a new polymeric product with a specific burning behavior can be considerably shortened. Moreover, providing an easy possibility for taking an accurate determination of the burning behavior of a product into account al-ready during the design process allows to design the product such that safety requirements of the environment in which the product should be applied can be fulfilled without a huge amount of testing of potential products. In particular, it can be ensured that only potential products are provided to the final design production and test stages that have a high po-tential to fulfil all necessary safety requirements, in particular, with respect to their burning behavior.

Moreover, since the characterizing parameters are utilized that contain physico-chemical information of the polymer, e.g. quantum chemical information of the polymer, the training of a respective burning property model can be improved. In particular, utilizing the charac-terizing parameters allows training of such models with less training data, because some of the correlation information that needs to be learned is already presented to the model by using the characterizing parameters. This, further allows to save tests and experiment nec-essary for providing the training data set.

Generally, companies developing new plastics need to invest significant resources in self-assessing product burning behaviour and in certification. The overall burning behaviour assessment, including laboratory spaces and equipment, becomes costly and time con-suming. Thus, there is a need to early identify the burning behaviour of a new material in the development process. The proposed method of determining burning behaviour as dis-closed herein enables a faster and more efficient way of developing new materials. In an early phase, even before synthesis of the polymer, the burning behaviour can be deter-mined. This allows to determine whether the polymer is suited for market entry. This leads to a faster time to market. This also allows to reduce waste production, because the poly-mer does not need to be synthesized to determine burning behaviour. The proposed method provides a digital twin of measuring the burning behaviour of a polymer.

Further, the standard measurements and tests for a burning behavior are often time con-suming and consume a lot of material and resources, for example, test samples have to be produces and burned including the production of respective waste products. In particular when developing new polymers for respective applications these resource intensive tests can strongly limit the development process. In this context the invention allows to provide results for a new polymer instantly strongly decreasing the time, resources and waste until results are available.

Moreover, due to the incredibly high number of possible, often not even fully explored pol-ymers, potentially suitable for a specific application, today a technical product engineer, given the technical task of finding a polymer that is not only suitable for a specific applica-tion, but also fulfills respective target properties, in particular, a target burning behavior, has to synthesize and test huge amounts of possible polymers, or go through huge datasets and libraries in which potential polymers are stored in order to find a respective polymer that might fit the application. Even when utilizing sophisticated design of experiment meth-ods, still a very high number of possible polymers has to be synthesized and experimentally tested. In this context the above described method allows to assist a user, for instance, a technical product engineer, to find potentially suitable polymers automatically and much faster. In particular, by utilizing the above method the user only has to synthesis and test potentially suitable polymers for which it has been determined that it is very likely that they fulfill the respective target property, in particular, a target burning behavior. Accordingly, unnecessary synthesizing and testing of polymers can be avoided. Thus, the method allows a user to perform a technical task of finding a polymer suitable for a technical application faster and more efficient.

The method refers to a computer implemented method and thus can be performed by a general or dedicated computer adapted to perform the method, for instance, by executing a respective computer program. The method is adapted to determine burning properties of a polymer usable for validating a burning behavior of a polymer. Generally, the burning properties can refer to any properties that allow for a quantification of the burning behavior of a polymer, for example, to determine when the polymer in a certain situation will burn. The determined one or more burning properties can refer to only one value, for instance, to an ignition temperature of the polymer, but can also refer to more than one value, for instance, can refer to a temperature profile within probe made from the polymer when sub-jected to a predetermined heat source. The determined burning properties then allow to evaluate the burning behavior of a polymer. This evaluation of the burning behaviour also allows to estimate the suitability of the polymer for a certain application situation, for exam-ple, when provided as part of a predetermined product and subjected to a heat source, for example, the flame of a lighter. For example, the burning behavior of the polymer in a predetermined situation can be derived using predetermined rules from the respective burning properties of the polymer. For example, an ignition temperature allows to derive the burning behavior of a polymer in a product when subjected to the flame of the lighter. Generally, the burning properties are an intrinsic characteristic of a polymer. In this context, an intrinsic characteristic of the polymer refers to a property of the polymer that is caused by and thus reflects the nature of the polymer, i.e. the structure, composition, etc., with respect to a specific context. In particular, a burning property reflects the nature of the polymer when subjected to a heat source. Preferably, the one or more burning properties indicative for the burning behavior of the polymer comprised at least one of a heat release rate, a peak heat release, a total heat release, an average rate of heat emission, a maxi-mum rate of heat emission, effective heat of combustion, flame height, burning time, after-burn time, mass loss, mass loss rate, fire growth rate, total smoke production, smoke growth rate, dripping behavior, ignition time and extinguishment time.

Generally, the polymer can be any polymer. Preferably, the polymer is a synthetic polymer. In an embodiment, a synthetic polymer may be a chemical compound which is produced by a chemical production from one or more starting material (s) , such as monomers, and which comprises at least two monomer units. The monomer units may be regarded as subunits of the polymer. The polymer may be prepared from the monomers by commonly known polymerization reactions. The polymer may be produced from a single type of mon-omers or from different monomers. The monomer units may be distributed randomly or may be present as blocks within the polymer. The polymer may be a linear polymer. The polymer may be a branched polymer. The polymer may be a crosslinked polymer.

In a first step, the method comprises providing a digital representation of the polymer indic-ative of characterizing parameters of the polymer. In particular, the providing can refer to receiving the digital representation from an input of a user using, for instance, a respective input unit. Moreover, the providing can also refer to accessing a storage unit on which the digital representation is already stored. Further, the providing can also comprise receiving characterizing parameters, for instance, via a network connection from other sources and providing the received characterizing parameters as digital representation. In particular, the characterizing parameters of a polymer can be quantified by polymer physicochemical pa-rameters. Preferably, the digital representation is indicative of and/or comprises polymer physicochemical parameters quantifying the physical and/or chemical characteristics of the polymer, preferably, referring to polymer descriptors. In particular, the polymer physico-chemical parameters are indicative of parameters quantifying the characterizing parame-ters of the polymer. In this context, the term “characterizing parameters” refers to physical and/or chemical characteristics of the polymer. However, the digital representation can also be provided such that it allows to derive characterizing parameters, for example, in form of polymer descriptors, for instance, by providing a representation of the polymer for which respective characterizing parameters are already stored or can be determined, for instance, by respective polymer descriptor calculations. The providing of the digital representation can comprise deriving the characterizing parameters from the digital description. Preferably, the digital representation refers to at least one of a recipe, a structural formula, a brand name, an IUPAC name, a chemical identifier and a CAS number of the polymer.

In a preferred embodiment, the characterizing parameters can refer to parameters related to a synthesis process for synthesizing the polymer. Such characterizing parameter can, for instance, be derived from a synthesis specification. Thus, the digital representation can also refer to or comprise a synthesis specification, wherein at least some of the character-izing parameters can then be derived from the synthesis specification. For example, pro-cess parameters, like a temperature, pressure, moisture or other environmental specifica-tions for synthesizing the polymer can be utilized as characterizing parameters. Further, recipe parameters indicative of substances and/or amounts of substances that are utilized in the synthesis can be utilized additionally or alternatively as characterizing parameters. For example, the recipe parameters can comprise an amount of certain prepolymers, an amount of a catalyst, an amount of fire protective additives, etc.

Additionally or alternatively, the polymer characterizing parameters can be parameters quantifying the characterizing parameters of subgroups of the polymer. In this embodiment, the digital representation can also be provided such that it allows to derive the polymer physicochemical parameters by determining subgroups of the polymer and to determine the polymer physicochemical parameters based on characterizing parameters of the deter-mined subgroups. Generally, a subgroup refers to a part of the polymer, wherein all sub-groups of a polymer together form the polymer. For example, a subgroup can refer to a part of the polymer, wherein the subgroups are linked together successively along a chain or network to form the polymer. Preferably, the subgroups of the polymer refer to repeating units that describe a part of the polymer which when repeated produces the complete pol-ymer chain. However, in some cases, a subgroup can also refer to a single part of the polymer that is not repeated. Moreover, it is preferred that the subgroups comprise parts that are repeated, for example, a subgroup of a polymer can comprise a repeating core also present in other subgroups and further additional parts that are not present in other subgroups. Preferably, the subgroups refer to at least one of polymerized monomers or oligomer fragments. More preferably, the subgroups refer to polymerized monomers. In this context, polymerized monomers refer to monomers after their polymerization some-times also called “mer unit” or “mer” . In particular, polymerized monomers do not refer to monomers, i.e. raw materials, as present in a reaction mixture before polymerization, but refer to repeating units derived from monomers that have been changed during or after the polymerization. Thus, subgroup descriptors determined for polymerized monomers are dif-ferent from subgroup descriptors determined for unreacted monomers before polymeriza-tion. It has been found by the inventors that in particular the polymerized monomers allow to determine polymer descriptors from the subgroup descriptors of the polymerized mono-mers that allow for an accurate determination of the biodegradability. In a preferred em-bodiment, the digital representation of the polymer comprises subgroups provided as mo-lecular model which is indicative of its chemical structure of the subgroup after its polymer-ization. Even more preferably, the molecular model of a subgroup is determined in a way that is suited for quantum chemical computations regarding a number and type of atoms and their connectivity that is representative of the properties of the subgroup within the polymer. Moreover, additionally an alternatively to a molecular model of a subgroup treating the subgroup as a monomer structure, also a molecular model referring to an oligomer model can be utilized that takes into account effects of neighbouring molecular structures of the subgroup in the polymer.

Generally, if the digital representation of the polymer does not directly comprise the polymer physicochemical parameters, it is preferred that the polymer physicochemical parameters are determined by determining the subgroups of the polymer. For example, respective sub-groups of the polymer can be determined utilizing known methods. However, it is preferred that the determination of the subgroups of the polymer is performed in accordance with later described embodiments of the invention. In particular, it is preferred that the sub-groups are determined such that between atoms of different subgroups in the polymer the bond is as least polarized as possible and, preferably, with a bond order as small as pos-sible (e.g. a CC single bond) . Additionally, it is preferred that the subgroups representing a polymer comprise the same number of active non-hydrogen-atoms then the polymer. Be-sides the active atoms, a subgroup can also contain further atoms, which can be ignored during computing the descriptors of the subgroup. Further, it is preferred that the subgroups are determined in a way that polymers comprising parts, which were built up with different polymerization techniques, are well covered and fulfill the foresaid conditions. An example is a polyether used as ingredient for a polyurethane. Generally, a database or archive with a plurality of reactions between polymer parts can be generated and the subgroups can be derived from the respective structure of the reactions. For example, specific chemical lan-guages like SMILES and SMARTS can be utilized to easily derive the subgroup of a poly-mer. For example, a database of reaction SMARTS can be generated and then based on the polymerization of the respective polymer a corresponding reaction SMARTS can be selected. From the selected reaction SMARTS then the SMILES of monomers of the poly-mer are directly derivable and, for example, RDkit can be used to determine from the SMILES of the monomers the SMILES, i.e. the number and connectivity of the atoms, of the subgroups.

The determined subgroups of the polymer are associated with subgroup physicochemical parameters quantifying characterizing parameters of the subgroups in the polymer, prefer-ably, also the subgroup physicochemical parameters refer to subgroup descriptors. In par-ticular, it is preferred that if the polymer physicochemical parameters are not directly pro-vided by the digital representation, the polymer physicochemical parameters are deter-mined by determining a respective subgroup physicochemical parameter for each of the subgroups and to determine the polymer physicochemical parameters based on the sub-group physicochemical parameters of the subgroups, for instance, by averaging. Thus, the method preferably comprises first providing or determining for the polymer the subgroups from the digital representation of the polymer, then to determine or provide the subgroup physicochemical parameters, i.e. values of the parameters quantifying the characterizing parameters, of the subgroups, and then to determine the polymer physicochemical param-eters based on the subgroup physicochemical parameters of each polymer.

Preferably, the polymer characterizing parameters refer to polymer descriptors referring to at least one of constitutional descriptors, count descriptors, list of structural fragments, fin-gerprints, graph invariants, 3D-descriptors and/or higher dimensional descriptors that are indicative of parameters quantifying characterizing parameters of the polymer. In a pre-ferred embodiment the polymer descriptors refer to 3D descriptors, in particular, quantum chemical descriptors. Moreover, the inventors have found that in particular a at least one of a amount of P-and halogen atoms, the amount of atoms of an oxidization level, amount of aromatic components, amount of polyisocyanurat groups, amount of burnable and/or not burnable blowing agents, index as ratio between NCO-groups and OH-, NH-groups, Water and formic acid in the recipe describes the burning behavior of a polymer very accurately. Thus, it is in particular preferred that the characterizing parameters comprise at least one of the above quantities.

Generally, polymer characterizing parameters can be derived from the subgroup charac-terizing parameters, thus, also the subgroup characterizing parameters can refer to the same descriptors as stated above. However, the characterizing parameters can also be derived without utilizing subgroups, for instance, by quantum chemical simulations of the whole polymer. In the following the possible characterizing parameters are defined in more detail. Also in these cases the defined characterizing parameters can refer directly to the polymer characterizing parameters or, optionally, to the subgroup characterizing parame-ters.

A constitutional descriptor can refer to any of a potential, average molecular weight, poly-dispersity, charge, spin, boiling point, melting point, enthalpy of fusion, dissociation con-stant, Hansen parameter, protic, polar and dispersive contributions, Abraham parameter, retention index, TPSA, receptor binding constant, Michaelis-Menten constant, Inhibitor con-stant, Mutagenicity, LD50, bioconcentration, toxicity, biodegradation profile and viscosity.

A count descriptor can refer to any of a sum of atomic electro negativities, a sum of atomic polarizabilities, an amount of ingredients, a ratio of amounts of ingredients, a number of atoms and non H-atoms, a number of H, B, C, N, O, P, S, Hal and heavy atoms, a number of H-donor and H-acceptor atoms, a number of bonds, non-H or multiple bonds, a number of double, triple and aromatic bonds, a number of functional groups, a ratio of functional groups, a sum of bond orders, an aromatic ratio, a number of rings or circuits, a number of unpaired electrons, a number of rotatable bonds, rotatable bond fractions, and a number of conformers.

Polymer descriptors referring to a list of structural fragment descriptors can refer to at least one of a list of molecular fractions, a list of functional groups, a list of bonds, and a list of atoms. Fingerprint descriptors comprise preferably, at least one of MACCS keys, preferably, in bit format or total amount format, Morgan and other circular fingerprints, preferably, in bit format or total amount format, topological torsion, atom pairs, infrared and related spectra, fingerprint count, PubChem fingerprint, substructure fingerprint, and Klekota-Roth finger-print. Graph invariants/topological indices descriptors comprise preferably at least one of topostructural indices and topochemical indices.

In a preferred embodiment the polymer characterizing parameters are 3D descriptors com-prising at least one of a volume as sum overall atoms, a mean volume per atom, an area as sum overall atoms, an area as mean per atom, an area over all atoms, an area as mean per atom, a solvent accessible surface, a dispersion energy, a dielectric energy, a H-donor, H-acceptor, polar and non-polar surface area, an atom resolved H-donor, H-acceptor, polar and non-polar surface area, a shape, a sphericity, dipole and higher electric moments, po-larizability, dielectric energy, protic, polar and non-polar surface area, orbital energies and orbital gaps, ionization energy, electron affinity, hardness, electronegativity, electrophilicity, excitation energies and intensities, infrared and ultraviolet absorption bands, reactivity measurements, redox potential, bond criterial points, partial charges, charge surface areas, atomic orbital contributions, bond orders, atom radius. In particular, it is preferred that the polymer physicochemical parameters refer to 3D descriptors comprising at least one of a sum of a volume over all atoms, a mean of a volume per atom, a sum of the area over all atoms, a mean of an area per atom, a solvent accessible surface, a dispersion energy, a dielectric energy, a H-donor, H-acceptor, polar and/or non-polar surface area, atom re-solved H-donor, H-acceptor, polar and/or non-polar surface area, shape, sphericity, cone angles, polarizability, dielectric energy, protic, polar and/or non-polar surface area, excita-tion energies and intensities, infrared and/or UV absorption bands, reactivity measure-ments, particle charges and/or charge surface areas. A preferably utilized higher dimen-sional descriptor can comprise at least one of a conformational partition function, solubility, vapor pressure, activity coefficient, diffusion coefficient, partition coefficient, interfacial ac-tivity, rotational constant, moment of inertia, radius of gyration, compositional drift of poly-mer, density, viscosity, conformer weighted volume and area, conformer weighted H-donor, H-acceptor, protic, polar and/or non-polar surface area, charge distribution, conformational dipole moment and molecular refraction. Preferably higher dimensional descriptors are uti-lized that comprise at least one of solubilities, vapor pressure and activity coefficients, in-terfacial activity, conformer weighted H-donor, H-acceptor, protic, polar and non-polar sur-face area, and charge distribution.

In a further step, the method comprises providing a digital representation of burning test conditions, wherein the burning test conditions are indicative of or associated with the burn-ing test method and burning test parameters. The digital representation can be any repre-sentation, for example, any data format or structure, that allows a respective computer system performing the method to read the digital representation, in particular, to read the burning test conditions, such that that they can be processed further. Generally, the burning test conditions can be provided such that it allows to derive the burning test method and the burning test parameters or such that it directly comprises the burning test method and the burning test parameters. For example, the burning test conditions can be provided in a form of an identifier of a burning test method, wherein based on the identifier a storage unit can be accessed comprising the burning test method and the burning test parameters. The identifier can, for example, be a name or identification number of the burning test as pro-vided by a standard. However, the burning test conditions can also be directly provided, for instance, by a user utilizing an input unit, such that the burning test method and the burning test parameters are provided. For example, a user can be provided with a selection of known burning test method and can then select the respective burning test method. Gen-erally, the burning test method is indicative of a standardized test method for determining experimentally one or more burning properties of a polymer. Generally, a plurality of such standardized test methods for one or more burning properties are known and can be re-ferred to by a respective identifier. Preferably, the burning test method refers to one of single burning item, single-flame source test, UL94, UL 94 HB, ASTM E84 and cone calo-rimeter test. The test parameters are further indicative of a specific test procedure of the burning test method, for instance, of one or more process parameters specifying the burn-ing test method. For example, the test parameters can indicate the value of a distance of a heat source specified by the burning test method from the polymer. Further examples refer, for instance, to a time for which the product formed by the polymer is subjected to a heat source specified by the burning test method, a temperature profile of a heat source utilized in the burning test method, the presence or absence and specification of material between the heat source specified by the burning test method and the product formed from the pol-ymer, specifics of a cooling source present during the burning test method, etc. In particular, the test parameters are specific to each burning test method and thus depend on the defi-nition of the burning test method. However, even in a standardized test procedure the test parameters can be varied in some cases such that it is possible that for the same burning test method different test parameters can be specified within a range of possible test pa-rameters defined by the burning test method.

The method further comprises providing a burning property model based on the provided burning test conditions. In particular, it is preferred that the providing of the burning property model refers to a selecting of a burning property model based on the provided burning test conditions. For example, a plurality of burning property models can be stored on a burning property model storage, wherein each burning property model has been trained for a spe-cific burning test method. Based on the provided burning test conditions indicative of the burning test method, a respective suitable burning property model can then be selected from the plurality of burning property models. However, in another embodiment the provid-ing of a burning property model based on the provided burning test conditions can also refer to a user selection of the burning property model. For instance, the user can be pro-vided with a preselection of burning property models that are commonly utilized or are used for a specific application of a polymer and then be allowed to select the respective burning property model that should be utilized. Generally, the possible stored burning property mod-els refer to burning property models that have already been parameterized based on a respective training data set for one or more burning tests. Since the training data sets uti-lized for parameterizing a burning property model are historical data, as described in more detail below, the burning property models can be trained and thus generated at any time before the determination of a specific burning property for a specific polymer, and after the training be stored on a respective database. However, the training and thus the generation of a burning property model can of course also be performed at the time that it is determined that a specific burning property model, for instance, for a specific burning test, is needed.

The provided burning property model is then adapted to determine one or more burning properties of a polymer that would be measured in an actual performance of the burning test. In particular, the burning property model is a data driven model that is parameterized with respect to the burning test method such that it can determine one or more burning properties of a polymer based on the characterizing parameters, preferably, based on the polymer characterizing parameters quantifying the characterizing parameters, indicated by the digital representation. The term “such that” is to be interpreted here that the parame-terization adapts and thus enables the burning property model to provide the property with respect to a burning test when provided with polymer characterizing parameters as input. For example, the property model relates polymer characterizing parameters of historic dig-ital representations of synthesis specification and historic digital representations of burning tests to a property measured or derived for the respective polymer associated with a syn-thesis specification in a respective burning test. Thus, the burning property model can be parameterized based on training data comprising i) digital representations of a plurality of training polymers indicative of characterizing parameters of each of the training polymers, ii) one or more burning properties determined, in particular, measured or derived from measurements, by the respective burning test method associated with the respective burn-ing test parameters for each training polymer, and optionally, iii) ii) a plurality of burning test parameters for the predetermined burning test method. This allows that, based on a target property, a digital representation of the synthesis specification may be determined. The term “data driven” is used here to emphasize that the model is mainly based on respective data input and not, for instance, on intuition, personal experience or knowledge. Preferably, the burning property model refers to a machine learning based model that is based on known machine learning algorithms, like neural networks, regression models, classification algorithms, etc. It has been found that for most applications in this context, in particular, regression models based on Linear Regression, Random Forests, Boosted Trees, Lasso, Ridge Regression and MARS algorithms are suitable, whereas for classification models, in particular, Random Forests, Logistic Regression and SVM algorithms are suitable. Gener-ally, the burning property model is parameterized during a training process in which char-acterizing parameters, preferably, polymer descriptors derived from parameters quantifying the characterizing parameters of the polymer, are utilized together with corresponding burn-ing properties that can be derived or measured from respective burning test methods. Based on such a training data set that is specific for a burning test method the respective parameters of the data driven model can be determined utilizing known training methods such that the burning property model is also able to determine one or more burning prop-erties of polymers that are not part of the training data set.

Moreover, in a preferred embodiment, the burning property model can also be adapted to determine the one or more burning properties for a polymer further based on test parame-ters as input. For example, in cases in which the test parameters can vary within certain ranges during the standardized burning test method, the burning property model can be trained to take the specific test parameters, i.e. the specific test parameter values, provided by the burning test conditions into account. In particular, the burning property model can be trained by utilizing a training data set comprising polymer characterizing parameters of polymers associated with different test parameters for a specific burning test method, as described above, leading to a burning property model that takes the test parameters vari-ations of the burning test method indirectly into account. However, the training data set can optionally also comprise specific test parameter values of a respective burning test method. In this case, the burning property model can be trained such that in addition to the polymer characterizing parameters also test parameter values can be provided as input, wherein the burning property model then determines the one or more burning properties further based on the test parameter values. This has the advantage that the burning properties can be determined even more accurately, in particular, in cases in which the burning prop-erties strongly depend on the specific test parameter values of a burning test method.

Further, the method comprises determining the one or more burning properties of the pol-ymer based on the provided burning property model, the burning test conditions and the digital representation of the polymer. In particular, if the digital representation of the poly-mer comprises the polymer characterizing parameters, the polymer characterizing param-eters are provided as input to the burning property model, wherein the burning property model then provides the determined one or more burning properties as output. If the digital representation does not directly comprise the polymer characterizing parameters, the de-termining of the one or more burning properties can comprise also determining firstly the polymer characterizing parameters, for instance, as described above. The such determined polymer characterizing parameters can then be provided to the burning property model as input. The determined one or more burning properties can then be provided, for instance, to an output unit or to a computing unit for further processing. Preferably, the providing of the burning properties leads to a further processing utilizing the determined one or more burning properties. In such a case, the providing as individual step can be omitted and replaced by the processing of the determined one or more burning properties.

The determination of the burning properties utilizing the burning property model can be regarded as a virtual measurement of the burning behavior. In particular, the burning prop-erty model is based on measurement data, for example, measured burning properties of polymers utilized for the training of the burning property model. Thus, the burning property model comprises the information provided by these previous measurements. Moreover, the characterizing parameters can in some cases also refer to measured characteristics of the polymer. Accordingly, also the determined burning property of new polymer determined utilizing the burning property model can be regarded as being based at least partly on measurement results.

Preferably, the processing of the one or more burning properties comprises providing con-trol data based on the determined one or more burning properties associated with the burn-ing behaviour. In particular, it is preferred that the control data is configured for causing and/or monitoring a production process based on the determined one or more burning properties and/or a display to display the burning properties. In an embodiment, the control data is configured for controlling and/or monitoring a production of the polymer and/or a production of a product comprising the polymer based on the determined one or more burning properties of the polymer and/or for causing a display for displaying the determined one or more burning properties. Control data for controlling and/or monitoring includes any data resulting from the method described above that may be used to directly or indirectly derive machine readable instructions to control and/or monitor i) a polymer synthesis of the polymer or ii) a production of a product comprising the polymer associated with the digital representation. In this sense the method may be viewed as a method for controlling and/or monitoring a polymer synthesis or a production utilizing the synthesized polymer, wherein the polymer is known prior to the controlling and/or monitoring. The production process can refer to a production process of the polymer or can refer to an application process of a product in which the polymer is utilized. For example, if the determined one or more burning properties indicate that a product formed from the polymer will ignite at a specific temper-ature the generation of the control data can comprise generating controlling and/or moni-toring signals for controlling and/or monitoring a production process of or utilizing the poly-mer such that the respective ignition temperature is not reached in any of the production steps. For example, by implementing via the controlling and/or monitoring signals a respec-tive temperature threshold in the production process control. In a preferred embodiment the control data is indicative of a machine executable synthesis specification of the polymer, in particular, when a comparison indicates that the determined one or more burning prop-erties of the polymer lies within a predetermined range around one or more provided target burning properties.

Moreover, the process of processing the burning properties can also refer to a step of se-lecting one or more polymers based on respectively determined one or more burning prop-erties. For example, if for a plurality of potential polymers respective one or more burning properties have been determined, the selecting can comprise comparing the one or more burning properties of the different polymers to predetermined selection criteria and select the polymers for which the determined one or more burning properties fulfill these criteria. In particular, in an embodiment the method comprises receiving a target one or more burn-ing properties for a polymer and comparing the received target one or more burning prop-erties with the determined one or more burning properties and providing depending on the comparison control data. The control data can refer to any signal that allows for a further control and/or monitor of a technical system or to derive directly or indirectly a signal for a further control and/or monitor of a technical system. For example, the control data can be adapted to control an interface for providing the result of the comparison on the interface. In a preferred embodiment the comparison refers to a validation of the target one or more burning properties, wherein the validation is positive if the determined one or more burning properties fall within a predetermined range around the target one or more burning proper-ties. In this case the control data can be adapted to simply control a user interface to pro-vide an indication of a positive or negative validation result. However, preferably, the control data can include to a recipe, i.e. synthesis specification, of the one or more polymers which fulfill the specified target one or more burning properties, i.e. which are validated positively. A recipe, i.e. synthesis specification, is generally be defined as an instruction on how a polymer can be synthesized. In particular, the recipe comprises the starting substances and the respective parameters for polymerization from the starting substances. Preferably, the control data comprise a recipe in a form that directly allows an automatic controlling and/or monitoring of respective industrial systems or labor equipment for producing the polymer. In particular, it is preferred that the control data is indicative of a machine execut-able synthesis specification of the polymer, when the result of the comparison refers to the determined one or more burning properties being within a predetermined range around the target one or more burning properties.

In a preferred embodiment the method further comprises providing as digital representation of the polymer a synthesis specification and determining the characterizing parameters, for example, in form of polymer characterizing parameters, preferably, as polymer descriptors, from the synthesis specification. In particular, the synthesis specification, i.e. recipe, com-prises information on the polymer synthesis of the polymer, for instance, on the starting substance and process by which respective starting substances are covalently bonded to form the polymer chain or network of the polymer. The method then comprises determining characterizing parameters, for instance, the polymer descriptors, from the synthesis spec-ification. Optionally, from a synthesis specification the subgroups can be determined and the polymer characterizing parameters can then be determined based on subgroup char-acterizing parameters of the subgroups, for instance, from a database or utilizing known characterizing parameter determination algorithms. In a preferred embodiment, further from the synthesis specification utilized catalysts and/or non-reactive process ingredients are determined. In this case it is preferred that this information is also utilized together with the characterizing parameters, in particular, the polymer characterizing parameters, by the burning property model for determining the one or more burning properties. Preferably, characterizing parameters are also determined for the catalysts and/or non-reactive pro-cess ingredients and the respective characterizing parameters are also used for determin-ing the physicochemical parameters of the polymer. Preferably, the characterizing param-eter for the catalysts and/or non-reactive process ingredients refers to an amount of the respective ingredient, for example, a molar mass, a molar percentage, etc. and is taken into account for determining a polymer characterizing parameter for the polymer.

In a preferred embodiment, the determining of polymer characterizing parameters from the synthesis specification comprises identifying types and amounts of subgroups based on the synthesis specification, for instance, as characterizing parameters of the subgroups, and determining the polymer characterizing parameters based on the identified types and amounts of subgroups. Generally, the types of subgroups can refer to predetermined types or classes that are associated with specific characterizing parameters, e.g.. physicochem-ical parameters, of the subgroups, and thus with specific characterizing parameters of a polymer comprising these subgroups. However, since the general characterizing parame-ters of a polymer and hence the polymer characterizing parameters can also depend on the amount of a subgroup present in the polymer that amount can also be taken into ac-count. In a preferred embodiment the determination of the type and amount of subgroups takes into account information provided by the synthesis specification indicative of the type of polymerization. The information on the type of polymerization that can be utilized can refer, for instance, to whether the polymerization refers to a polycondensation, polyaddition, radical polymerization, cationic polymerization, anionic polymerization, or coordinative chain-polymerization. Preferably, for each type of polymerization rules are predetermined that can be applied to determine the subgroups of the polymer. For example, rules can be predetermined that determined which functional groups of monomers in the synthesis spec-ification react with which prioritization to which functional groups of the synthesized polymer. The rules can be based, for instance, on kinetic considerations. Based on the number and type of polymerized functional groups the subgroups can be determined and a number and type of the subgroups can be calculated.

In an embodiment the determination of the amount of subgroups comprises determining the amount of at least one of, amide, ester, thioester, carbonate, ether, amine, urea, ure-thane, thiourethane, isocyanurate, biuret, allophanate, acetal, Michal-adduct, radically pol-ymerized double bond, siloxane, silane, silazane, phosphazene groups as well as residual amine, aldehyde, ketone, epoxide, aziridine, isocyanate, alcohol, thiol, carboxylic acid, acyl halogenide, α, β-unsaturated carbonyl groups, α, β-unsaturated carboxyl and double bond groups in the polymer based on the synthesis specification.

In an embodiment, the polymer comprises the shape of a polymer foam, wherein a) the digital representation is further indicative of or associated with foam characteristics of the polymer foam, wherein the foam characteristics are indicative of characteristics of the foam structure of the polymer foam, and b) the burning property model is adapted to determine the one or more burning properties for the polymer foam further based on the foam char-acteristics. Generally, foams refer to materials that are formed by trapping pockets of gas in a liquid or solid base material. Thus, the polymer comprising the shape of a polymer foam refers to a polymeric base material in which pockets of gas have been trapped. Thus, generally the characteristics of a foam are defined by characteristics of the base material, in particular, by mechanical characteristics of the base material, and further the character-istics provided by the specific structure of the foam, in particular, by the structure of the gas pockets within the foam. For example, a size, distribution and density of the cavities, i.e. gas pockets, within the foam not only influence the mechanical structure of the foam but can also influence the burning properties of the foam. Moreover, the gas filling the cavities also provides an additional influence in particular on the burning properties, for example, if the gas comprises a fire retarding characteristic, a high inflammability of a polymer forming the foam can be in some cases be compensated leading to an overall acceptable inflam-mability. Moreover, polymers comprising the shape of the polymer foam are used in a wide variety of applications since the foaming of the polymer allows to further alter the charac-teristics of the polymer, in particular, the mechanical characteristics, advantageously re-duce the weight of respective foam products compared to a non-foaming material and to reduce the amount of resources used for a product. Accordingly, it is advantageous for such applications to also take the foam characteristics of the polymer foam into account when determining the burning properties. In particular, the burning property model can be trained based on training datasets in which the polymers refer to a polymer foam and the respective parameters of the polymer foam are further provided as part of the training da-taset. This allows to determine the burning properties of a polymer foam very accurately based on the provided burning property model, the burning test conditions and the digital representation, in this case, further comprising the foam characteristics. Preferably, the foam characteristics refer to at least one of structural characteristics, compositional char-acteristics, topology characteristics, and foaming process characteristics. Structural char-acteristics can, for instance, refer to the structure of the polymer foam like a size, distribu-tion or density of the cavities provided in the foam. Compositional characteristics can refer to the composition of the polymer foam, in particular, to the gas utilized in the cavities or to gas polymer interactions during the forming of the cavities. Topology characteristics can refer to a 3D model of the shape of the formed foam structure, for instance, of the cavities. Further, the foaming process characteristics refer, for example, to process parameters of the foaming process, for example, to utilized blowing agents, temperature profiles, pressure profiles, etc. Generally, the polymer foam can be produced utilizing a respective synthesis specification that utilizes chemical reactions within the used base materials to produce gas and thus initiate the foaming process of the polymer foam. However, the polymer foam can also be produced from any already produced base polymer, for instance, provided in the form of polymer pellets, in a foaming process in which the base polymer is heated and a respective blowing agent is utilized for mixing gas into the polymer to form the polymer foam. Thus, the foam characteristics can be provided for any form of production of the polymer foam. Preferably, the foam characteristics comprise at least one of information on a gas filling the cavities of the foam and an average size of the cavities in the foam.

In an embodiment, the provided test information is indicative of an intended application of the polymer and wherein the burning test method and the burning test parameters are de-termined based on the intended application. The intended application can refer to any in-tended application of a product in which the polymer should be utilized. For example, the intended application can refer to an intended application in a seat in a public transport, as construction material in a building construction, as material in an automotive context, etc. Generally, each intended application of a polymer is associated with different safety re-quirements, in particular, with respect to a burning behavior of the utilized materials. In most cases, the respective burning behavior and safety requirements for the respective applications are even standardized or regulated by respective authorities. Thus, from the intended application the respective burning test methods and burning test parameters can directly be derived. For example, for common intended applications a respective list of as-sociated burning test methods and burning test parameters can be stored and the provided test information indicating the intended application can then be utilized to access the stored burning test method and burning test parameters associated with the intended application.

In a further aspect an interface method for providing an interface is presented, wherein the interface method comprises a) receiving as input a digital representation of a polymer and of burning test conditions via a user interface and providing the received digital represen-tation and the burning test conditions to a processor performing the method as described above, and b) providing the determined one or more burning properties of the polymer to a user via a user interface as a result, wherein the result is received from the processor performing the method as described above.

In a further aspect, a computer-implemented training method for training a data-driven based burning property model for parameterizing the burning property model is presented, wherein the training method comprises a) providing training data associated with a prede-termined burning test method, wherein the training data comprises i) digital representations of a plurality of training polymers indicative of characterizing parameters of each of the training polymers, ii) a plurality of burning test parameters for the predetermined burning test method, and iii) one or more burning properties determined by the respective burning test method associated with the respective burning test parameters for each training poly-mer, b) providing a data-driven based trainable burning property model and c) training the provided data-driven based burning property model based on the provided training data such that the trained burning property model is adapted to determine one or more burning properties of a polymer based on characterizing parameters of the polymer and based on the burning test parameters, and d) providing the trained burning property model. The pro-vided trained burning property model can then be utilized in the computer implemented method described above.

In a further aspect, an apparatus for determining burning properties usable for determining a burning behavior of a polymer is presented, wherein the apparatus comprises one or more processors configured for performing the functions a) providing a digital representa-tion of the polymer indicative of or associated with characterizing parameters of the polymer, wherein the characterizing parameters are indicative of physical and/or chemical charac-teristics of the polymer, b) providing a digital representation of burning test conditions in-dicative of or associated with a burning test method and burning test parameters, wherein the burning test method is indicative of a standardized test method for determining experi-mentally a respective burning property of a polymer and wherein the test parameters are indicative of a specific test procedure of the burning test method, c) providing a burning property model based on the provided burning test conditions, wherein the burning property model is adapted to determine one or more burning properties of a polymer with respect to the respective burning test method, wherein the burning property model is a data-driven model parameterized with respect to the respective burning test method to determine one or more burning properties of a polymer based on the characterizing parameters and the burning test parameters, and d) determining the one or more burning properties of the pol-ymer based on the provided burning property model, the burning test conditions and the digital representation of the polymer.

In a further aspect, an interface apparatus for providing an interface is presented, wherein the interface apparatus comprises one or more processors configured for performing the functions a) receiving as input a digital representation of a polymer and of burning test conditions via a user interface and providing the received digital representation and the burning test conditions to a processor performing the method as described above, and b) providing the determined one or more burning properties of the polymer to a user via a user interface as a result, wherein the result is received from the processor performing the method as described above.

In a further aspect, a training apparatus for training a data-driven based burning property model for parameterizing the burning property model is presented, wherein the training apparatus comprises one or more processors configured for performing the functions a) providing training data associated with a predetermined burning test method, wherein the training data comprises i) digital representations of a plurality of training polymers indicative of characterizing parameters of each of the training polymers, ii) a plurality of burning test parameters for the predetermined burning test method, and iii) one or more burning prop-erties determined by the respective burning test method associated with the respective burning test parameters for each training polymer, b) providing a data-driven based traina-ble burning property model, c) training the provided data-driven based burning property model based on the provided training data such that the trained burning property model is adapted to determine one or more burning properties of a polymer based on characterizing parameters of the polymer and based on the burning test parameters, and d) providing the trained burning property model.

In a further aspect, a computer program product for determining burning properties usable for validating a burning behavior of a polymer is presented, wherein the computer program product comprises program code means for causing the apparatus as described above to execute the method as described above.

In a further aspect, a computer program product for training a data-driven based burning property model is presented, wherein the computer program product comprises program code means for causing the apparatus as described above to execute the method as de-scribed above.

It shall be understood that the methods as described above, the apparatuses as described above and the computer program products as described above have similar and/or identi-cal preferred embodiments, in particular, as defined in the dependent claims. Moreover, also the training method as described above, the training apparatus as described above, and the training computer program product as described above have similar and/or identi-cal preferred embodiments, in particular, as defined in the dependent claims.

It shall be understood that a preferred embodiment of the present invention can also be any combination of the dependent claims or above embodiments with the respective inde-pendent claim.

These and other aspects of the present invention will be apparent from and elucidated with reference to the embodiments described hereinafter.

BRIEF DESCRIPTION OF THE DRAWINGS

In the following drawings:

Fig. 1 shows schematically and exemplarily an embodiment of a system comprising an apparatus for determining one or more burning properties of a polymer,

Fig. 2 shows schematically and exemplarily a flow chart of a method for determining one or more burning properties of a polymer,

Fig. 3 shows schematically and exemplarily a flow chart of a method for training a burning property model for determining one or more burning properties of a polymer,

Fig. 4 shows schematically and exemplarily a flow chart of an embodiment of a method for determining one or more burning properties of a polymer,

Fig. 5 shows schematically and exemplarily an optional extension of a method for determining one or more burning properties of a polymer,

Figs. 6 to 8 show schematically and exemplarily a block diagram of a system architecture of a system and apparatus for determining one or more burning properties of a polymer,

Figs. 9a, b shows schematically and exemplarily an output and input screen of an exe plary user interface, and

Figs 10 to 14 show schematically and exemplarily representative diagrams of burning test methods for measuring one or more burning properties.

DETAILED DESCRIPTION OF EMBODIMENTS

Fig. 1 shows schematically and exemplarily an embodiment of a system 100 comprising an apparatus 110 for determining one or more burning properties of a polymer that are usable for validating a burning behavior of a polymer. Further, the system 100 comprises a training apparatus 130 for training a burning property model utilized in the apparatus 110, a database 140 in which determination results of the one or more burning properties of a polymer can be stored and a production system 120 for producing a product, in particular, comprising the polymer, that can be controlled utilizing the determined one or more burning properties.

The apparatus 110 comprises one or more processors configured to perform a method for determining one or more burning properties of a polymer. In particular, the one or more processors can be configured to provide functional units performing one or more functions of the method. In particular, the one or more processors can be configured to perform the functions provided by a digital representation providing unit 111, a burning test conditions providing unit 112, a model providing unit 113, a determination unit 140 and optionally an output and/or control unit 115 that can be adapted to output the determined one or more burning properties and/or to provide control data for controlling and/or monitoring a produc-tion process of the production system 120 based on the determined one or more burning properties.

The digital representation providing unit 111 is adapted to provide a digital representation indicative of polymer characterizing parameters, in particular, polymer descriptors, of a pol-ymer for which one or more burning properties should be determined. The digital represen-tation providing unit 111 can refer, for instance, to an input unit into which a user can input the respective digital representation. Moreover, the digital representation providing unit 111 can refer to or be part of a user interface that allows the user to interact with the apparatus 110 and/or the database 140. However, the digital representation providing unit 111 can also refer to or be communicatively coupled with a storage unit on which the digital repre-sentation of the polymer is already stored. Generally, the digital representation can directly comprise the polymer characterizing parameters that are indicative of parameters quanti-fying characterizing parameters of the respective polymer. However, instead of directly providing the polymer characterizing parameters also a synthesis specification of the poly-mer can be provided. In this case, it is preferred that the digital representation providing unit 111 is further adapted to determine the polymer characterizing parameters from the synthesis specification. In particular, it is preferred that the digital representation providing unit 111 is adapted to identify from the synthesis specification types and amounts of sub-groups of the polymer and to determine the polymer characterizing parameters based on the identified types and amounts of subgroups. In particular, the digital representation providing unit 111 can be adapted to determine for each identified subgroup respective subgroup characterizing parameters, for instance, by accessing a database on which for a plurality of the most relevant subgroups respective characterizing parameters are stored. The characterizing parameters of the polymer can then be determined based on the sub-group characterizing parameters of the subgroups and preferably, also on the determined amount and type of the subgroups, for example, by weighted averaging of the subgroup characterizing parameters of the subgroups. The digital representation providing unit 111 is then adapted to provide the digital representation comprising the polymer characterizing parameters, for instance, to the determination unit 114.

In a preferred example, the polymer is used in the form of a polymer foam. Since in this case the foam structure of the polymer can influence the outcome of the burning tests and thus the burning properties, it is preferred that the foam structure of the polymer foam is taken into account. In particular, it is preferred that the digital representation is further in-dicative of the foam characteristics of the polymer foam. For example, the digital represen-tation can then refer to a 3D simulation or model of the polymer foam allowing to derive respective foam characteristics, like, a density of the cavities in the foam, a distribution of the cavities or the sizes of the cavities, etc. However, the digital representation can also refer to a synthesis specification of the polymer foam that allows to derive as foam charac-teristics for example the process parameters that lead to the formation of the foam when executing the synthesis specification. Further, the digital representation can also directly comprise the foam characteristics.

The burning test conditions providing unit 112 is adapted to provide a digital representation of burning test conditions. The burning test conditions providing unit 112 can refer, for in-stance, to an input unit into which a user can input a respective burning test conditions. For example, a user interface can be provided that allows a user to input a burning test condi-tions. In particular, the interface can be configured to allow the user to select from a plurality of predetermined burning test methods and/or applications of the product. Based on the selection, the burning test conditions providing unit 112 can then be adapted to determine as part of the burning test conditions the respective burning test method and one or more test parameters of the burning test method. For example, based on a selected intended application of a product the burning test conditions providing unit 112 can be configured to access a storage unit like storage unit 140, on which burning test methods and possible test parameters associated with the respective application are stored. For example, for an intended application of the polymer respective rules and safety considerations can be de-termined by a respective authority and the respective application can then be associated with burning test methods and test parameters that allow to show whether the polymer fulfils the respective regulation.

Generally, the burning test conditions is indicative of or associated with a burning test method and burning test parameters. Burning test methods are indicative of a standardized test method for determining experimentally a respective burning property of a polymer and test parameters are indicative of a specific test procedure of the burning test method. In the following, some preferred examples of burning test methods and corresponding test parameters and possible resulting burning properties are described with respect to Figs 9 to 12.

Preferably the burning test methods refer to at least one of, but are not limited to, single burning item (EN 13823: 2015) , single-flame source test (EN ISO 11925-2: 2020) , UL94 and UL 94 HB (EN 60695-11-10: 2014 and EN 60695-11–20: 2016, respectively) , an ASTM E84 test, as well as cone calorimeter (ISO 5660-1: 2015) . All these burning test methods are characterized in that they require specific test conditions as defined in the respective norm and that the burning behavior is evaluated based on specific burning properties that are measured during the burning test as defined in the respective burning test method norm.

Fig. 9 shows a representation of a test configuration of a single burning item test method (EN 13823: 2015) . The test conditions are characterized by specific sample dimensions and the test specimens are pre-conditioned before testing. The test specimens are mounted in a specific way, for example, as shown in Fig. 9 and subjected to a flame of a defined energy output per unit area. These conditions can, for example, be reflected by respective test parameters referring to these conditions. The O₂ consumption, CO₂ and CO formation are recorded during the test. Further, the burning behavior of the probe is evaluated visually. From these observables the output parameters, i.e. the burning properties, are derived, which are an index representing the fire growth rate (FIGRA) , the total heat released over the first 10 minutes (THR_600s) , occurrence of a lateral flame spread to the end of the spec-imen (LFS_edge) , an index representing the smoke growth rate (SMOGRA) , the total smoke produced over the first 10 minutes (TSP_600s) , and a parameter defining the formation of flaming droplets and particles including the afterburn time (FDP) . Based on these output parameters, i.e. burning properties, the burning behavior can then be assessed.

Fig. 10 shows a representation of a test configuration of a single-flame source test method (EN ISO 11925-2: 2020) . The test conditions are characterized by specific sample dimen-sions and the test specimens are pre-conditioned before testing. The test specimens are mounted in a specific way as shown in Fig. 10 and subjected to a flame of defined size. The flame is brought in contact with the specimen in a defined angle and kept in contact with the specimen for a defined time. The contact point might be at the edge of the speci-men or at the surface. These conditions can be defined by the test parameters, in particular, the test parameter can determine whether the contact point is the edge or the surface of the specimen for a specific determination of burning properties. The flame is removed from the specimen and the observation of the specimen is continued for a defined time. The output of the test is characterized by a maximum flame height during the observation period and by the afterburn time after removal of the flame from the specimen, as exemplary burn-ing properties associated with this test.

Fig. 11 shows a representation of a test configuration of a UL94 and UL 94 HB test methods (EN 60695-11-10: 2014 and EN 60695-11–20: 2016, respectively) . The test conditions are characterized by specific sample dimensions and the test specimens are pre-conditioned before testing. The thickness of the sample may vary in a range defined by the norm. The test specimens are mounted in a specific way (horizontally (UL94 HB) or vertically (UL94) ) and subjected to a flame of defined size. The flame is brought in contact with the specimen in a defined angle and kept in contact with the specimen for a defined time. The flame is removed from the specimen and the afterburn time is recorded. The flame is again brought in contact with the specimen for a defined time and removed thereafter. The afterburn time is recorded again. These condition can be provided by the test parameters, in particular, the thickness of the sample can be used for this test method as further input to the burning property model. The output of the test and thus the burning properties can refer to the afterburn time of any single specimen after the first removal of the flame, combined after-burn time of a set of specimens after pre-conditioning of the specimens, afterburn time and afterglow time of any single specimen after the second removal of the flame, formation of burning droplets and ignition of cotton positioned below the specimen, burning of the spec-imen to the clamp.

Fig. 12 shows a representation of a test configuration of a Cone Calorimeter test method (ISO 5660-1: 2015) . The test conditions are characterized by specific sample dimensions and the test specimens are pre-conditioned before testing. The specimen thickness may vary in a range defined by the norm. The test specimens are mounted horizontally below a conical radiant electrical heater as shown in Fig. 12 and subjected to a heat flux generated by the conical radiant electrical heater. The heater might produce a heat flux unto the spec-imen surface of up to 75 kW/m². The heating power may be selected prior to testing. A spark igniter as defined in the norm is oriented closely above the specimen surface and ignites combustion gases formed during testing. These conditions can be described by the test parameters, and in particular, the test parameters can define the thickness of the spec-imen and the heating power as further input to a respective burning property model for this test method. The O₂ consumption, CO₂ and CO formation are recorded. From these ob-servables the output parameters, i.e. burning properties, are derived. The output parame-ters may be, but are not limited to, peak heat release rate (pHRR) , total heat released during the measurement (THR) , maximum average rate of heat emission (MARHE) , effec-tive heat of combustion (EHC) , total mass loss, mass loss rate, total smoke production (TSP) , smoke formation per unit area.

In the following some further possible the burning test methods are described that can be selected as burning test method for respective applications in the method described above for determining a target polymer with respective one or more target properties. In EN ISO 4589-2 a burning behavior is determined by determining an oxygen index. ISO 5658-2 de-termines a flame growth by measuring a critical flux at extinguishment. For a target appli-cation referring to a polymer utilized as or as part of a building material also ISO 5660-1 can be selected for determining a maximal heat release rate per surface area. For a target application referring to a polymer utilized as or as part of a flooring also EN ISO 9239-1 can be selected for determining a critical heat flux at extinguishment. In EN ISO 11925-2 an ignitability when directly subjected to a flame is determined. For a target application referring to a polymer utilized as or as part of a furniture, in particular, a seat, ISO/TR 9705-2 can be utilized to determine a mean heat release. For a target application referring to a polymer utilized as or as part of textile, in particular, bedding, EN ISO 12952-2 can be used to determine an afterglow time. In ISO 2592/ISO 2719 a flash point and combustion point is determined. For a target application referring to a polymer utilized as or as part of an electric cable EN 60332-1-2 can be utilized for determining a length of a burned and un-burned part of the cable and EN 60332-3-24 can be utilized to determining a height of burned and unburned area. For a target application referring to a polymer utilized as or as part of a plastic EN ISO 5659-2 can be selected for determining a maximal optical density of fumes. Further, EN 45545-2: 2013+A1: 2015 can be utilized to determine a conventional index of toxicity. Also NF X70-100-1 and NF X70-100-2 can be utilized for determining toxicity parameters. For a target application referring to a polymer utilized as or as part of an electric cable EN 61034-2 to determine a transmission or EN 50305 can be utilized to determine an ITC parameter for cable used in rail vehicles. For a target application referring to a polymer utilized as or as part of a building material EN 13501-1 can be utilized to determine a plurality of burning properties. Also EN 60695-2-11 and EN 60695-11-10 can utilized for determining respective burning properties.

In particular for target polymers that are to be utilized in or as part of upholstered furniture at least one of the following test methods can be selected EN ISO 12952-1, EN ISO 12952-2, EN 597-1, EN 597-2, NF P92501, NF P92507 M3, EN 1021-1, EN 1021-2, BS 5852, CSE RF 4/83. For target polymers that are to be utilized in or as part of a textile at least one of the following test methods can be selected EN 469, EN ISO 14460: 1999, EN 340, ISO 694d2: 2002, EN 367, EN 470, EN 533, EN ISO 11612: 2008, EN ISO 15025: 2002, EN 1103, EN 13772, EN ISO 13772, EN ISO 12952-1, EN ISO 12952-2, EN 597-1, EN 597-2, EN 1021-1, EN 1021-2, EN 597-1, EN 597-2, DIN 4102, UNI 9175, NFP 92 501-507, Italian UNI 9175.

Generally, for each of the above described burning test methods a respective burning prop-erty model can be trained that is adapted to determined the burning properties of a specific burning test method based on the respective polymer characteristics and/or foam charac-teristics of the polymer and optionally further based on the test parameters as will be ex-emplarily described in the following.

The model providing unit 113 is adapted to provide a burning property model based on the provided burning test conditions, in particular, based on the burning test method. Preferably, the model providing unit 113 is adapted to select the burning property model from a plurality of burning property models stored already on a database. For example, a burning property model can be trained with respect to training data corresponding to one or more specific burning test methods. For example, for each of the above described exemplary burning test methods measurement data of the resulting burning properties of a plurality of poly-mers can be provided as training data and then for each burning test method a respective burning property model can be trained. Moreover, in some cases a burning test method can allow to provide a value range of test parameters, wherein in this case the training data can also comprise the measurement results for a polymer with respect to the different test parameters allowed by the burning test method. In this case, the burning property model can be trained to also utilize the test parameters for a respective burning test method as input for determining the one or more burning properties.

Moreover, in the preferred case that the polymer if provided in form of a polymer foam, the burning property model is then trained with training data referring to a polymer foam. Pref-erably, the burning property model is in this case trained to also take the foam characteris-tics as further input into account. Thus, in this case the burning property model is configured to determined the one or more burning properties based on the characterizing parameters and the foam characteristics, and optionally also the test parameters of a specific burning test method.

The burning property model is a data-driven model parameterized such that it can deter-mine the one or more burning properties of the polymer based on the digital representation, in particular, based on the polymer characterizing parameters quantifying the characteriz-ing parameters associated with the polymer. In a preferred embodiment, the data-driven model refers to a machine learning model, for instance, utilizing regression model based algorithms or classifier model based algorithms. A regression model based algorithm can be based on any of a neural network algorithm, a Linear Regression algorithm, a LASSO algorithm, a Ridge Regression algorithm, a MARS algorithm, a Random Forest algorithm, and a Boosted Trees algorithm. A classifier based model algorithm can be based on any of a Random Forest algorithm, a Logistic Regression algorithm, and a SVM algorithm. The inventors have found that for most applications, in particular, Linear Regression, Random Forest and MARS based algorithms are suitable.

The burning property model can be trained, for instance, utilizing training apparatus 130. In particular, the training apparatus 130 comprises a training data providing unit 131 for providing training data for training the data-driven based burning property model. The train-ing data comprises a) polymer characterizing parameters of a plurality of training polymers, and b) one or more burning property measured or derived for each training polymer in association with a respective burning test method. Optionally, if the burning test method allows for a variation of test parameters characterizing the test method, then the training data can also comprise for each polymer the test parameter values for which the burning properties have been measured. Further, if the burning property model should be utilized in the context of a polymer foam, the training data can be provided for a plurality of respec-tive polymer foam, wherein in this case further the foam characteristics of each polymer foam can be provided as part of the training data. Generally, the training data can be de-signed to cover predetermined polymer types or different foam characteristics for a prede-termined burning test method. Known methods for designing and optimizing training data for a predetermined burning test method space can be utilized such that the training space is well covered with training data and that random outliers are avoided. In normal applica-tion scenarios the inventors have found that with training data comprising approximately 50 training polymers an acceptable accuracy of the determined properties can be achieved, wherein the accuracy can be increased if more training polymers are provided in the train-ing data. Preferably, more than 100 training polymers are utilized.

Further, the training apparatus 130 comprises a model providing unit 132 adapted to pro-vide a data-driven based trainable burning property model, for instance, a burning property model comprising parameters that can be set during the training process for training the burning property model. For example, a trainable burning property model can already be stored on a storage unit to which the model providing unit 132 can have access for provid-ing the same. Moreover, the training apparatus 130 comprises a training unit 133 for train-ing the provided data-driven based burning property model based on the provided training data. In particular, the training can refer to varying the parameters of the burning property model based on the respective training data until the burning property model is adapted to determine one or more burning properties of a polymer based on a digital representation. Generally, any known training algorithms for training data-driven, in particular, machine learning based models can be utilized. Preferably, during the training of the burning prop-erty model also the characterizing parameters of the polymer that have the most influence on the one or more burning properties in the respective burning test method are determined and the model is then trained based on these most influential characterizing parameters. For determining these most influential characterizing parameters, for example, feature-se-lection or statistical-hypothesis-test tools can be utilized. In particular, the characterizing parameters can be utilized to represent the application space, wherein the application space is then defined by the characterizing parameters of the polymer and optionally the foam characteristics. Then algorithms for proposing new experimental runs can be applied in the application space, for instance, space-filling design to cover the application space with as few training data as possible or active learning to search for the optimal polymer foams iteratively.

The training apparatus 130 then comprises a trained model providing unit 134 that is adapted to provide the trained burning property model, for instance, to a storage unit on which respectively trained burning property models for different habitat and/or different types of polymers are stored. However, the trained model providing unit 134 can also be adapted to directly provide the trained burning property model, for instance, to the burning property model providing unit 113 of apparatus 110.

In all cases, the burning property providing unit 113 is then adapted to provide a suitable trained burning property model to the property determination unit 114. The determination unit 114 can then utilize the burning property model and the provided digital representation for determining the burning property. In particular, the determination unit 114 can be adapted to utilize the polymer characterizing parameters and optionally the foam charac-teristics indicated by the digital representation as input to the burning property model that has, as already described above, been trained to then provide as output a determination for one or more burning properties for which it has been trained. An output unit 116 referring, for instance, to a display, can then be adapted to output the determined one or more burn-ing properties. However, the output unit 116 can additionally or alternatively be adapted to provide the determined burning property to a database 140 for storing the polymer or pol-ymer foam in association with the determined one or more burning properties for future usage. In particular, the output unit 116 can be adapted, if for different polymers burning properties have already been determined and, for instance, been stored on the storage unit, i.e. database 140, to select a respective polymer based on predetermined criteria with re-spect to the burning property. The output unit 116 can then be adapted to provide and/or output the selected polymer and its burning property. This is in particular suitable in cases in which a user searches for a polymer with a specific burning property or burning behavior, from a plurality of candidate polymers.

Optionally, the apparatus 110 can comprise the control unit 115 that is adapted to provide control data based on the determined one or more burning properties for controlling and/or monitoring a production process of a production system 120. In particular, it is preferred that the control unit 115 is adapted to receive one or more target burning properties for a polymer or polymer foam and to compare the received one or more target burning proper-ties with the determined one or more burning properties and to provide the control data depending on the comparison, preferably, to provide control data that indicate the usage or production of the polymer or polymer foam for which the one or more burning properties have been determined. Moreover, the control data can be indicative of a machine execut-able synthesis specification of the polymer of polymer foam for which the one or more burning properties have been determined, when the result of the comparison refers to the determined one or more burning properties being within a predetermined range around the one or more target burning properties. However, the control unit 115 can also be adapted to control the production process of another product based on the determined one or more burning properties, for instance, to provide control data indicative of a machine executable synthesis specification for another product utilizing or comprising the respective polymer or polymer foam.

Fig. 2 shows schematically and exemplarily a flow chart of a method for determining one or more burning properties of a polymer. In a first step 210, the method comprises providing a digital representation of the polymer, for instance, as described above with respect to Fig. 1. In particular, the digital representation is indicative for characterizing parameters of the polymer that are indicative of physical and/or chemical characteristics of the polymer. In a second step 220, the method comprises providing a digital representation of burning test conditions indicative of or associated with a burning test method and burning test parame-ters. In particular, the burning test conditions can indicate, for example, one of the above described burning test methods and corresponding burning test parameters. In a further step 230, a burning property model is provided based on the provided burning test condi-tions. The burning property model is adapted to determine one or more burning properties of a polymer with respect to the respective burning test method, wherein the burning prop-erty model is a data-driven model parameterized with respect to the respective burning test method such that it can determine one or more burning properties of a polymer based on the characterizing parameters of the polymer and the burning test parameters. Then, the method comprises a step 240 of determining the one or more burning properties of the polymer based on the provided burning property model, the burning test conditions and the digital representation of the polymer. In a step 250, the method can additionally also com-prise generating control data that allow for a controlling and/or monitoring of a production process of a product, for instance, the polymer or a product comprising the polymer, as already described above in more detail.

Fig. 3 shows schematically and exemplarily a flow chart of a method for training the data driven based burning property model utilized, for instance, in the method 200 discussed with respect to Fig. 2. Generally, the method 300 can be performed, for instance, by re-spective units of the training apparatus 130 as described with respect to Fig. 1. The method 300 comprises a step 310 of providing training data for training the data driven based burn-ing property model. The training data comprises a) polymer characterizing parameters of a plurality of training polymers, and b) one or more burning properties measured during or derived from a respective burning test method. In particular, the training data can be pro-vided in accordance with the principles described above with respect to the training data providing unit 131 described with respect to Fig. 1. The method comprises further a step 320 of providing a data-driven based trainable burning property model, for instance, a ma-chine learning based burning property model like a neural network. Generally, the step 310 and the step 320 can be performed in arbitrary order or even at the same time. The method 300 then further comprises a step 330 of training the provided data driven based burning property model based on the provided training data, for instance, by varying parameters in the data driven based trainable burning property model, such that the trained burning prop-erty model is adapted to determine one or more burning properties of a polymer based on a digital representation of the polymer. In step 340 the trained burning property model can then be provided, for instance, by storing the trained burning property model on a storage or by directly providing the trained burning property model to the apparatus 130 as de-scribed with respect to Fig. 1.

In the following, more detailed preferred examples of the above described method and the corresponding apparatus will be described. An exemplary embodiment of the method can consist of steps described in the following. A schematic and exemplary flow chart of an exemplary embodiment of the method is provided by Fig. 4. In this exemplary embodiment, the method starts with requesting, for instance, via a user interface, a digital representation of a new polymer. Further, a target application of the new polymer can be requested, for instance, also via the user interface. The target application can refer, for instance, to how the new polymer for which the digital representation is provided should be utilized in a product. The respective target application is then, for instance, indicative of a respective burning test method. For example, a list can be presented via a user interface to a user from which the user can select respective target applications and based on the respective selection further a selection of burning test methods that are associated with the target application can also be provided for the user to select. Based on the target application, in particular, based on the burning test method indicated by the target application, the respec-tive burning property model can be selected. Optionally, further preselected conditions in-dicated by the selected burning property model can be requested. For example, the burning property model can be adapted to utilize further descriptors, for instance, optional test pa-rameters, foam characteristics, application constraints, etc. that can be requested if neces-sary and that might allow the burning property model to determine the one or more burning properties with a further accuracy or specifically for the constrains. Moreover, from the pro-vided digital representation the polymer characterizing parameter values can be derived, wherein also the polymer characterizing parameters can depend on the provided target application. Further details on the possibilities of deriving polymer characterizing parameter values will be described in the following with respect to Fig. 5. Utilizing the selected burning property model and the derived characterizing parameter values allows then to provide respective determined one or more burning properties, i.e. a respective target performance.

Fig. 5 shows schematically and exemplarily a preferred method 500 for deriving character-izing parameter values, in this example referring to polymer descriptors, from a digital rep-resentation of a new polymer. In a first step 510 a digital representation of the polymer is provided. The digital representation can directly comprise the polymer descriptors, wherein in this case the steps shown in Fig. 5 until step 550 can be omitted. However, in many cases the polymer descriptors first have to be determined based on the provided digital representation referring in such a case, for example, to a recipe for the synthesis of the polymer, or to a chemical representation of the polymer indicating the chemical compo-nents and bonds in the polymer. In this step 510 the digital representation can comprise any one or more of the following information: an amount of monomer components; an amount of non-monomer components, like initiators, fillers, additives; a reaction condition, like temperature, vessel, pressure, stirring rate; condition profile, e.g. temperature profile, pH value, solvents; feed profiles; type of polymerization, e.g. radical, cationic, anionic, pol-ycondensation, polyaddition, polyether formation; post-processing, like amount of compo-nents, conditions, as well as temperature and feed profiles; type of post-processing, e.g. radical, cationic, anionic, polycondensation, polyaddition, polyether formation; chemical in-formation on components, like mixtures, connectivity of non-polymeric pure compounds, composition of polymeric pure compounds on the basis of subgroups, connectivity of the monomers associated to the subgroups in the polymeric pure components; for block-co- polymers also information, in which block each monomer and reactive prepolymer is incor-porated; for structures/layered materials and composites also information in which phase/layer each component is included. If such information is not provided by the digital representation directly, in optional step 520, the reactive components and subgroups can also be derived from the digital representation, for example, from the recipe.

If the provided information indicates the presence of a mixture, then in a following step the mixture is decomposed into its pure components and each polymer component is treated as input polymer. Moreover, the polymer composition can also be transformed into mol%, wt%, vol%or, absolute mol, if necessary.

In the next step 530 the polymerizable components can be transformed into subgroups, e.g. repeating units, and the subgroups are determined as different types. For example, polymerizable subgroups can be determined based on connectivity information of non-pol-ymeric pure compounds by using SMARTS, for instance, via KNIME workflow. Also con-nectivity information of all possible subgroups can be derived from connectivity information of non-polymeric pure compounds by using reaction SMARTS, for example, also via KNIME workflow

After the subgroups and their types have been determined, in step 540 the type of de-scriptors that should be utilized can be provided. However, the descriptors can also be determined without first selecting the type of the subgroups. In order to decrease the com-putational resources for the method it is preferred that in a step 541 it is determined whether subgroup descriptors associated with a respective type of subgroup are already stored in a database, for example, if entries for subgroups with identical connectivity information al-ready exist in the database. If this is the case the respective associated subgroup descriptor can be directly downloaded, for example, in step 544. If the determined type of subgroup is not stored on the database the subgroup descriptors that are associated with a respective type of subgroup can be determined, for example, in step 542. For example, either a 3D structure of respective types of subgroups can be derived based on connectivity information and an automatic computation of subgroup descriptors can be started using, for instance, a computer cluster, or already existing machine-learning determinations can be utilized as subgroup descriptors. Generally, it is preferred that if computations on new subgroups are necessary, in step 543, the results are stored in the database after the computations are finished. Optionally further subgroup descriptors can be provided from a topological analy-sis of the subgroups, a quantum chemical computation, a molecular dynamics computation, coarse-grained methods, finite-element computations and kinetic simulations. In particular, polymer reaction engineering methods can be used to derive subgroup descriptors that allow to take into account a microstructure of the polymer.

In step 531 the amount of subgroups, i.e. of each type of subgroup, is determined, for example based on the provided recipe information for the polymer and provided in step 532. For example, the amount can be determined by counting an amount of polymerizable groups per polymerizable component, optionally, including prepolymers. In this case, infor-mation on polymerizable groups can be derived from non-polymeric components and the such determined amount can be added to a count of the number of, optionally, non-pol-ymerized, polymerizable groups of the subgroups for polymeric components based on the composition of the polymeric components to determine a resulting amount. Further, it is preferred that the amount of polymerizable groups originating from agents used for post-processing after polymerization is removed from the resulting amount.

However, although it is preferred that the polymer descriptors are derived from polymer subgroups, in other embodiments of the invention the polymer descriptors can also be de-rived in other ways, for instance, by directly determining the polymer descriptors from the complete polymer. Moreover, the polymer descriptors for respective polymers can also be already stored on a storage unit such that the deriving of the polymer descriptors from a digital representation of the polymer can refer to determining from the digital representation information on the polymer that allows to access the database and retrieve the correspond-ing polymer descriptors.

Optionally the derived amounts of subgroups can be used for a further interpretation of the polymer composition. For example, a total number of polymerized functional groups, e.g. double bonds, amine groups, alcohols groups, thiol groups, carboxylic acid groups, isocy-anate groups, epoxide groups, and formed functional groups, e.g. amid groups, ester groups, thioester groups, urea groups, urethane groups, thiourethane groups, ether groups, can be determined. Also the molar weighted total number of polymerized functional groups, the mass weighted total number of polymerized functional groups, the total number of re-sidual functional groups, e.g. double bonds, amine groups, alcohol groups, thiol, groups, carboxylic acid groups, isocyanate groups, epoxide groups, aromatic groups, isocyanurate groups, the molar weighted total number of residual functional groups, the mass weighted total number of residual functional groups, the sum of all residual functional groups, the ratio between functional groups after polymerization, the amount of atoms in a certain oxi-dation state in the polymer, amount of phosphorus atoms in the polymer, the amount of halogen atoms in the polymer, the number of crosslinks in polymer, the molar fraction of crosslinks in polymer, optionally, with mass-weighting as well, the average number of at-oms per subgroup, optionally, per weight as well, the average number of non-H-atoms per subgroup, optionally, per weight as well, the average number of bonds per subgroup, op-tionally, per weight as well, the average number of bonds between non-H-atoms per sub-group, optionally, per weight as well, the average number of rotors per subgroup, optionally, per weight as well, the average number of rotors between non-H-atoms per subgroup, op-tionally, per weight as well, the average number of rings per subgroup, optionally, per weight as well, the average polar surface areas per subgroup, optionally, per weight as well, the average refractivity per subgroup, optionally, per weight as well, the total number of blocks, the molar size of first block, the molar size of last block, the HLB value of polymer, optionally, with area weighted HLB value, the HLB value of block with lowest HLB value, optionally, with area weighted HLB value, the HLB value of block with largest HLB value, optionally, with area weighted HLB value, the HLB value of first block, optionally, with area weighted HLB value, the HLB value of last block, optionally, with area weighted HLB value, the mass of first block, the mass of last block, the area of block with lowest HLB value, the area of block with largest HLB value, the difference of the HLB values of the blocks, op-tionally, with area weighted HLB value, the hydrophilic area of the polymer, the lipophilic area of the polymer, the number of arms for ring-opening-polymerization, or the length of arms for ring-opening-polymerization can be determined.

In step 550 the determined amount and type of the subgroups and the associated subgroup descriptors can be utilized to compute the polymer descriptors. For example, the polymer descriptors can be determined by one or more of molar weighted, e.g. arithmetic, harmonic or logarithmic, averaging, mass weighted, e.g. arithmetic, harmonic or logarithmic averag-ing, volume weighted, e.g. arithmetic, harmonic or logarithmic, averaging, surface area weighted, e.g. arithmetic, harmonic or logarithmic, averaging of the associated descriptors of the subgroups. Moreover, the polymer descriptors can be determined by determining from the associated subgroup descriptors one or more of a molar weighted standard devi-ation, a mass weighted standard deviation, a volume weighted standard deviation, a sur-face area weighted standard deviation, a molar weighted maximum value, a mass weighted maximum value, a volume weighted maximum value, a surface area weighted maximum value, a molar weighted minimum value, a mass weighted minimum value, a volume weighted minimum value, a surface area weighted minimum value, a molar weighted sum, a mass weighted sum, a volume weighted sum, a surface area weighted sum, and a max-imal difference.

In step 560 the derived or provided polymer descriptors can then be provided to the trained burning property model for determining the one or more burning properties, for example, as described with respect to Fig. 4. The polymer descriptors can be all or partially used in the burning property model. If they are partially used, a descriptor selection step is needed, which is also called feature selection. For instance, by doing correlation analysis and clus-tering analysis, the highly correlated descriptor pairs or groups can be detected. The rep-resentative descriptors can then be selected from these descriptor pairs or groups. Op-tionally, the descriptors can then be further selected based on their predictive power or importance for the burning properties. Alternatively, a screening design of experiments can be performed to select the descriptors that are statistically significant. The same process can optionally be performed for the foam characteristics in order to select foam character-istics that are most relevant for the determination of one or more burning properties of polymer foams in a specific burning test method. Based on the selected polymer de-scriptors and, optionally also based on the foam characteristics, an application space can be determined and defined. More data points can be added to this space by space-filling design, optimal design, active learning, etc, which propose new lab runs. The burning prop-erty model is then trained based on the training data set in the application space. The burning property model can generally refer to sparse, e.g. splines, LASSO regression, PLS, and non-sparse, e.g. linear regression, ridge regression, tree methods, kernel based meth-ods, statistical learning models for relating the polymer descriptors to the one or more burn-ing properties of a specific burning test method. Moreover, the burning property model can further provide a reliability estimation of the prediction. For example, kernel density estima-tion can be used to estimate the prediction uncertainty. In step 570 the predicted one or more burning properties, i.e. technical application property, can then be provided to a user, for example, via a user interface.

Fig. 6 illustrates a block diagram of an exemplary system architecture of an automated laboratory system 1000 for synthesizing a polymer with a laboratory equipment control de-vice 1102, a network 1150 and the synthesis specification, i.e. recipe, module 1100/1110, and a client device 1108. The automated laboratory system includes a laboratory equip-ment control device layer 1152 as part of the laboratory equipment control device 1102 as well as a synthesis specification module layer 1154 associated with the synthesis specifi-cation module and a remote control or client layer 1156 associated with the client device 1108. The laboratory equipment control device layer can be split into several hierarchical layers: the hardware, the middleware and the interface layer. The hardware layer relates to hardware resources such as sensors and actuators, in particular for controlling and/or monitoring synthesis of a polymer. The middleware relates to any of the known middleware for laboratory or plant synthesis operations. One example is LABS/QM, providing different abstractions to hardware, network and operating system such as low-level device control and message passing. The communication layer relates to communication protocols one the protocol may be REST, which may be implemented over different transport protocols (i.e. UDP, TCP, Telemetry) that allow the exchange of messages between the laboratory equipment control device and laboratory equipment devices. Such software architecture allows to control and monitor laboratory equipment without having to interact with the hard-ware.

The synthesis specification module layer 1154 may include: a mass storage layer, the com-puting layer, the interface layer. The storage layer is configured to provide mass storage for the data-driven burning property model for providing a recipe, i.e. synthesis specification, of a polymer based on a burning test method, as described in detail above. In particular, the functions performed by the apparatus, as described above, can be provided as program code means stored on the mass storage. Furthermore, synthesis specifications for a plu-rality of polymers can be stored in the mass storage. Such data may be stored in structured databases such as SQL databases or in a distributed file system such as HDFS, NoSQL databases such as HBase, MongoDB. The computing layer may include an application layer that allows to customize the functionalities provided by standard cloud services to perform computing processes based on target properties. Such functionalities can include determining based on a target burning property and the burning property model a digital representation of a target polymer, generating a synthesis specification from the digital representation of the target polymer, and providing the synthesis specification as control data to the laboratory equipment control device.

The interface layer may implement web services, network interfaces as UDP or TCP or Websocket interfaces. For communication with the laboratory equipment control device a REST API is implemented.

The client layer 1156 provides interfaces for end-users. For end-users, the client layer 1156 can run client side Web applications, which provide interfaces to the synthesis specification module layer 1154 or the laboratory equipment control device layer 1152. Users may be provided with a UI for selecting a target burning property and a burning test method for the target burning property, the target burning property may also comprise a range of burning property values. In other examples, the users may be provided with a UI for selecting more than one target burning property and respective values. The applications may be config- ured for users to monitor and control the laboratory equipment control device and the op-eration remotely. In other examples, the client device layer and the synthesis specification module layer may be integrated into one device. The alternatives described here are only for illustration purposes and should not be considered limiting.

Fig. 7 illustrates a block diagram of an exemplarily system architecture of a system and apparatus for generating a burning property model for determining a burning property, a network 2150 and a model generating module 2100/2110 that can be regarded as or com-prising a training model apparatus, a synthesis specification module 1100/1110, and a cli-ent device 2108. The system for generating a burning property model includes a model generating module layer 2154 as part of model generating module and a client layer 2156 associated with the client devices 2108.

The model generating module layer 2154 may include: a mass storage layer, a computing layer, an interface layer. The storage layer is configured to provide mass storage for the data-driven burning property as described above. Furthermore, the mass storage is con-figured for storing synthesis specifications for polymers and measured burning property for one or more habitats. Such data may be stored in structured databases such as SQL da-tabases or in a distributed file system such as HDFS, NoSQL databases such as HBase, MongoDB. The computing layer may include an application layer that allows to customize the functionalities provided by standard cloud services to perform computing processes for generating a burning property model for determining a burning property of a polymer. Such functionalities may include receiving for at least two previously measured polymers their respective digital representations associated with a synthesis specification, measurement data of at least one burning property in at least one habitat for each of the at least two previously measured polymers, receiving at the model generating module the digital repre-sentation of at least one unmeasured polymer, training the model according to the above described training principles based on the digital representation of the at least two previ-ously measured polymers, the measurement data of the burning property in at least one habitat for each of the at least two previously measured polymers, and, preferably, a simi-larity measure between the digital representation associated with the synthesis specifica-tion of each of the at least two previously measured polymers and the respective digital representation associated with a synthesis specification of the at least one unmeasured polymer, and providing via an output interface the burning property model for the burning property. The model generating module layer may be configured for deploying the gener-ated model and the synthesis specification database to the synthesis specification module layer. This may include storing the generated model and the synthesis specification data-base in the mass storage devices associated with the synthesis specification module.

The model generating module layer may further be configured for determining a digital representation of the polymer associated with the synthesis specification from the synthesis specification. The digital representation may include a set of polymer characterizing pa-rameters and polymer characterizing parameter values associated with a synthesis speci-fication of each measured polymer. One way of deriving these polymer characterizing pa-rameters can be to apply the SMILES algorithm or any other already above described prin-ciple. In the case, where the model is generated based on the digital representation derived from the recipe, a relation between the synthesis specification and the characterizing pa-rameters may be stored in the mass storage devices associated with the model generating module. In such cases, deploying the model comprises providing that relation.

The interface layer may implement web services, network interfaces as UDP or TCP or Websocket interfaces. For communication with the client device a REST API is imple-mented in this example. The client layer 2156 provides access to mass storage devices, that contain synthesis specifications for polymers, and for at least two polymers at least one biodegradability. The client layer further provides an interface for end-users. For end-users, the client layer 2156 may run client side Web applications, which provide interfaces to the model generation module layer 2154 or the mass storage devices associated with the client layer. Users may be provided with a UI for selecting a burning test method for which the burning property shall be determined. The user may further be provided with a UI for selection of the synthesis specification data. The user interface may also provide an option for uploading the selected data to the model generating module layer and optionally an option to initiate model generation.

Fig. 8 shows an exemplary system 700 for producing a chemical product based on a syn-thesis specification generated according to the invention. In this example the system com-prises a user interface 710 and a processor 720, associated with a control unit 740. The user interface 710 and the processor 720 can be associated with or realized in accordance with the principles described above, in particular, can be adapted to perform a computer implemented method to determine a target polymer and/or synthesis specification based on a determined burning property, as described above. The control unit 740 is, for example, configured for receiving control data generated according to the invention as described above, in particular, to receiving control data generated based on a synthesis specification of a polymer comprising a target burning property. In this example the control data is pro-vided from a data base 730, in other examples, however the control data can also be pro-vided from a server or any other computational unit for distributing data. Vessels 750, 752 each contain a component of the chemical product, for example, pre-polymers, catalysts, etc. In general, more than two vessels are present, however, in this example for illustrative purposes only two are shown. Valves 760, 762 are associated with vessels 750, 752. Valves 750 and 752 can be controlled to dose appropriate amounts of each component into reactor 770, according to the synthesis specification. A motor 800 of a mixer 780 may also be controlled by the control unit according to the synthesis specification. An optional heater 790 may also be controlled according to the synthesis specification. Finally, an exit valve 810 in fluid communication with the reactor may be controlled by the control unit to provide the chemical product to a container or test system 820.

Figs. 9a and b show exemplarily and schematically a possible user interface for interfacing, for example, with a processor performing the above described method for determining the burning behavior of a polymer. In this example, an input screen is shown in Fig. 9a. The input screen allows for a definition of a polymer for which the burning behavior should be determined. In this case as polymer class a polyurethane foam is defined, for example, by using a dropdown menu. Moreover, a further field is provided for further optional specifica-tions and inputs. In this example, the polymer is then further defined below by defining materials of a synthesis specification of the polymer in form of ingredient types and asso-ciated amounts. Additionally, the input screen allows in this example to input which test methods should be utilized for determining respective burning properties, wherein in this case the test methods define then the determined burning properties. However, in another example, also directly the to be determined burning properties can be selected and the test methods can then be determined based on the selected burning properties. In this example, three test methods are selected. An exemplary output screen is shown in Fig. 9b. In this case the output screen provides the result of the determination of the burning properties for the defined polymer for the three selected test methods defined on the input screen. The determined properties are the properties measured in the respective test methods.

In a preferred example, the polymer is a polyurethane foam. Polyurethane foams are widely used in industries due to their broad range of application properties. This encompasses amongst others insulation materials, shoe soles, seating materials, matrasses and sound damping materials. In many of these applications, the burning behavior plays a crucial role and specific burning tests have to be past to comply with regulations. These burning tests require large amounts of materials and are very time-consuming. Therefore, the above de-scribed method provides a digital tool also for this application, which predicts the outcome a specific burning test in order to reduce material consumption and time demand of these tests.

Generally, in an embodiment the method for determining the burning behavior of a polymer, in particular, a polyurethane foam, for a specific burning test comprises a workflow de-scribed in the following. In a first step a digital representation of a polymer is provided. The digital representation may be a recipe, a structural formula, a brand name, CAS number. In an optional step a target application of the polyurethane foam may be provided. In a second step, a specific burning test method may be selected. A “specific burning test method” is the test, in which the burning behavior of the polyurethane foam is determined. Dependent on the burning test, other parameters may become relevant. In a case the burn-ing test may be selected upon the target application. For example, foams used as insulation materials for construction applications may have to pass a burning test according to DIN 4102 or EN 13501-1, while a foam used as engine cover in automotive vehicles may have to pass a burning test according to UL94. Consequently, for the latter example the auto-matic selection would select UL94 as the burning test. Generally, the burning property mod-els can be based on the test parameters that are predominant for the burning test. Conse-quently, the models may vary by the inputs. Therefore, it is likely that different models for different burning tests exist. In the example workflow this is represented by selecting a burning property model based on the burning test method. Upon selection of the burning property model the inputs of the burning property model are clear and will be requested. This may be done by providing a list of test parameters such as burner dimension, heat flux, sample size, etc. Then the appropriate values are requested. These are called burning test parameter values and will be an input into the burning property model. From the digital representation of the polymer, for instance, of the polyurethane foam, parameter values are derived, which also form inputs to the model. Based on the burning test parameters and the polymer parameters a measure for the burning behavior is determined and pro-vided. In an optional step, the representation of the burning behavior can be selected. In this case, the output is based on the selection.

In a preferred embodiment, the computer implemented method refers to a computer imple-mented method of predicting the burning behavior of a polyurethane foam, comprising the steps of providing a digital representation of the polyurethane foam associated with a syn-thesis specification, optional providing test parameter related to a burning test method in-dicative of a heat flux, providing a data driven burning property model, relating a measure of burning behavior of polyurethane foams to the digital representation of the polyurethane foam and the data related to the burning test, at least partially based on a) a digital repre-sentation of historical polyurethane foams associated their synthesis specification, b) his-torical data related data related to the burning test and c) measured data of a measure for burning behavior of the respective historical polyurethane foams, and determining the burn-ing behavior of the polyurethane foam based on the data driven model, the provided data related to the burning test and the digital representation of the polyurethane foam, and providing a measure for the burning behavior via an output interface.

Generally, potential representations of the burning behavior can be any on or more of heat release rate, peak heat release, total heat release, average rate of heat emission, maxi-mum rate of heat emission, effective heat of combustion, flame height, burning time, after-burn time, mass loss, mass loss rate, fire growth rate (FIGRA) , total smoke production, smoke growth rate, dripping behavior, ignition time, extinguishment time.

Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the dis-closure, and the appended claims.

For the processes and methods disclosed herein, the operations performed in the pro-cesses and methods may be implemented in differing order. Furthermore, the outlined op-erations are only provided as examples, and some of the operations may be optional, com-bined into fewer steps and operations, supplemented with further operations, or expanded into additional operations without detracting from the essence of the disclosed embodi-ments.

In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality.

A single unit or device may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

Procedures like the providing of the polymer characterizing parameters and the burning property model, the determining of the burning property, the providing of the burning prop-erty, etc. performed by one or several units or devices can be performed by any other number of units or devices. These procedures can be implemented as program code means of a computer program and/or as dedicated hardware.

A computer program product may be stored/distributed on a suitable medium, such as an optical storage medium or a solid-state medium, supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems.

Any units described herein may be processing units that are part of a classical computing system. Processing units may include a general-purpose processor and may also include a field programmable gate array (FPGA) , an application specific integrated circuit (ASIC) , or any other specialized circuit. Any memory may be a physical system memory, which may be volatile, non-volatile, or some combination of the two. The term “memory” may include any computer-readable storage media such as a non-volatile mass storage. If the computing system is distributed, the processing and/or memory capability may be distrib-uted as well. The computing system may include multiple structures as “executable com-ponents” . The term “executable component” is a structure well understood in the field of computing as being a structure that can be software, hardware, or a combination thereof. For instance, when implemented in software, one of ordinary skill in the art would under-stand that the structure of an executable component may include software objects, routines, methods, and so forth, that may be executed on the computing system. This may include both an executable component in the heap of a computing system, or on computer-reada-ble storage media. The structure of the executable component may exist on a computer-readable medium such that, when interpreted by one or more processors of a computing system, e.g., by a processor thread, the computing system is caused to perform a function. Such structure may be computer readable directly by the processors, for instance, as is the case if the executable component were binary, or it may be structured to be interpretable and/or compiled, for instance, whether in a single stage or in multiple stages, so as to generate such binary that is directly interpretable by the processors. In other instances, structures may be hard coded or hard wired logic gates, that are implemented exclusively or near-exclusively in hardware, such as within a field programmable gate array (FPGA) , an application specific integrated circuit (ASIC) , or any other specialized circuit. Accordingly, the term “executable component” is a term for a structure that is well understood by those of ordinary skill in the art of computing, whether implemented in software, hardware, or a combination. Any embodiments herein are described with reference to acts that are per-formed by one or more processing units of the computing system. If such acts are imple-mented in software, one or more processors direct the operation of the computing system in response to having executed computer-executable instructions that constitute an exe-cutable component. Computing system may also contain communication channels that al-low the computing system to communicate with other computing systems over, for example, network. A “network” is defined as one or more data links that enable the transport of elec-tronic data between computing systems and/or modules and/or other electronic devices. When information is transferred or provided over a network or another communications connection, for example, either hardwired, wireless, or a combination of hardwired or wire-less, to a computing system, the computing system properly views the connection as a transmission medium. Transmission media can include a network and/or data links which can be used to carry desired program code means in the form of computer-executable instructions or data structures and which can be accessed by a general-purpose or special-purpose computing system or combinations. While not all computing systems require a user interface, in some embodiments, the computing system includes a user interface sys-tem for use in interfacing with a user. User interfaces act as input or output mechanism to users for instance via displays.

Those skilled in the art will appreciate that at least parts of the invention may be practiced in network computing environments with many types of computing system configurations, including, personal computers, desktop computers, laptop computers, message proces-sors, hand-held devices, multi-processor systems, microprocessor-based or programma-ble consumer electronics, network PCs, minicomputers, main-frame computers, mobile tel-ephones, PDAs, pagers, routers, switches, datacenters, wearables, such as glasses, and the like. The invention may also be practiced in distributed system environments where local and remote computing system, which are linked, for example, either by hardwired data links, wireless data links, or by a combination of hardwired and wireless data links, through a network, both perform tasks. In a distributed system environment, program mod-ules may be located in both local and remote memory storage devices.

Those skilled in the art will also appreciate that at least parts of the invention may be prac-ticed in a cloud computing environment. Cloud computing environments may be distributed, although this is not required. When distributed, cloud computing environments may be dis-tributed internationally within an organization and/or have components possessed across multiple organizations. In this description and the following claims, “cloud computing” is defined as a model for enabling on-demand network access to a shared pool of configura-ble computing resources, e.g., networks, servers, storage, applications, and services. The definition of “cloud computing” is not limited to any of the other numerous advantages that can be obtained from such a model when deployed. The computing systems of the figures include various components or functional blocks that may implement the various embodi-ments disclosed herein as explained. The various components or functional blocks may be implemented on a local computing system or may be implemented on a distributed com-puting system that includes elements resident in the cloud or that implement aspects of cloud computing. The various components or functional blocks may be implemented as software, hardware, or a combination of software and hardware. The computing systems shown in the figures may include more or less than the components illustrated in the figures and some of the components may be combined as circumstances warrant.

Any reference signs in the claims should not be construed as limiting the scope.

The invention refers to a method for determining a biodegradability for a polymer. A digital representation of the polymer indicative of characterizing parameters of the polymer is pro-vided. Further, a habitat is provided that is indicative of habitat descriptor values influencing a biodegradation of a polymer. The habitat descriptors are indicative of environ-mental characteristics of the habitat. A biodegradation model is provided based on the habitat, wherein the biodegradation model is adapted to determine a biodegradability of a polymer in the respective habitat, wherein the biodegradation model is a data-driven model para-metrized with respect to the habitat such that it can determine a biodegradability of a poly-mer based on the characterizing parameters. The biodegradability of the polymer is then determined based on the provided biodegradation model and the digital representation of the polymer.

Procedures like the providing of the target burning behaviour, the digital representations, the property model, the determining of the burning properties, the comparing, etc. per-formed by one or several units or devices can be performed by any other number of units or devices. These procedures can be implemented as program code means of a computer program and/or as dedicated hardware.

Those skilled in the art will appreciate that at least parts of the invention may be practiced in network computing environments with many types of computing system configurations, including, personal computers, desktop computers, laptop computers, message proces-sors, hand-held devices, multi-processor systems, microprocessor-based or programma-ble consumer electronics, network PCs, minicomputers, mainframe computers, mobile tel-ephones, PDAs, pagers, routers, switches, datacenters, wearables, such as glasses, and the like. The invention may also be practiced in distributed system environments where local and remote computing system, which are linked, for example, either by hardwired data links, wireless data links, or by a combination of hardwired and wireless data links, through a network, both perform tasks. In a distributed system environment, program mod-ules may be located in both local and remote memory storage devices.

Those skilled in the art will also appreciate that at least parts of the invention may be prac-ticed in a cloud computing environment. Cloud computing environments may be distributed, although this is not required. When distributed, cloud computing environments may be dis-tributed internationally within an organization and/or have components possessed across multiple organizations. In this description and the following claims, “cloud computing” is defined as a model for enabling on-demand network access to a shared pool of configura-ble computing resources, e.g., networks, servers, storage, applications, and services. The definition of “cloud computing” is not limited to any of the other numerous advantages that can be obtained from such a model when deployed. The computing systems of the figures include various components or functional blocks that may implement the various embodi-ments disclosed herein as explained. The various components or functional blocks may be implemented on a local computing system or may be implemented on a distributed compu-ting system that includes elements resident in the cloud or that implement aspects of cloud computing. The various components or functional blocks may be implemented as software, hardware, or a combination of software and hardware. The computing systems shown in the figures may include more or less than the components illustrated in the figures and some of the components may be combined as circumstances warrant.

The invention refers to a method for determining burning properties of a polymer. A digital representation of the polymer indicative of characterizing parameters is provided. A digital representation of burning test conditions is provided. A burning property model is provided based on the provided burning test conditions, wherein the burning property model is adapted to determine one or more burning properties of a polymer with respect to the re-spective burning test method. The burning property model is a data-driven model parame-terized with respect to the respective burning test method such that it can determine one or more burning properties of a polymer based on the characterizing parameters and the burning test parameters. The burning properties of the polymer are determined based on the provided burning property model, the burning test conditions and the digital represen-tation of the polymer.

Claims

A computer-implemented method for determining burning properties usable for vali-dating a burning behavior of a polymer, wherein the method comprises:

providing a digital representation of the polymer indicative of or associated with char-acterizing parameters of the polymer, wherein the characterizing parameters are indicative of characteristics of a polymer and/or are derivable from one or more characteristics of the polymer,

providing a digital representation of burning test conditions indicative of or associ-ated with a burning test method and burning test parameters, wherein the burning test method is indicative of a standardized test method for determining experimentally a respec-tive burning property of a polymer and wherein the test parameters are indicative of a spe-cific test procedure of the burning test method,

providing a burning property model based on the provided burning test conditions, wherein the burning property model is adapted to determine one or more burning properties of a polymer with respect to the respective burning test method, wherein the burning prop-erty model is a data-driven model parameterized with respect to the respective burning test method to determine one or more burning properties of a polymer based on the character-izing parameters and the burning test parameters, and

determining the one or more burning properties of the polymer based on the provided burning property model, the burning test conditions and the digital representation of the polymer.
The method according to claim 1, wherein the polymer comprises the shape of a polymer foam and wherein a) the digital representation is further indicative of or associated with foam characteristics of the polymer foam, wherein the foam characteristics are indic-ative of characteristics of the foam structure of the polymer foam, and b) the burning prop-erty model is adapted to determine the one or more burning properties for the polymer foam further based on the foam characteristics.
The method according to claim 2, wherein the foam characteristics refer to at least one of structural characteristics, compositional characteristics, topology characteristics, and foaming process characteristics.
The method according to any of the preceding claims, wherein the provided test in-formation is indicative of an intended application of the polymer and wherein the burning test method and the burning test parameters are determined based on the intended appli-cation.
The method according to any of the preceding claims, wherein the one or more burn-ing properties indicative for the burning behavior of the polymer comprised at least one of a heat release rate, a peak heat release, a total heat release, an average rate of heat emission, a maximum rate of heat emission, effective heat of combustion, flame height, burning time, afterburn time, mass loss, mass loss rate, fire growth rate, total smoke pro-duction, smoke growth rate, dripping behavior, ignition time and extinguishment time.
The method according to any of the preceding claims, wherein the burning test method refers to one of single burning item, single-flame source test, UL94, UL 94 HB, ASTM E84 and cone calorimeter test.
The method according to any of the preceding claims, wherein the method further comprises providing control data based on the determined one or more burning properties associated with the burning behaviour.
The method according to claims 7, wherein the control data is configured for control-ling and/or monitoring a production of the polymer and/or a production of a product com-prising the polymer based on the determined one or more burning properties of the polymer and/or for causing a display for displaying the determined one or more burning properties.
An interface method for providing an interface, wherein the interface method com-prises:

receiving as input a digital representation of a polymer and of burning test conditions via a user interface and providing the received digital representation and the burning test conditions to a processor performing the method according to any of the preceding claims, and

providing the determined one or more burning properties of the polymer to a user via a user interface as a result, wherein the result is received from the processor performing the method according to any of the preceding claims.
A computer-implemented training method for training a data-driven based burning property model for parameterizing the burning property model, wherein the training method comprises:

providing training data associated with a predetermined burning test method, wherein the training data comprises a) digital representations of a plurality of training poly-mers indicative of characterizing parameters of each of the training polymers, b) a plurality of burning test parameters for the predetermined burning test method, and c) one or more burning properties determined by the respective burning test method associated with the respective burning test parameters for each training polymer,

providing a data-driven based trainable burning property model

training the provided data-driven based burning property model based on the pro-vided training data such that the trained burning property model is adapted to determine one or more burning properties of a polymer based on characterizing parameters of the polymer and based on the burning test parameters, and

providing the trained burning property model.
An apparatus for determining burning properties usable for validating a burning be-havior of a polymer, wherein the apparatus comprises one or more processors configured for performing the functions:

providing a digital representation of the polymer indicative of or associated with char-acterizing parameters of the polymer, wherein the characterizing parameters are indicative of characteristics of a polymer and/or are derivable from one or more characteristics of the polymer,

providing a digital representation of burning test conditions indicative of or associ-ated with a burning test method and burning test parameters, wherein the burning test method is indicative of a standardized test method for determining experimentally a respec-tive burning property of a polymer and wherein the test parameters are indicative of a spe-cific test procedure of the burning test method,

providing a burning property model based on the provided burning test conditions, wherein the burning property model is adapted to determine one or more burning properties of a polymer with respect to the respective burning test method, wherein the burning prop-erty model is a data-driven model parameterized with respect to the respective burning test method to determine one or more burning properties of a polymer based on the character-izing parameters and the burning test parameters, and

determining the one or more burning properties of the polymer based on the provided burning property model, the burning test conditions and the digital representation of the polymer.
An interface apparatus for providing an interface, wherein the interface apparatus comprises one or more processors configured for performing the functions:

receiving as input a digital representation of a polymer and of burning test conditions via a user interface and providing the received digital representation and the burning test conditions to a processor performing the method according to any of claims 1 to 8, and

providing the determined one or more burning properties of the polymer to a user via a user interface as a result, wherein the result is received from the processor performing the method according to any of claims 1 to 8.
A training apparatus for training a data-driven based burning property model for pa-rameterizing the burning property model, wherein the training apparatus comprises one or more processors configured for performing the functions:

providing training data associated with a predetermined burning test method, wherein the training data comprises a) digital representations of a plurality of training poly-mers indicative of characterizing parameters of each of the training polymers, b) a plurality of burning test parameters for the predetermined burning test method, and c) one or more burning properties determined by the respective burning test method associated with the respective burning test parameters for each training polymer,

providing a data-driven based trainable burning property model

training the provided data-driven based burning property model based on the pro-vided training data such that the trained burning property model is adapted to determine one or more burning properties of a polymer based on characterizing parameters of the polymer and based on the burning test parameters, and

providing the trained burning property model.
A computer program product for determining burning properties usable for validating a burning behavior of a polymer, wherein the computer program product comprises pro-gram code means for causing the apparatus of claim 11 to execute the method according to any of claims 1 to 8.
A computer program product for training a data-driven based burning property model, wherein the computer program product comprises program code means for causing the apparatus of claim 13 to execute the method according to claim 10.