WO2024217297A1

WO2024217297A1 - Digital twin for composite material repair, intelligent repair method, and intelligent repair system

Info

Publication number: WO2024217297A1
Application number: PCT/CN2024/086801
Authority: WO
Inventors: Xuefeng Yao; Xiaoyao XU; Shanyong XUAN; Yan KAN; Xin FAN
Original assignee: Wuhu Machinery Factory; Tsinghua University
Current assignee: Wuhu Machinery Factory; Tsinghua University
Priority date: 2023-04-21
Filing date: 2024-04-09
Publication date: 2024-10-24
Anticipated expiration: 2025-10-21
Also published as: CN116588347A; CN116588347B

Abstract

The present disclosure provides a digital twin for composite material repair, an intelligent repair method, an intelligent repair system and an intelligent repair device. The method includes: transmitting repair factors of a repair entity of a composite material acquired in real time to the digital twin for composite material repair; establishing an initial visual digital model of the repair entity by the digital twin according to the structural parameters and the damage parameters of the repair entity; predicting critical operational characteristics of different combinations of repair process parameters through the digital twin performing a design space search according to the repair process parameters, to obtain target repair process parameters required for the repair entity to reach the critical operational characteristics after the repair entity being repaired; predicting a full-field distribution information of the critical operational characteristics of the repair entity by the digital twin according to the repair process parameters and the initial visual digital model, displaying and analyzing the full-field distribution information, and transmitting the received target repair process parameters to a repair tool; and setting a repair procedure by the repair tool according to the target repair process parameters to implement the repair of the repair entity.

Description

DIGITAL TWIN FOR COMPOSITE MATERIAL REPAIR, INTELLIGENT REPAIR METHOD, AND INTELLIGENT REPAIR SYSTEM

This application claims priority to Chinese Patent Application No. 202310434472.7 filed on April 21, 2023, which is incorporated herein by reference in its entirety.

TECHNICAL FIELD

The present disclosure belongs to a field of digital twin for composite material repair, in particular relates to a digital twin for a composite material repair, an intelligent repair method, an intelligent repair system and an intelligent repair device.

BACKGROUND

With the rapid improvement of composite manufacturing technology and its proportion of use, the application scope of the composite manufacturing technology has gradually developed from non-load-bearing parts to load-bearing parts, involving aerospace, automobile manufacturing, energy storage materials, construction device, wind power generation and other fields. The safety of composite structures plays an increasingly critical role. At the same time, there is a rapid growth on the stock of composite structures, and with the influence of service time, complex loads and the external environment, the damage and deterioration of composite materials continue to accumulate. How to quickly and intelligently assess the damage of composite materials, provide efficient and reliable repair programs and repair processes has become more and more important.

A significant demand for composite material repair is to be "fast" , but the current composite material repair has the problems of long time consumption, repair difficulty and high repair costs, especially for specific structures. In addition, a large part of composite components are structures which are fragile and easy to damage, and the diversity and complexity of composite components, structures, damage and failure modes also put forward strict requirements on repair processes and technologies, which brings outstanding difficulties to the repair process design, real-time prediction and analysis of the repair procedure and intelligent repair in actual repair conditions. Therefore, it is particularly important to develop a method that can realize intelligent repair according to the damage situation.

SUMMARY

For the above technical problems, the present disclosure provides a method, a system and a device for establishing a digital twin for composite material repair and intelligent repair, to at least partially solving the above technical problems.

In order to solve the above technical problems, the technical scheme provided by the present disclosure is as follows.

As a first aspect of the present disclosure, an intelligent repair method using a digital twin for composite material repair is provided, including:

transmitting repair factors of a repair entity of a composite material acquired in real time to the digital twin for composite material repair, wherein the repair factors include damage parameters, repair process parameters and structural parameters;

establishing an initial visual digital model of the repair entity by the digital twin according to the structural parameters and the damage parameters of the repair entity, wherein the initial visual digital model is used to describe the structural parameters and the damage parameters of the repair entity;

predicting critical operational characteristics of different combinations of repair process parameters through the digital twin performing a design space search according to the repair process parameters, to obtain target repair process parameters required for the repair entity to reach the critical operational characteristics after the repair entity being repaired;

predicting in real time a full-field distribution information of the critical operational characteristics of the repair entity by the digital twin according to the repair process parameters and the initial visual digital model, displaying and analyzing the full-field distribution information in real time, and transmitting the received target repair process parameters to a repair tool; and

setting a repair procedure by the repair tool according to the received target repair process parameters to implement the repair of the repair entity.

As a second aspect of the present disclosure, an intelligent repair system for composite material is provided, including:

a real-time data transmission module, configured to transmit repair factors of a repair entity of a composite material acquired in real time to the digital twin for composite material repair, wherein the repair factors include damage parameters, repair process parameters and structural parameters;

a digital model acquisition module, configured to establish an initial visual digital model of the repair entity by the digital twin according to the structural parameters and the damage parameters of the repair entity, wherein the initial visual digital model is used to describe the structural parameters and the damage parameters of the repair entity;

an intelligent repair design module, configured to predict critical operational characteristics of different combinations of repair process parameters through the digital twin performing a design space search according to the repair process parameters, to obtain target repair process parameters required for the repair entity to reach the critical operational characteristics after the repair entity being repaired;

a digital twin control module, configured to predict a full-field distribution information of the critical operational characteristics of the repair entity by the digital twin according to the repair process parameters and the initial visual digital model, display and analyze the full-field distribution information in real time, and transmit the received target repair process parameters to a repair tool module; and

the repair tool module, configured to set a repair procedure according to the received target repair process parameters to implement the repair of the repair entity.

As a third aspect of the present disclosure, an intelligent repair device for composite material is provided, including the above intelligent repair system for composite material;

an input part, configured to obtain repair information of the repair entity, wherein the repair information includes at least one of repair tool module information, text information, image information and graphic information;

a storage part, configured to store a computer program including the digital twin;

a processor, configured to execute the above intelligent repair method using a digital twin for composite material repair;

an output part, configured to output real-time repair information of the repair entity; and

a virtual-real fusion interface, configured for a virtual-real interaction between the repair entity and the digital twin.

According to embodiments of the present disclosure, the digital twin provided by the disclosure fully considers the diversity and complexity of the composition, structure, damage and failure mode of the composite material, and the digital twin, the repair process and technology are enhanced by using machine learning. This effectively solve the problem that it is difficult to quickly achieve the target repair process design, predict and analyze the repair procedure and integrate the intelligent repair in the actual repair procedure.

Specifically, the repair factors of the repair entity of the composite material collected in real time are transmitted to the digital twin for composite material repair, through which the structural parameters and damage parameters of the repair entity are used to establish the initial visual digital model of the repair entity, that is, the repair entity is transformed into a digital virtual object. By using the digital twin to perform the design space search according to the repair process parameters, the critical operational characteristics of different combinations of repair process parameters are predicted, and the target repair process parameters required for the repair entity to achieve the critical operational characteristics after the repair entity being repaired are obtained. Then, by using the digital twin according to the repair process parameters and the initial visual digital model, the full-field distribution information of the critical operational characteristics of the repair entity can be predicted and displayed and analyzed in real time, and the received target repair process parameters can be transmitted to the repair tool. Through the repair tool, the repair procedure is set according to the received target repair process parameters and the repair of the repair entity is implemented. In this way, digital twins can be used to analyze the repair process parameters and critical operational characteristics of the composite materials during the repair procedure of the repair entity, and the repair work of the repair tool to the repair entity can be intelligently adjusted by using the digital twin.

The digital twin in the disclosure has the capability of two-dimensional or three-dimensional full-field high-fidelity information simulation and prediction of the critical operational characteristics of the composite material repair entity, real-time display and analysis, and dynamic updating and evolution, and fully considers the multi-scale connection of the iterative information of the digital twin. In this way, when the damage parameters of the composite material are given and the target repair process parameters required for the repair entity to achieve the critical operational characteristics are predicted by the digital twin, the repair tool can repair the repair entity according to the repair procedure set by the digital twin, and the integration of the digital twin and the intelligent repair method is realized. It is helpful to improve the repair speed and accuracy of composite materials.

BRIEF DESCRIPTION OF THE DRAWINGS

Fig. 1 illustrates a schematic diagram of a flow diagram of an intelligent repair method for composite materials in the embodiments of the present disclosure.

Fig. 2 illustrates a schematic diagram of a flow diagram of constructing a digital twin in the embodiments of the present disclosure.

Fig. 3 illustrates a structural block diagram of an intelligent repair system for composite materials in the embodiments of the present disclosure.

Fig. 4 illustrates a schematic diagram of intelligent repair and life cycle management of composite materials in the embodiments of the present disclosure.

Fig. 5 illustrates a block diagram of an intelligent repair device for composite materials in the embodiments of the present disclosure.

DETAILED DESCRIPTION OF EMBODIMENTS

Embodiments of the present disclosure will be described below with reference to the accompanying drawings. However, it should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present disclosure. In the detailed description below, for the purpose of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, in the following description, the description of common knowledge structures and techniques has been omitted to avoid unnecessarily obscuring the concepts of the present disclosure.

The terms used herein are merely for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprising" , "including" and the like used herein indicate the presence of the described features, steps, operations, and/or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

Unless otherwise defined, all terms used herein (including technical and scientific terms) have meanings commonly understood by those skilled in the art. It should be noted that the terms used here should be interpreted to have meanings consistent with the context of this specification, and not in an idealized or overly rigid manner.

When using expressions such as "at least one of A, B, and C, " it should generally be interpreted according to the meaning commonly understood by those skilled in the art (for example, ′a system having at least one of A, B, and C′ should include, but not be limited to, systems having only A, only B, only C, A and B, A and C, B and C, and/or A, B, and C) .

In the process of realizing the present disclosure, it is found that although the digital twin can realize the prediction and analysis of fault devices, the digital twin used lacks the ability of high-fidelity information simulation, prediction and dynamic update, which cannot effectively strengthen the multi-scale connection of the iterative information of the digital twin, and it is difficult to realize the effective integration of the digital twin and intelligent repair device.

For the problem that it is difficult to integrate digital twins with intelligent repair methods and intelligent repair devices in related technologies, the present disclosure provides an intelligent repair method, an intelligent repair system and an intelligent repair device for digital twins for composite material repair and composite materials.

Fig. 1 illustrates a schematic diagram of a flow diagram of an intelligent repair method using a digital twin for composite material repair in the embodiments of the present disclosure.

As shown in Fig. 1, an intelligent repair method 100 using a digital twin for composite material repair provided in the present disclosure includes: operation S101 to operation S 105.

In operation S101, repair factors of a repair entity of a composite material acquired in real time are transmitted to the digital twin for composite material repair. The repair factors include damage parameters, repair process parameters and structural parameters.

In operation S102, an initial visual digital model of the repair entity is established by the digital twin according to the structural parameters and the damage parameters of the repair entity. The initial visual digital model is used to describe the structural parameters and the damage parameters of the repair entity.

In operation S 103, critical operational characteristics of different combinations of repair process parameters are predicted through the digital twin performing a design space search according to the repair process parameters, to obtain target repair process parameters required for the repair entity to reach the critical operational characteristics after the repair entity being repaired.

In operation S104, a full-field distribution information of the critical operational characteristics of the repair entity is predicted in real time by the digital twin according to the repair process parameters and the initial visual digital model, the full-field distribution information is displayed in real time, and the received target repair process parameters are transmitted to a repair tool.

In operation S 105, a repair procedure is set by the repair tool according to the received target repair process parameters to implement the repair of the repair entity.

According to embodiments of the present disclosure, the digital twin for composite material repair (referred to as "digital twin" ) provided herein is a set of virtual objects composed of information technology, which can imitate the structure, environment and behavior of the composite repair entity, and dynamically update the digital twin through the use of the repair data of the repair entity during the entire life cycle of the digital twin. The digital twin also provides valuable repair decisions, such as providing repair process parameters and guiding repair tools to implement repair. Specifically, the repair factors of the repair entity of the composite material collected in real time are transmitted to the digital twin for composite material repair, through which the structural parameters and damage parameters of the repair entity are used to establish the initial visual digital model of the repair entity, that is, the repair entity is transformed into a digital virtual body. By using the digital twin to perform the design space search according to the repair process parameters, the critical operational characteristics of different combinations of repair process parameters are predicted, and the target repair process parameters required for the repair entity to achieve the critical operational characteristics after the repair entity being repaired are obtained. Then, by using the digital twin according to the repair process parameters and the initial visual digital model, the full-field distribution information of the critical operational characteristics of the repair entity can be predicted in real time, displayed and analyzed in real time, and the received target repair process parameters can be transmitted to the repair tool. Through the repair tool, the repair procedure is set according to the target repair process parameters and the repair of the repair entity is implemented. In this way, digital twins can be used to analyze the repair process parameters and properties of the composite materials during the repair, and the repair work of the repair tool can be intelligently adjusted so that the repair tool can repair the composite material repair entity according to the preset repair process.

According to embodiments of the present disclosure, in operation SI01, the repair entity is a physical component that has suffered damage during a manufacturing and/or a service process. The damage includes, but is not limited to, gaps formed by external impact, delamination, degumming, scratches, cracks, impact, lightning strike, burning, etc.

The composite material in the embodiments of the present disclosure is composed of at least two components with anisotropic mechanical properties, such as carbon fiber laminates, honeycomb sandwich structures, etc. The composite material includes but is not limited to components applied to composite material skins, equipment covers, hatch doors, wind power blades, automotive skeletons, energy storage panels, etc.

According to embodiments of the present disclosure, the repair factors include damage parameters, repair process parameters and structural parameters. Specifically, the structural parameters include but are not limited to material properties, geometric shapes, boundary conditions, etc. of the repair entity; the damage parameters include but are not limited to damage size, damage type, damage depth, number of damage layers, impact time, thickness of adhesive layer, etc.; and the repair process parameters include but are not limited to medium pressure, curing temperature, curing time, repair tool path, adhesive strength, temperature rate, pressure rate, etc.

According to embodiments of the present disclosure, in operation S102, the digital twin is used to establish an initial visual digital model based on the structural parameters and damage parameters of the repair entity, and the repair entity is transformed into a virtual object for visual display, so as to describe the structural parameters and damage parameters of the repair entity.

According to embodiments of the present disclosure, in operation S103, the digital twin is used to perform a design space search according to the repair process parameters to predict the critical operational characteristics of the combinations of repair process parameters under different damage parameters, and the target repair process parameters required for the repair entity to reach the critical operational characteristics after the repair entity being repaired are obtained. The design space search is achieved in the following manner: A reduced-order model is used by the digital twin to convert high-dimensional data into low-dimensional data and a high-fidelity simulation prediction is performed. Under a combination of repair process parameters in a design space, a mean value and an uncertainty of the critical operational characteristics of the repair entity after repair are obtained, so as to obtain the critical operational characteristics of the repair entity after the repair entity being repaired. The combination of repair process parameters includes at least one combination of a temperature, a pressure, a size, a time, a curing degree, and a tool path. The critical operational characteristics include at least one of the curing degree, a deformation, a strain, a stress, a tensile strength, a bearing strength, a hardness, a plasticity, and a toughness.

According to embodiments of the present disclosure, in operations S 104-S105, the digital twin obtains the full-field distribution information of the critical operational characteristics of the repair entity based on the real-time acquired repair process parameters and the initial visual digital model, realizing the two-dimensional or three-dimensional real-time full-field display and analysis of the repair entity. The digital twin transmits the target repair process parameters to the repair tool, and the repair tool sets the repair procedure according to the given target repair process parameters. The repair tools can be tools for cropping, grinding, cutting, drilling, digging, heat curing, microwave curing, electron beam curing, light curing, laser ablation, anchoring, daubing, vacuuming, etc.

According to embodiments of the present disclosure, the intelligent repair method for the composite material also includes: regulating a repair process of the repair tool to the repair entity according to the repair procedure, to achieve rapid and accurate repair of the repair entity.

According to embodiments of the present disclosure, the intelligent repair method for the composite material also includes: monitoring in real time, by using the digital twin, parameter changes of the repair entity during a service phase after the repair entity being repaired. It can be understood that after the repair of the repair entity is completed, the digital twin continues to receive the same changes in load and environmental parameters as the repaired entity during the service phase, and the digital twin provides the latest virtual information of the repair entity until the repair entity fails and the failure parameters such as strength reduction degree and life span are obtained. Thus, the digital twin can be used to monitor the parameter change of the repair entity in the service phase.

According to embodiments of the present disclosure, the intelligent repair method for the composite material also includes: dynamically updating the digital twin by using repair data of the repair entity collected in real time during the repair procedure. The repair data includes repair process parameters and observation data. The repair process parameters can be set repair process parameters and repair process parameters dynamically adjusted in real time according to observation data during the repair procedure. The observation data is data obtained from some measuring instruments. It can be understood as: The repair data of the repair entity collected in real time is used as the input of the digital twin, and the digital twin is used to simulate and predict the actual repair procedure according to the input. For example, the repair process parameters set in the actual repair procedure are used as the input, and the digital twin is used to simulate according to the repair process parameters, and the optimal repair procedure is determined. Besides, the observation data in the data collected in real time and the predicted data output by the digital twin are verified by a multi-scale interaction model in the data twin, so as to realize the correction of the digital twin and realize the update of the digital twin.

In the embodiments of the present disclosure, by updating the digital twin with the repair data of the repair entity continuously collected in real time during the repair procedure, the data twin can be continuously updated and evolved, and the multi-scale connection of the iteration information of the digital twin is effectively considered. It is helpful for the digital twin to provide more accurate repair process parameters in the subsequent repair procedure.

According to embodiments of the present disclosure, the intelligent repair method for the composite material also includes: establishing a digital twin database for composite material repair according to accumulated repair data of a plurality of repair entities and corresponding digital twins, to realize an analysis, an update, and an evolution of the digital twin for composite material repair.

According to embodiments of the present disclosure, the digital twin in the embodiments of the present disclosure is obtained by training a digital twin to be trained using training data and/or observation data collected in real time. A repair digital model established by repair factors of a repair entity sample and a mechanism model established during a repair procedure of the repair entity sample may be used as the training data. Specifically, the digital twin modeling process is shown in Fig. 2.

Fig. 2 illustrates a schematic diagram of a flow diagram of constructing a digital twin for composite material repair in the embodiments of the present disclosure.

As shown in Fig. 2, the construction of the digital twin in the embodiments of the present disclosure is shown in operations S201 to S211.

In operation S201, the repair factors of the repair entity sample are obtained.

Specifically, the repair factors of the repair entity sample also include structural parameters, repair process parameters and damage parameters.

in operations S202 to S203, the repair digital model and the mechanism model are established.

Specifically, the repair digital model is established based on the repair factors of the repair entity sample, the mechanism model is established based on the repair entity sample during the repair procedure, and the training data is constructed based on the repaired digital model and the mechanism model.

More specifically, the repair digital model is a digital model established based on the repair entity sample of a composite material, which has a comprehensive reflection of the repair factors of the repair entity sample, and is suitable for computational processing. The mechanism model is a mathematical model that accurately describes a repair procedure, and the mathematical model is established according to an internal mechanism of the repair entity sample in the repair procedure. The internal mechanism of the repair entity sample in the repair procedure includes at least one of a basic law required by the digital twin, a thermodynamic coupling dynamic equation, a material constitutive model, a damage evolution model, a fatigue failure model, a physical significance of parameters in the mechanism model, and a repair process of the composite material. It should be noted that the basic law required by the digital twin is a law that conform to the laws of nature, such as Newton′s first law and Newton′s second law. The repair process of the composite material includes but is not limited to: drilling, dredging, laying process, curing process, testing process, design process, service testing, etc.

Before completing the construction of training data, it is needed to determine whether the training data meets the high-fidelity information simulation, that is, operation S204.

In operation S204, it is determined whether the actual repair procedure is accurately described.

Specifically, the repair digital model and the mechanism model established by the above repair entity sample are used to establish a repair model that fully reflects the repair factors of the repair entity sample and is suitable for computational processing, so as to realize the numerical simulation in the actual repair procedure. The repair model can realize the high-fidelity simulation and prediction of the actual repair procedure. The repair model is trained with the above training data, and the simulation value of the repair model is output. When the simulation value of the repair model has a large error compared with the actual test result, it is determined that the training data cannot perform high-fidelity information simulation and prediction, and cannot meet the required accuracy, that is, it cannot accurately describe the repair procedure. In this situation, it is needed to re-establish the repair digital model and the mechanism model, and constantly iterate and adjust, so that the training data can perform high-fidelity information simulation and prediction. When the error difference between the simulation value of the repair model and the actual test result is small and the required accuracy can be met, it is determined that the repair procedure can be accurately described. After comprehensive consideration of cost and accuracy requirements, appropriate sampling strategies are adopted to filter and construct training data, and the training data is a more representative repair model suitable for computational processing, and is used for the construction of digital twins.

In operations S205-S211, the digital twin to be trained is constructed and the digital twin is obtained.

Specifically, the digital twin includes a statistical inference model, a multi-scale interaction model and a data assimilation model, and the digital twin is trained by the following operations S206-S211.

The repair digital model which reflects the repair factors of the repair entity sample is established according to the repair entity sample, and the mechanism model which describes the repair procedure is established according to an internal mechanism of the repair entity sample in the repair procedure.

The repair digital model and the mechanism model of the repair entity sample are determined as the training data and a mechanism constraint of the digital twin to be trained.

The statistical inference model in the digital twin to be trained is trained according to the training data, the observation data of the repair entity sample collected in real time, and prior knowledge data in the mechanism model, and the prediction data is output.

Under the constraint of the mechanism model, a loss value is calculated according to the prediction data and the observation data of the repair entity sample collected in real time, to obtain a loss result. The multi-scale interaction model and the statistical inference model of the digital twin are obtained by iteratively adjusting parameters of the multi-scale interaction model in the digital twin to be trained.

New observation data of the repair entity sample collected in real time are input into the data assimilation model of the digital twin to be trained for updating, to obtain the data assimilation model of the digital twin.

The statistical inference model, the multi-scale interaction model and the data assimilation model in the digital twin are integrated to obtain the digital twin.

According to embodiments of the present disclosure, the statistical inference model is based on a dynamic Bayesian network. According to the observation data of the repair entity sample collected in real time and the prior knowledge (namely, the basic law required by the digital twin) , the digital twin to be trained is trained, and an inference of the repair conditions outside the range of assimilation is made, and the inference of the unknown conditions is expressed in the form of probability. Thus, the overall condition of the repair entity sample is predicted and forecasted.

According to embodiments of the present disclosure, the multi-scale interaction model is based on the dynamic Bayesian network. Under the constraint of the mechanism model, the loss value is calculated according to the predicted data and the observation data of the repair entity sample collected in real time, and the loss result is obtained. The parameters of the multi-scale interaction model in the digital twin to be trained are iteratively adjusted by using the loss result. The multi-scale interaction model and statistical inference model of the digital twin are obtained to ensure the mechanism coordination of the output information of the digital twin on the multi-scale.

It can be understood that according to the multi-scale mechanism between the input, output and observation data of different scales, combined with the internal mechanism of the repair entity sample in the repair procedure (that is, the multi-scale mechanism and statistical methods integrate multi-scale mechanism constraints in the calculation and prediction of the digital twin) , the high-fidelity collaborative integration between the digital twin and the multi-scale and multi-physical model is realized. The state and analysis of repair entity sample at different scales are given, where the multi-scale can be understood as macroscopic, microscopic and meso physical quantities.

According to embodiments of the present disclosure, the data assimilation model is constructed by using a probability graph model or a dynamic Bayesian network-Markov network. By considering the spatial and temporal distribution of data and the uncertainty of the model, new observation data is fused on the basis of the dynamic operation of the digital twin to be trained, and the dynamic update of the digital twin to be trained is realized, so as to obtain the data assimilation model of the digital twin. The spatial and temporal distribution of data includes: distribution characteristics of repair data which are associated with the coordinates and processes of repair entities based on the unified temporal and spatial datum; the model error includes the uncertainty caused by noise and deviation due to the fact that the test, mechanism and simulation are not completely consistent with the real situation.

Then, the statistical inference model, the multi-scale interaction model and the data assimilation model are integrated to obtain the digital twin. In the case that the digital twin can realize data assimilation, statistical inference and multi-scale interaction functions in the repair procedure according to the given repair entity of the composite material, the digital twin suitable for repairing the repair entity is obtained, so that it has the characteristics of virtual-real coordination, data fusion, iterative optimization, error quantification and intelligent decision-making. This lays a foundation for improving the repair level of the repair entity of the composite material.

According to embodiments of the present disclosure, after obtaining the digital twin, the digital twin can be used to transform the repair entity into a virtual object, and through the virtual object, an intelligent repair scheme suitable for the repair entity can be designed. Then, according to the intelligent repair plan, the repair entity is repaired by using the digital twin to control the repair tool, and the virtual and real interaction between the repair entity and the virtual object is realized. In the construction process of the digital twin provided in the present disclosure, the diversity and complexity of the composition, structure, damage and failure mode of the composite material are fully considered, and the repair process and technology of the digital twin are enhanced by using the machine learning algorithm. This effectively solve the problem that it is difficult to quickly achieve the target repair process design, predict and analyze the repair procedure and integrate the intelligent repair in the actual repair procedure.

In the embodiments of the present disclosure, the digital twin constructed by the above method replaces the high-fidelity engineering simulation achieved by the repair digital model and mechanism model of the composite material, realizes the two-dimensional or three-dimensional full-field real-time prediction of the critical operational characteristics of the repair entity, and is used to accelerate the prediction and design space search. The digital twin provided by the present disclosure also has the capability of updating and evolution by using a data assimilation model, and utilizes a multi-scale interaction model to enable the digital twin to effectively strengthen the multi-scale association of iterative information. The critical operational characteristics of the repair entity include at least one of a curing degree, a deformation, a strain, a stress, a tensile strength, a bearing strength, a hardness, a plasticity and a toughness.

According to embodiments of the present disclosure, the digital twin can be used to accelerate prediction and design space search by the following operations.

The digital twin to be trained is approximated to high nonlinearity with relatively loose training data by statistical method and machine learning algorithm according to parametric or non-parametric reduced-order model to realize high-fidelity information simulation. On this basis, combined with data assimilation model, statistical inference model and multi-scale interaction model, the obtained digital twin provides the predicted mean value and predicted uncertainty of the critical operational characteristics of the repair entity after being repaired, under the combination of repair process parameters (such as any point in the design space) in the design space, so as to obtain the critical operational characteristics of the repair entity after the repair. The combination of repair process parameters includes at least one of a temperature, a pressure, a size, a time, a curing degree, and a tool path.

Based on the above intelligent repair method for composite material, the present disclosure also provides an intelligent repair system for composite material. The device will be described in detail in combination with Fig. 3 below.

As shown in Fig. 3, the intelligent repair system for composite material includes: a real-time data transmission module 310, a digital model acquisition module 320, an intelligent repair design module 330, a digital twin control module 340, and a repair tool module 350.

Specifically, the real-time data transmission module 310 is used to transmit repair factors of a repair entity of a composite material acquired in real time to the digital twin for composite material repair, where the repair factors include damage parameters, repair process parameters and structural parameters. In an embodiment, the real-time data transmission module 310 can be used to perform the operation S101 described above, which is not repeated here.

The digital model acquisition module 320 is used to establish an initial visual digital model of the repair entity by the digital twin according to the structural parameters and the damage parameters of the repair entity. The initial visual digital model is used to describe the structural parameters and the damage parameters of the repair entity, and transform the repair entity into a virtual object for visual display, so as to describe the structural parameters and the damage parameters of the repair entity. In an embodiment, the digital model acquisition module 320 can be used to perform the operation S 102 described above, which is not repeated here.

The intelligent repair design module 330 is used to predict critical operational characteristics of combinations of repair process parameters under different damage parameters through the digital twin performing a design space search according to the repair process parameters, to obtain target repair process parameters required for the repair entity to reach the critical operational characteristics after the repair entity being repaired. In an embodiment, the intelligent repair design module 330 can be used to perform the operation S 103 described above, which is not repeated here.

The digital twin control module 340 is used to predict a full-field distribution information of the critical operational characteristics of the repair entity by the digital twin according to the repair process parameters and the initial visual digital model, display and analyze the full-field distribution information in real time, and transmit the received target repair process parameters to a repair tool module 350. In an embodiment, the digital twin control module 340 can be used to perform the operation S104 described above, which is not repeated here.

The repair tool module 350 is used to set a repair procedure according to the received target repair process parameters to implement the repair of the repair entity. In an embodiment, the repair tool module 350 can be used to perform the operation S105 described above, which is not repeated here.

In the embodiments of the present disclosure, the repair factors of the repair entity acquired in real time are transmitted to the digital twin by adopting the real-time data transmission module. The digital twin establishes the initial visual digital model of the repair entity according to the structural parameters and damage parameters of the repair factors of the repair entity by using the digital model acquisition module, and realizes the 2D or 3D transformation of the repair entity to the virtual object through the digital twin. By using the intelligent repair design module, the digital twin can perform the design space search according to the repair process parameters, predict the critical operational characteristics under different repair process combinations, and determine the target repair process parameters of the repair entity. Through the digital twin control module, the digital twin transmits the acquired target repair process parameters to the repair tool module, and guides the repair tool module to implement the repair. Besides, the digital twin control module can also predict the full-field distribution information of the critical operational characteristics of the repair entity according to the repair process parameters and the initial visual digital model and display and analyze the full-field distribution information in real time. In this way, it is possible to adjust the repair procedure of the repair tool module in time, the virtual -real cooperation, data fusion and intelligent decision-making of the digital twin and the intelligent repair system are realized, and the problem that the digital twin and the intelligent repair system are difficult to integrate is also solved.

According to embodiments of the present disclosure, the structural parameters include, but are not limited to, material properties, geometric shapes, boundary conditions, etc. of the repair entity; the damage parameters include but are not limited to damage size, damage type, damage depth, number of damage layers, impact time, thickness of adhesive layer, etc.; and the repair process parameters include but are not limited to medium pressure, curing temperature, curing time, repair tool path, adhesive strength, temperature rate, pressure rate, etc.

According to embodiments of the present disclosure, the real-time data transmission module 310 includes a damage scanning and identification module and a sensor.

Specifically, the damage scanning and identification module can obtain a damage parameter through image recognition and processing technology by scanning a damage characteristic of a damage part. The damage scanning and identification module can be an instrument related to digital images, ultrasound, laser and thermal imaging. Regarding the damage parameter, a defect can be described by a shape function, a defect feature can be extracted by image segmentation technology, the type and volume fraction of the defect can be quickly counted, the cause of the damage can be determined and converted into damage degree rating, which can be used as a damage parameter input to the digital twin.

The sensor is used to measure repair process parameters of the repair procedure, for example, the sensor can be a temperature sensor, a pressure sensor, etc., which will not be detailed here.

According to embodiments of the present disclosure, the intelligent repair design module 330 also includes:

an update module used to dynamically update the digital twin by using repair data of the repair entity collected in real time accumulated during the repair procedure, in which the repair data includes repair process parameters and observation data.

According to embodiments of the present disclosure, the repair tool module 350 includes at least one of:

a modular repair unit, a non-destructive testing unit, a composite material pretreatment unit, a curing repair unit, an unmanned aerial vehicle repair unit, and a repair vehicle repair unit. The repair module 350 is used for the intelligent repair design module 330 to implement more accurate repair of the repair entity, the repair tool module 350 can be manual, and can also be mechanical arm assisted or digital.

For example, the repair tool module 350 includes tools for cropping, grinding, cutting, drilling, digging, heat curing, microwave curing, electron beam curing, light curing, laser ablation, anchoring, daubing, vacuuming, etc.

The modular repair unit prefabricates general standard parts according to different damage parts, and gives a series of standard repair components with the same or similar configuration under different damage degrees.

The non-destructive testing unit uses percussion, digital image correlation, thermal imaging, ultrasound, X-ray imaging, array sensing and other non-destructive testing technology to detect the damage area of the repair entity.

The composite material pretreatment unit removes water, oil, fuel, dust or other foreign matter from the damage area of the repair entity by cropping, grinding, cutting, drilling, digging, and vacuuming.

The curing repair unit uses curing resin material system, such as thermal curing, microwave curing, electron beam curing, light curing, anchoring, coating, injection and other technologies, to improve the efficiency of multi-crosslinking reaction, resin curing speed, reduce the use of hot binders, and achieve high efficiency and high-performance maintenance of the damage area of the composite material repair entity.

The unmanned aerial vehicle repair unit uses an unmanned aerial vehicle repair module with composite material repair entity detection technology and curing technology to realize a large-area and high-mobility detection and repair of a single UAV and a rapid detection and repair of multi-UAV intelligent cluster in the field repair environment.

The repair vehicle repair unit integrates the intelligent repair system for composite material into a specific vehicle to restore the basic function of the damage structure of the repair entity in a relatively short time in the field repair environment.

According to embodiments of the present disclosure, the digital twin control module 340 also includes:

an adjustment unit used to regulate a repair process of the repair tool module 350 to the repair entity according to the repair procedure.

The manner of using the adjustment unit of the digital twin control module 340 to regulate the repair process of the repair tool module 350 to the repair entity includes at least one of a single-chip digital automatic control, a full voltage starting, a voltage ramp starting, a voltage step starting and a current limiting starting, so as to ensure the accuracy, reliability, and safety of the on-site repair process parameters and the operation of the repair tool module 350. By utilizing the digital twin control module 340 to perform online analysis, evaluation, and dynamic optimization during the repair procedure, unmanned and intelligent repair of the repair entity of the composite material can be achieved, improving the efficiency of the repair of the repair entity of the composite material.

According to embodiments of the present disclosure, the intelligent repair system for composite material also includes:

a life cycle management module used to monitor in real time, by using the digital twin, parameter changes of the repair entity during a service phase after the repair entity being repaired.

a digital twin database used to establish a digital twin database for composite material repair according to accumulated repair data of a plurality of repair entities and corresponding digital twins, so as to realize an analysis, an update and an evolution of the digital twin for composite material repair.

In the embodiments of the present disclosure, the intelligent repair system of composite material provided in the present disclosure uses the technology of combining big data and mechanism to realize the knowledge graph of massive energy and production data, which is conducive to making implicit knowledge explicit for manufacturing enterprises.

According to the embodiments of the present disclosure, the intelligent repair system for composite material includes a digital twin constructing module for constructing a digital twin. The digital twin is obtained by training a digital twin to be trained using training data and/or observation data collected in real time, wherein a repair digital model established by repair factors of a repair entity sample and a mechanism model established during a repair procedure of the repair entity sample are used as the training data.

Specifically, the digital twin constructing module includes a statistical inference model, a multi-scale interaction model and a data assimilation model. The digital twin is trained by:

establishing the repair digital model which reflects the repair factors of the repair entity sample according to the repair entity sample, and establishing the mechanism model which describes the repair procedure according to an internal mechanism of the repair entity sample in the repair procedure;

determining the repair digital model and the mechanism model of the repair entity sample as the training data and a mechanism constraint of the digital twin to be trained;

training the statistical inference model in the digital twin to be trained according to the training data, the observation data of the repair entity sample collected in real time, and prior knowledge data in the mechanism model, and outputting prediction data;

calculating a loss value under the constraint of the mechanism model according to the prediction data and the observation data of the repair entity sample collected in real time, to obtain a loss result, and iteratively adjusting parameters of the multi-scale interaction model in the digital twin to be trained by using the loss result, to obtain the multi-scale interaction model and the statistical inference model of the digital twin;

inputting new observation data of the repair entity sample collected in real time into the data assimilation model of the digital twin to be trained for updating, to obtain the data assimilation model of the digital twin; and

integrating the statistical inference model, the multi-scale interaction model and the data assimilation model in the digital twin to obtain the digital twin.

According to embodiments of the present disclosure, the new observation data may be repair data, the repair data includes repair process parameters and observation data, and the observation data can be data detected by an instrument.

According to embodiments of the present disclosure, any two or more of the real-time data transmission module 310, the digital model acquisition module 320, the intelligent repair design module 330, the digital twin control module 340, and the repair tool module 350 may be combined in a single module, or any of the modules may be split into multiple modules. Alternatively, at least some of the functionality of one or more of these modules can be combined with at least some of the functionality of other modules and implemented in a single module. According to embodiments of the present disclosure, at least one of the real-time data transmission module 310, the digital model acquisition module 320, the intelligent repair design module 330, the digital twin control module 340, and the repair tool module 350 can be at least partially implemented as a hardware circuit, such as field programmable gate arrays (FPGA) , programmable logic arrays (PLA) , system-on-chip, system-on-substrate, system-on-package, application-specific integrated circuits (ASIC) , or any other reasonable means by which circuits are integrated or packaged, or can be implemented in any one or any appropriate combination of software, hardware, and firmware. Alternatively, at least one of the real-time data transmission module 310, the digital model acquisition module 320, the intelligent repair design module 330, the digital twin control module 340, and the repair tool module 350 may be at least partially implemented as a computer program module, which can perform the corresponding function when the computer program module is run.

As shown in Fig. 4, the intelligent repair and life cycle management of composite materials in the embodiments of the present disclosure includes: giving repair task for composite material 401, intelligent repair process for composite material 402, and life cycle management for repair entity of composite material repair 403, where the intelligent repair process 402 includes: a repair entity of composite material and an intelligent repair design device for composite material 4021, a digital twin 4022 and a virtual-real fusion interface 4023.

The repair entity of the composite material includes laminates, honeycomb laminates and other composite repair structures. The intelligent repair design device for composite material includes testing, drilling, digging, layering, heating blanket, vacuum bag, digital repair device, curing unit, large area and high-mobility non-destructive testing unit, composite material repair vehicle and other repair modules; and related character input part, image input part, graphic input part, sound input part, storage, processor and output part. The virtual-real fusion interface 4023 is used to expand the function of virtual-real interaction between the intelligent repair design device for composite material 4021 and the digital twin 4022, such as wireless data transmission and life cycle management.

Specifically, after receiving the repair task for composite material 401, the intelligent repair process for composite material 402 is carried out. In the repair process, the digital twin is constructed, the digital twin is used to implement the intelligent repair of the repair entity, and the digital twin is used to manage the whole life cycle of the repair entity of the composite material in the operation process. The whole life cycle management includes the management of the repair entity during the repair process, and the life management of the repair entity during the service phase after the repair.

As shown in Fig. 5, the intelligent repair device 500 for composite material according to the embodiments of the present disclosure includes a processor 501 that can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 502 or loaded from the storage part 508 into random access memory (RAM) 503. The processor 501 may include, for example, a general-purpose microprocessor (e.g., CPU) , an instruction set processor and/or associated chipset, and/or a specialized microprocessor (e.g., an application-specific integrated circuit (ASIC) ) , etc. The processor 501 may also include onboard memory for caching purposes. The processor 501 may include a single processing unit or multiple processing units for performing different actions of the intelligent repair method for composite material according to the embodiments of the present disclosure.

In the RAM 503, various programs and data, such as digital twins, are stored for the operation of the intelligent repair device 500 for composite material. The processor 501, ROM 502, and RAM 503 are connected to each other via a bus 504. Processor 501 performs various operations of the intelligent repair method for composite material according to the embodiments of the present disclosure by executing programs in ROM 502 and/or RAM 503. It should be noted that the program may also be stored in one or more memories other than ROM 502 and RAM 503. The processor 501 may also perform various operations of the intelligent repair method for composite material according to the embodiments of the present disclosure by executing programs stored in the one or more memories.

According to embodiments of the present disclosure, the intelligent repair electronic device 500 for composite material may also include an input/output (I/O) interface 505. The input/output (I/O) interface 505 is also connected to the bus 504. The intelligent repair device 400 for composite material may also include one or more of the following components connected to the input/output (I/O) interface 505: a virtual-real fusion interface (not shown) for the virtual-real interaction of the repair entity with the digital twin, an input part 506, an output part 507, a storage part 508, a communication part 509, a drive 510, and a removable media 511. The input part 506 includes a repair tool device, a text input device, a sound input device, a graphic device, an image input device, etc., and the input part 506 is used to obtain repair information of the repair entity, the repair information includes at least one of repair tool module information, text information, image information and graphic information, the repair tool device can be detecting device, drilling device, digging device, laying device, curing device, etc., and the text input device can be related characters. The output part 507 includes cathode ray tube (CRT) , liquid crystal display (LCD) , printer, plotter, imaging device, voice device, magnetic recording device, and loudspeaker device, etc., and the output part 507 is used to output real-time repair information of the repair entity. The storage part 508 includes a hard disk, etc. The communication part 509 includes a network interface card, such as LAN card, modem, etc. The communication part 509 performs communication processing over a network such as the Internet. The drive 510 is also connected to the input/output (I/O) interface 505 as required. The removable media 511, such as disk, optical disc, magnetic disc, semiconductor memory, etc., is installed on the drive 510 as required so that computer programs read from it are installed into the storage part 508 as required.

The disclosure also provides a computer readable storage medium that may be included in the apparatus/device/system described in the above embodiments. The computer readable storage medium can also exist separately and not be incorporated into the equipment/device/system. The computer readable storage medium carries one or more programs, and when the one or more programs are executed, the intelligent repair method for composite material according to the embodiments of the present disclosure is realized.

According to embodiments of the present disclosure, the computer readable storage medium may be a non-volatile computer readable storage medium, which may include, for example, but is not limited to: portable computer disk, hard disk, random access memory (RAM) , read only memory (ROM) , erasable programmable read only memory (EPROM or flash memory) , portable compact disk read only memory (CD-ROM) , optical storage device, magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or apparatus. For example, according to embodiments of the present disclosure, the computer readable storage medium may include the ROM 502 and/or RAM 503 as described above and/or one or more memories other than the ROM 502 and/or RAM 503.

According to the embodiments of the present disclosure, a computer program product is also provided, which includes a computer program containing program code for performing the method shown in the flow chart. When the computer program product is running in the computer system, the program code is used to cause the computer system to implement the intelligent repair method for composite material provided in the embodiments of the present disclosure.

The above functions defined in the system of the embodiments of the present disclosure are performed when the computer program is executed by the processor 501. According to embodiments of the present disclosure, the systems, modules, units, etc. described above may be implemented by computer program modules.

In an embodiment, the computer program may rely on a tangible storage medium such as an optical storage device, a magnetic storage device, etc. In another embodiment, the computer program may also be transmitted, distributed as a signal over a network medium, and downloaded and installed via the communication part 509, and/or installed from the removable media 511. The computer program contains program code that may be transmitted over any appropriate network medium, including but not limited to wireless network medium, wired network medium, etc., or any suitable combination of the above.

In such embodiments, the computer program may be downloaded and installed from the network via the communication part 509, and/or installed from the removable media 511. When the computer program is executed by the processor 501, the above functions defined in the system of the embodiments of the present disclosure are performed. According to embodiments of the present disclosure, the systems, devices, apparatuses, modules, units, etc. described above may be implemented by computer program modules.

According to the embodiments of the present disclosure, program code for executing computer programs provided by the embodiments of the present disclosure may be written in any combination of one or more programming languages, and specifically, these computational programs may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. The programming languages include, but are not limited to, programming languages such as Java, C++, python, the "C" language, or similar. The program code may be executed entirely on the user computing device, partially on the user computing device, partially on the remote computing device, or completely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device over any kind of network, including a local area network (LAN) or wide area network (WAN) , or may be connected to an external computing device (for example, using an Internet service provider to connect over the Internet) .

The flow charts and block diagrams in the attached drawings illustrate the possible realization of the architecture, functions, and operations of the systems, methods, and computer program products in accordance with various embodiments of the present disclosure. At this point, each box in a flowchart or block diagram may represent a module, program segment, or part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the box can also occur in a different order than those indicated in the accompanying drawings. For example, two boxes that are shown consecutively can actually be executed basically in parallel, and they can sometimes be executed in a reverse order, depending on the functionality involved. It should also be noted that each box in a block diagram or flow chart, and combinations of boxes in a block diagram or flow chart, may be implemented by a dedicated hardware-based system that performs a specified function or operation, or by a combination of dedicated hardware and computer instructions.

It is understood by those skilled in the art that the features described in the various embodiments and/or claims of this disclosure may be combined and/or grouped in a number of ways, even if such combination or grouping is not expressly stated in the disclosure. In particular, without departing from the spirit and teachings of the disclosure, the features recorded in the various embodiments and/or claims of the disclosure may be combined and/or grouped in a variety of ways. All such combinations and/or groupings fall within the scope of this disclosure.

Claims

An intelligent repair method using a digital twin for composite material repair, comprising:

transmitting repair factors of a repair entity of a composite material acquired in real time to the digital twin for composite material repair, wherein the repair factors comprise damage parameters, repair process parameters and structural parameters;

establishing an initial visual digital model of the repair entity by the digital twin according to the structural parameters and the damage parameters of the repair entity, wherein the initial visual digital model is used to describe the structural parameters and the damage parameters of the repair entity;

predicting critical operational characteristics of different combinations of repair process parameters through the digital twin performing a design space search according to the repair process parameters, to obtain target repair process parameters required for the repair entity to reach the critical operational characteristics after the repair entity being repaired;

predicting in real time a full-field distribution information of the critical operational characteristics of the repair entity by the digital twin according to the repair process parameters and the initial visual digital model, displaying and analyzing the full-field distribution information in real time, and transmitting the received target repair process parameters to a repair tool; and

setting a repair procedure by the repair tool according to the received target repair process parameters to implement the repair of the repair entity.
The method of claim 1, wherein the repair entity is: a physical component that has suffered damage during a manufacturing and/or a service process; and

the composite material is composed of at least two components and has anisotropic mechanical properties.
The method of claim 1, wherein the design space search is achieved by:

obtaining the critical operational characteristics of the repair entity after being repaired, under a combination of repair process parameters in a design space by using a reduced-order model through the digital twin,

wherein the combination of repair process parameters comprises at least one combination of a temperature, a pressure, a size, a time, a curing degree, and a tool path, and

the critical operational characteristics comprise at least one of the curing degree, a deformation, a strain, a stress, a tensile strength, an impact strength, a hardness, a plasticity, and a toughness.
The method of claim 1, further comprising:

regulating a repair process of the repair tool to the repair entity according to the repair procedure.
The method of claim 4, further comprising:

monitoring in real time, by using the digital twin, parameter changes of the repair entity during a service phase after the repair entity being repaired.
The method of claim 4 or 5, further comprising:

dynamically updating the digital twin by using repair data of the repair entity collected in real time during the repair procedure, wherein the repair data comprises repair process parameters and observation data.
The method of claim 6, further comprising:

establishing a digital twin database for composite material repair according to accumulated repair data of a plurality of repair entities and corresponding digital twins, to realize an analysis, an update, and an evolution of the digital twin.
The method of claim 1, wherein the digital twin is obtained by training a digital twin to be trained using training data and/or observation data collected in real time, wherein a repair digital model established by repair factors of a repair entity sample and a mechanism model established during a repair procedure of the repair entity sample are used as the training data.
The method of claim 8, wherein the digital twin comprises a statistical inference model, a multi-scale interaction model and a data assimilation model, and the digital twin is trained by:

establishing the repair digital model which reflects the repair factors of the repair entity sample according to the repair entity sample, and establishing the mechanism model which describes the repair procedure according to an internal mechanism of the repair entity sample in the repair procedure;

determining the repair digital model and the mechanism model of the repair entity sample as the training data and a mechanism constraint of the digital twin to be trained;

training the statistical inference model in the digital twin to be trained according to the training data, the observation data of the repair entity sample collected in real time, and prior knowledge data in the mechanism model, and outputting prediction data;

calculating a loss value under the constraint of the mechanism model according to the prediction data and the observation data of the repair entity sample collected in real time, to obtain a loss result, and iteratively adjusting parameters of the multi-scale interaction model in the digital twin to be trained by using the loss result, to obtain the multi-scale interaction model and the statistical inference model of the digital twin;

inputting new observation data of the repair entity sample collected in real time into the data assimilation model of the digital twin to be trained for updating, to obtain the data assimilation model of the digital twin; and

integrating the statistical inference model, the multi-scale interaction model and the data assimilation model in the digital twin to obtain the digital twin.
The method of claim 9, wherein the internal mechanism of the repair entity sample in the repair procedure comprises at least one of:

a basic law required by the digital twin, a thermodynamic coupling dynamic equation, a material constitutive model, a damage evolution model, a fatigue failure model, a physical significance of parameters in the mechanism model, and a repair process of the composite material.
An intelligent repair system for composite material, comprising:

a real-time data transmission module, configured to transmit repair factors of a repair entity of a composite material acquired in real time to the digital twin for composite material repair, wherein the repair factors comprise damage parameters, repair process parameters and structural parameters;

a digital model acquisition module, configured to establish an initial visual digital model of the repair entity by the digital twin according to the structural parameters and the damage parameters of the repair entity, wherein the initial visual digital model is used to describe the structural parameters and the damage parameters of the repair entity;

an intelligent repair design module, configured to predict critical operational characteristics of different combinations of repair process parameters through the digital twin performing a design space search according to the repair process parameters, to obtain target repair process parameters required for the repair entity to reach the critical operational characteristics after the repair entity being repaired;

a digital twin control module, configured to predict a full-field distribution information of the critical operational characteristics of the repair entity by the digital twin according to the repair process parameters and the initial visual digital model, display and analyze the full-field distribution information in real time, and transmit the received target repair process parameters to a repair tool module; and

the repair tool module, configured to set a repair procedure according to the received target repair process parameters to implement the repair of the repair entity.
The system of claim 11, wherein the system comprises a digital twin constructing module configured to construct the digital twin;

wherein the digital twin is obtained by training a digital twin to be trained using training data and/or observation data collected in real time, wherein a repair digital model established by repair factors of a repair entity sample and a mechanism model established during a repair procedure of the repair entity sample are used as the training data.
The system of claim 12, wherein the digital twin constructing module comprises a statistical inference model, a multi-scale interaction model and a data assimilation model, and the digital twin is trained by:

establishing the repair digital model which reflects the repair factors of the repair entity sample according to the repair entity sample, and establishing the mechanism model which describes the repair procedure according to an internal mechanism of the repair entity sample in the repair procedure;

determining the repair digital model and the mechanism model of the repair entity sample as the training data and a mechanism constraint of the digital twin to be trained;

training the statistical inference model in the digital twin to be trained according to the training data, the observation data of the repair entity sample collected in real time, and prior knowledge data in the mechanism model, and outputting prediction data;

calculating a loss value under the constraint of the mechanism model according to the prediction data and the observation data of the repair entity sample collected in real time, to obtain a loss result, and iteratively adjusting parameters of the multi-scale interaction model in the digital twin to be trained by using the loss result, to obtain the multi-scale interaction model and the statistical inference model of the digital twin;

inputting new observation data of the repair entity sample collected in real time into the data assimilation model of the digital twin to be trained for updating, to obtain the data assimilation model of the digital twin; and

integrating the statistical inference model, the multi-scale interaction model and the data assimilation model in the digital twin to obtain the digital twin.
The system of claim 11, wherein the real-time data transmission module comprises: a damage scanning and identification module and a sensor;

wherein the damage scanning and identification module is configured to scan a damage characteristic of a damage part, and obtain a damage parameter by using an image recognition and processing technology; and

the sensor is configured to measure repair process parameters of the repair procedure.
The system of claim 11, wherein the intelligent repair design module further comprises: an update module configured to dynamically update the digital twin by using repair data of the repair entity collected in real time accumulated during the repair procedure, wherein the repair data comprises repair process parameters and observation data.
The system of claim 11, wherein the repair tool module comprises at least one of:

a modular repair unit, a non-destructive testing unit, a composite material pretreatment unit, a curing repair unit, an unmanned aerial vehicle repair unit, and a repair vehicle repair unit.
The system of claim 11, wherein the digital twin control module further comprises:

an adjustment unit, configured to regulate a repair process of the repair tool module to the repair entity according to the repair procedure;

wherein the manner of using the adjustment unit of the digital twin control module to regulate the repair process of the repair tool module to the repair entity comprises at least one of a single-chip digital automatic control, a full voltage starting, a voltage ramp starting, a voltage step starting and a current limiting starting.
The system of claim 17, further comprising:

a life cycle management module, configured to monitor in real time, by using the digital twin, parameter changes of the repair entity during a service phase after the repair entity being repaired.
The system of claim 18, further comprising:

a digital twin database, configured to establish a digital twin database for composite material repair according to accumulated repair data of a plurality of repair entities and corresponding digital twins, to realize an analysis, an update and an evolution of the digital twin for composite material repair.
An intelligent repair device for composite material, comprising the system of any one of claims 11 to 19;

an input part, configured to obtain repair information of the repair entity, wherein the repair information comprises at least one of repair tool module information, text information, image information and graphic information;

a storage part, configured to store a computer program comprising the digital twin;

a processor, configured to execute the method of any one of claims 1 to 10;

an output part, configured to output real-time repair information of the repair entity; and

a virtual-real fusion interface, configured for a virtual-real interaction between the repair entity and the digital twin.
The device of claim 20, wherein

the input part comprises at least one of a repair tool device, a text input device, a sound input device and an image input device; and

the output part comprises at least one of a display, a printer, a plotter, an image device, a voice device and a magnetic recording device.