WO2019136001A1

WO2019136001A1 - Improved computer processing based on data taxonomy-driven workflow processing and computer systems configured for utilizing thereof

Info

Publication number: WO2019136001A1
Application number: PCT/US2018/067976
Authority: WO
Inventors: Haresh G. MALKANI; Sergio Butkewitsch CHOZE
Original assignee: Arconic Inc
Current assignee: Howmet Aerospace Inc
Priority date: 2018-01-08
Filing date: 2018-12-28
Publication date: 2019-07-11
Anticipated expiration: 2020-07-08

Abstract

Disclosed are various embodiments of systems and methods for specifically relates to systems and methods for the improved computer processing based on data taxonomy-driven workflow processing in various computer-required processes of various technological areas. An embodiment of the present disclosure provides a method that at least includes the steps of: providing, by a computer, a taxonomy library of candidate node structures to a user; receiving, by the computer, from the user, a respective workflow design data that defines a respective workflow taxonomy for a respective manufacturing process; generating, by the computer, a respective workflow data object for the respective manufacturing process based at least in part on the respective workflow taxonomy; and causing, by the computer, a performance of the respective manufacturing process in accordance with the respective workflow data object.

Description

IMPROVED COMPUTER PROCESSING BASED ON DATA TAXONOMY-DRIVEN WORKFLOW PROCESSING AND COMPUTER SYSTEMS CONFIGURED FOR

UTILIZING THEREOF

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] The present application claims priority from U.S. Provisional Patent Application No. 62/614,823 filed January 8, 2018, and entitled “COMPUTER-DRIVEN SYSTEMS AND COMPUTER-IMPLEMENTED METHODS CONFIGURED FOR DATABASE DRIVEN RECURSIVE WORKFLOW GENERATION,” which is incorporated herein by reference in its entirety for all purposes.

FIELD OF TECHNOLOGY

[0002] The subject matter herein generally relates to the improved computer processing based on data taxonomy-driven workflow processing (e.g., generation, execution, etc.) and computer systems configured for utilizing thereof as applied in various computer-required processes of various technological areas.

BACKGROUND OF TECHNOLOGY

[0003] Typically, various processes in various technological areas may only proceed in accordance with workflow(s) that define at least critical step(s) and/or condition(s) of each such process. Typically, generating and/or running a particular workflow requires considerable computer processing power due to numerous criteria and/or conditions that would be needed to be determined and/or analyzed by the computer.

SUMMARY OF THE INVENTION

[0004] The present disclosure provides systems and methods for the improved computer processing based on data taxonomy-driven workflow processing in various computer-required processes of various technological areas. An embodiment of the present disclosure provides a method that at least includes the steps of: providing, by a computer, a taxonomy library of candidate node structures to at least one user; where each respective candidate node structure represents each respective workflow activity and includes: i) at least one node-definition element, identifying the at least one respective workflow activity associated with each respective candidate node, ii) at least one node-function element, identifying at least one respective software function to be executed in performing the at least one respective workflow activity, iii) at least one node- input parameter, identifying at least one input parameter that the at least one respective computer function requires to receive to perform the at least one respective workflow activity, and iv) at least one node-output parameter, identifying at least one output parameter that the at least one respective computer function outputs after performing the at least one respective workflow activity; receiving, by the computer, from the at least one user, a respective workflow design data that defines a respective workflow taxonomy for a respective manufacturing process; where the workflow design data includes: i) a node selection, identifying a plurality of selected node structures from the taxonomy library of candidate node structures, and ii) a node sequence, identifying a sequence in which the plurality of selected node structures to be executed; generating, by the computer, a respective workflow data object for the respective manufacturing process based at least in part on the respective workflow taxonomy; and causing, by the computer, a performance of the respective manufacturing process in accordance with the respective workflow data object.

[0005] An embodiment of the present disclosure provides a system that includes at least the following components: at least one processor; and a non-transitory computer readable storage medium storing thereon program logic, where, when executing the program logic, the at least one processor is configured to: provide a taxonomy library of candidate node structures to at least one user; where each respective candidate node structure represents each respective workflow activity and includes: i) at least one node-definition element, identifying the at least one respective workflow activity associated with each respective candidate node, ii) at least one node-function element, identifying at least one respective software function to be executed in performing the at least one respective workflow activity, iii) at least one node-input parameter, identifying at least one input parameter that the at least one respective computer function requires to receive to perform the at least one respective workflow activity, and iv) at least one node-output parameter, identifying at least one output parameter that the at least one respective computer function outputs after performing the at least one respective workflow activity; receive, from the at least one user, a respective workflow design data that defines a respective workflow taxonomy for a respective manufacturing process; where the workflow design data includes: i) a node selection, identifying a plurality of selected node structures from the taxonomy library of candidate node structures, and ii) a node sequence, identifying a sequence in which the plurality of selected node structures to be executed; generate a respective workflow data object for the respective manufacturing process based at least in part on the respective workflow taxonomy; and cause a performance of the respective manufacturing process in accordance with the respective workflow data object.

[0006] In some embodiments, the at least one respective workflow activity is associated with at least one machinery utilized by a respective manufacturing process.

[0007] In some embodiments, the exemplary method may further include receiving, by the computer, a pre-defmed node structure data for a plurality of manufacturing processes, manufacturing machinery, or both; where the pre-defmed node structure data defines each of: i) the at least one node-definition element, ii) the at least one node-function element, iii) the at least one node-input parameter, and iv) at least one node-output parameter; and populating, by the computer, the taxonomy library of candidate node structures based at least in part on the pre- defined node structure data.

[0008] In some embodiments, the respective workflow data object is a computer simulation of the respective manufacturing process.

[0009] In some embodiments, the respective workflow data object includes a graphical interface configured to display the performance of the respective manufacturing process in accordance with the respective workflow data object.

[00010] In some embodiments, the respective workflow data object includes a graphical interface configured to display the computer simulation of the performance of the respective manufacturing process in accordance with the respective workflow data object.

[00011] In some embodiments, the step of receiving, from the at least one user, the respective workflow design data for the respective workflow taxonomy for the respective manufacturing process, including: receiving, by the computer, via a workflow design graphical user interface, the respective workflow design data.

[00012] In some embodiments, the step of receiving, from the at least one user, the respective workflow design data for the respective workflow taxonomy for the respective manufacturing process, including: receiving, by the computer, via at least one verbal instruction, the respective workflow design data.

[00013] In some embodiments, the step of receiving, via the at least one verbal instruction, the respective workflow design data, including: generating, by at least one sound processing device, the respective workflow design data based at least in part on the at least one verbal instruction; and where the at least one sound processing device includes at least one of: i) a speech decoder, ii) a Natural Language Understanding software engine, or iii) a Natural Language Generation software engine.

[00014] In some embodiments, the step of receiving the pre-defmed node structure data, including: receiving, by at least one sound processing device, at least one verbal instruction; generating, by the at least one sound processing device, the pre-defmed node structure data based at least in part on the at least one verbal instruction; and where the at least one sound processing device includes at least one of: i) a speech decoder, ii) a Natural Language Understanding software engine, or iii) a Natural Language Generation software engine.

[00015] In some embodiments, the respective manufacturing process is an Additive Manufacture (AM) build process of building an AM part by an AM machine.

[00016] In some embodiments, the respective workflow taxonomy is a nested workflow taxonomy.

BRIEF DESCRIPTION OF THU DRAWINGS

[00017] The present disclosure can be further explained with reference to the attached drawings, wherein like structures are referred to by like numerals throughout the several views. The drawings shown are not necessarily to scale, with emphasis instead generally being placed upon illustrating the principles of the present disclosure. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a representative basis for teaching one skilled in the art to variously employ the present disclosure.

[00018] Fig. 1 illustrates an exemplary diagram according to an embodiment of the present disclosure;

[00019] Fig. 2 shows an illustrative example of a block diagram according to an embodiment of the present disclosure; [00020] Fig. 3 shows an illustrative example of a diagram according to an embodiment of the present disclosure;

[00021] Fig. 4 illustrates an exemplary diagram according to an embodiment of the present disclosure;

[00022] Fig. 5 illustrates an exemplary diagram according to an embodiment of the present disclosure;

[00023] Fig. 6 A illustrates an exemplary diagram according to an embodiment of the present disclosure;

[00024] Fig. 6B illustrates an exemplary diagram according to an embodiment of the present disclosure;

[00025] FIG. 7 is a schematic illustration of an overall architecture of that may occur within an exemplary inventive computer-based AM systems and related methods according to one or more embodiments of the present disclosure;

[00026] FIG. 8 is a schematic representation of an exemplary inventive computer-based AM system according to an embodiment of the present disclosure; and

[00027] FIG. 9 illustrates an exemplary diagram according to an embodiment of the present disclosure.

PET ATT, ED DESCRIPTION OF THE INVENTION

[00028] The present disclosure can be further explained with reference to the included drawings, wherein like structures are referred to by like numerals throughout the several views. The drawings shown are not necessarily to scale, with emphasis instead generally being placed upon illustrating the principles of the present disclosure. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a representative basis for teaching one skilled in the art to variously employ the present disclosure.

[00029] Among those benefits and improvements that have been disclosed, other objects and advantages of this invention can become apparent from the following description taken in conjunction with the accompanying figures. Detailed embodiments of the present disclosure are disclosed herein; however, it is to be understood that the disclosed embodiments are merely illustrative of the invention that may be embodied in various forms. In addition, each of the examples given in connection with the various embodiments of the present disclosure is intended to be illustrative, and not restrictive.

[00030] Throughout the specification, the following terms take the meanings explicitly associated herein, unless the context clearly dictates otherwise. The phrases“in one embodiment” and“in some embodiments” as used herein do not necessarily refer to the same embodiment s), though they may. Furthermore, the phrases “in another embodiment” and “in some other embodiments” as used herein do not necessarily refer to a different embodiment, although they may. Thus, as described below, various embodiments of the invention may be readily combined, without departing from the scope or spirit of the invention. Further, when a particular feature, structure, or characteristic is described in connection with an implementation, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other implementations whether or not explicitly described herein.

[00031] The term "based on" is not exclusive and allows for being based on additional factors not described, unless the context clearly dictates otherwise. In addition, throughout the specification, the meaning of "a," "an," and "the" include plural references. The meaning of "in" includes "in" and "on. [00032] It is understood that at least one aspect/functionality of various embodiments described herein can be performed in real-time, faster-than-real-time, and/or dynamically. As used herein, the term“real-time” is directed to an event/action that can occur instantaneously or almost instantaneously in time when another event/action has occurred. For example, the“real-time processing,”“real-time computation,” and“real-time execution” pertain to the performance of a computation prior to an actual time that the related physical process or physical transformation occurs (e.g., adding a build layer to an AM part), so that results of the real-time computation (e.g., a simulated dynamics model of the AM part being built) can be used in guiding the physical process (e.g., AM process). As used herein, the term“faster-than-real-time” is directed to simulations in which advancement of simulation time may occur faster than real world time. For example, some of the“faster-than-real-time” simulations of the present disclosure may be configured in accordance with one or more principles detailed in D. Anagnostopoulos, 2002, “Experiment scheduling in faster-than-real-time simulation,” 148-156. 10.1109/PADS.2002.1004212.

[00033] As used herein, the term“dynamically” means that events and/or actions can be triggered and/or occur without any human intervention. In some embodiments, events and/or actions in accordance with the present disclosure can be in real-time and/or based on a predetermined periodicity of at least one of: nanosecond, several nanoseconds, millisecond, several milliseconds, second, several seconds, minute, several minutes, hourly, several hours, daily, several days, weekly, monthly, etc.

[00034] As used herein, the term“runtime” corresponds to any behavior that is dynamically determined during an execution of a software application or at least a portion of software application. [00035] In some embodiments, the inventive specially programmed computing systems with associated devices are configured to operate in the distributed network environment, communicating over a suitable data communication network (e.g., the Internet, etc.) and utilizing at least one suitable data communication protocol (e.g., IPX/SPX, X.25, AX.25, AppleTalk(TM), TCP/IP (e.g., HTTP), etc.). Of note, the embodiments described herein may, of course, be implemented using any appropriate hardware and/or computing software languages. In this regard, those of ordinary skill in the art are well versed in the type of computer hardware that may be used, the type of computer programming techniques that may be used (e.g., object oriented programming), and the type of computer programming languages that may be used (e.g., C++, Objective-C, Swift, Java, JavaScript). The aforementioned examples are, of course, illustrative and not restrictive.

[00036] The material disclosed herein may be implemented in software or firmware or a combination of them or as instructions stored on a machine-readable medium, which may be read and executed by one or more processors. As used herein, the machine-readable medium may include any medium and/or mechanism for storing or transmitting information in a form readable by a machine (e.g., a computing device). By way of example, and not limitation, the machine- readable medium may comprise computer readable storage media, for tangible or fixed storage of data, or communication media for transient interpretation of code-containing signals. Machine- readable storage media, as used herein, refers to physical or tangible storage (as opposed to signals) and includes without limitation volatile and non-volatile, removable and non-removable media implemented in any method or technology for the tangible storage of information such as computer-readable instructions, data structures, program modules or other data. Machine-readable storage media includes, but is not limited to, RAM, ROM, EPROM, EEPROM, flash memory or other solid state memory technology, CD-ROM, DVD, or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, flash memory storage, or any other physical or material medium which can be used to tangibly store the desired information or data or instructions, including but not limited to electrical, optical, acoustical or other forms of propagated signals (e.g., carrier waves, infrared signals, digital signals, etc.), and which can be accessed by a computer or processor.

[00037] In another form, a non-transitory article, such as non-volatile and non-removable computer readable media, may be used with any of the examples mentioned above or other examples except that it does not include a transitory signal per se. It does include those elements other than a signal per se that may hold data temporarily in a“transitory” fashion such as RAM and so forth. In some embodiments, the present disclosure may rely on one or more distributed and/or centralized databases (e.g., data center).

[00038] As used herein, the term“server” should be understood to refer to a service point which provides processing, database, and communication facilities. By way of example, and not limitation, the term “server” can refer to a single, physical processor with associated communications and data storage and database facilities, or it can refer to a networked or clustered complex of processors and associated network and storage devices, as well as operating software and one or more database systems and application software that support the services provided by the server. Servers may vary widely in configuration or capabilities, but generally a server may include one or more central processing units and memory. A server may also include one or more mass storage devices, one or more power supplies, one or more wired or wireless network interfaces, one or more input/output interfaces, or one or more operating systems, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, or the like. [00039] As used herein, a“network” should be understood to refer to a network that may couple devices so that communications may be exchanged, such as between a server and a client device or other types of devices, including between wireless devices coupled via a wireless network, for example. A network may also include mass storage, such as network attached storage (NAS), a storage area network (SAN), or other forms of computer or machine-readable media, for example. A network may include the Internet, one or more local area networks (LANs), one or more wide area networks (WANs), wire-line type connections, wireless type connections, cellular or any combination thereof. Likewise, sub-networks, which may employ differing architectures or may be compliant or compatible with differing protocols, may interoperate within a larger network. Various types of devices may, for example, be made available to provide an interoperable capability for differing architectures or protocols. As one illustrative example, a router may provide a link between otherwise separate and independent LANs.

[00040] As used herein, the terms“computer engine” and“engine” identify at least one software component and/or a combination of at least one software component and at least one hardware component which are designed/programmed/configured to manage/control other software and/or hardware components (such as the libraries, software development kits (SDKs), objects, etc.).

[00041] Examples of hardware elements may include processors, microprocessors, circuits, circuit elements (e.g., transistors, resistors, capacitors, inductors, and so forth), integrated circuits, application specific integrated circuits (ASIC), programmable logic devices (PLD), digital signal processors (DSP), field programmable gate array (FPGA), logic gates, registers, semiconductor device, chips, microchips, chip sets, and so forth. In some embodiments, the one or more processors may be implemented as a Complex Instruction Set Computer (CISC) or Reduced Instruction Set Computer (RISC) processors; x86 instruction set compatible processors, multi- core, or any other microprocessor or central processing unit (CPU). In various implementations, the one or more processors may be dual -core processor(s), dual-core mobile processor(s), and so forth.

[00042] Software may refer to 1) libraries; and/or 2) software that runs over the internet or whose execution occurs within any type of network. Examples of software may include, but are not limited to, software components, programs, applications, computer programs, application programs, system programs, machine programs, operating system software, middleware, firmware, software modules, routines, subroutines, functions, methods, procedures, software interfaces, application program interfaces (API), instruction sets, computing code, computer code, code segments, computer code segments, words, values, symbols, or any combination thereof. Determining whether an embodiment is implemented using hardware elements and/or software elements may vary in accordance with any number of factors, such as desired computational rate, power levels, heat tolerances, processing cycle budget, input data rates, output data rates, memory resources, data bus speeds and other design or performance constraints.

[00043] One or more aspects of at least one embodiment may be implemented by representative instructions stored on a machine-readable medium which represents various logic within the processor, which when read by a machine causes the machine to fabricate logic to perform the techniques described herein. Such representations, known as“IP cores” may be stored on a tangible, machine readable medium and supplied to various customers or manufacturing facilities to load into the fabrication machines that actually make the logic or processor.

[00044] In some embodiments, as shown in Figures 1-3, the exemplary inventive database- driven recursive workflow generation system may utilize suitable taxonomy model(s), textual definitions, and/or verbal definitions, in the form of nodes, to generate one or more database-driven recursive workflows tailored to particular manufacturing flow path(s).

[00045] For example, as shown in Figure 3, exemplary structure of each node may include: description, function, performance sequence within a workflow, input(s), and output(s). For example, in Figure 3, the exemplary inventive database-driven recursive workflow generation system may utilize recursive processing of node structures to generate at least one workflow related to a use of computer-aided drafting (CAD) software as part of a rolling workflow.

[00046] In some embodiments, taxonomy model(s) may be applied in various suitable categories of machines and product manufacturing processes. For example, the use of the inventive taxonomy may be expanded into, without limitation, cast house, scalper and/or rolling mill(s). For example, taxonomy elements (nodes) of a rolling mill may include stands, oil house, sprays, etc. Within stands, a hierarchy may be defined further with support rolls and/or working rolls.

[00047] In some embodiment, the exemplary inventive database-driven recursive workflow generation system may utilize an exemplary designing-centric workflow engine built based, at least in part, on modeFRONTIER workflow environment (ESTECO SpA, Trieste, Italy) and/or PARC view tools (dataPARC, Vancouver, WA) to automate one of more stages of manufacturing path flow generation. An exemplary automation of construction workflows is detailed in Guenov. et ah, Computational design process modelling (2006).

[00048] In some embodiments, the exemplary inventive database-driven recursive workflow generation system may be configured/programmed to further utilize a taxonomy pre processing module to predefine a schema for each node of the exemplary workflow in order to automate the data flow definition processing. In particular, the taxonomy of each candidate node (data structure) may be configured to target representation of information pertaining to individual manufacturing machine/processing center so that the illustrative workflow itself would correspond to a manufacturing flow-path. In some embodiments, the exemplary inventive database-driven recursive workflow generation system may be configured/programmed to utilize a collection of data taxonomy definitions (a data taxonomy library) that may be configured to be reused in subsequent workflows.

[00049] Fig. 1 shows an illustrative example of a block diagram 100 depicting one example of an initial step of the use of the workflow with a fixed structure to construct a relational database that may be utilized by the exemplary inventive database-driven recursive workflow generation system. In particular, at step 102, the exemplary inventive database-driven recursive workflow generation system defines a collection of nodes in the workflow. Then, at step 104, the exemplary inventive database-driven recursive workflow generation system defines a sequence of nodes in the workflow. The exemplary inventive database-driven recursive workflow generation system further defines the computer software underpinning each workflow (an executable or any other form that can be run by the workflow) at step 106. In some embodiments, any node of the workflow can range from a full-fledged computer simulation code (or its physical database counterpart) to a very simple logical operator.

[00050] For defining the activity flow at step 108, the exemplary inventive database-driven recursive workflow generation system may define input data for each node of the workflow and then, at step 110, the exemplary inventive database-driven recursive workflow generation system may define the output data from each node in the workflow.

[00051] Fig. 2 shows an illustrative example of a data schema (node-based data taxonomy structure) of a database 202 constructed by the process 100 of Fig. 1 that may occur within an exemplary inventive database-driven recursive workflow generation system. The exemplary database 202 may be parsed for the construction of the workflow, in a recursive fashion, to build one or more general purpose workflows. In some embodiments, in the node-based data taxonomy structure of the relational database 202, each row may correspond to one node in the workflow. For example, row 1 of the node-based data taxonomy structure lists parameters of node 1 : Node Description Ndl (data element 1), Node Function Nf2 (data element 2), Node Sequence Nsl (data element 3), Node Inputs Nil (data element 4), Node Outputs Nol (data element 5) are in the same row. For example, row 2 of the node-based data taxonomy structure lists parameters of node 2. Row“n” of the node-based data taxonomy structure lists parameters of node“n”. In some embodiments, columns of the exemplary node-based data taxonomy structure may define the activity flow (102 to 106 in Fig. 1) followed by the data flow (108 to 110 in Fig. 1). In the exemplary embodiment shown in Fig. 2, at step 102 of Fig. 1, the exemplary inventive database- driven recursive workflow generation system may define a collection of nodes Ndl, Nd2 ... Ndn. In some embodiments, the exemplary inventive database-driven recursive workflow generation system may be configured to further define the collection of nodes with their respective node functions Nfl, Nf2, ... Nfn while defining the descriptions of the nodes. Then, at step 104 of Fig. 1, the exemplary inventive database-driven recursive workflow generation system may define a sequence of the nodes Nsl, Ns2, ... Nsn. At step 106 of Fig. 1, the exemplary inventive database- driven recursive workflow generation system may further define the computer software executable by the workflow (e.g., computer-aided drafting (CAD) software) as detailed below regarding Fig. 3.

[00052] In some embodiments, further referring to Fig. 2, at step 108 of Fig. 1, the exemplary inventive database-driven recursive workflow generation system may define the input data for each node Nil, Ni2, ... Nin. Then, at step 110 of Fig. 1, the exemplary inventive database- driven recursive workflow generation system defines the output data for each node Nol, No2, ... Non.

[00053] As per Fig. 2, columns of the exemplary database 202 may define data flow point(s) to other data schema and/or database, in which a full definition of the input and output data may be contained. An example of how the database 202 may correspond to an actual workflow is shown in Fig. 3.

[00054] Fig. 3 shows an illustrative example of the database 202 of Fig. 2 having a corresponding workflow, as applied in an exemplary case of comparing CAD design parameters with measured manufacturing geometries. The illustrative the node-based data taxonomy structure 302 of an exemplary database may be configured in a similar way as the exemplary node-based data taxonomy structure 202 shown in Fig. 2.

[00055] For example, an illustrative activity flow shown in Fig. 3 below the node-based data taxonomy structure 302 with its associated data flows (into and from each node) is represented by arrows and exemplary nodes 304, 306, 308, 310, and 312. At step 302 of the activity flow, the exemplary inventive database-driven recursive workflow generation system may define a collection of nodes:“Id CAD” for inner diameter of an exemplary model designed by the node “CAD” (304),“Od CAD” for outer diameter of the exemplary model designed by the node CAD (304), and“t_CAD” for thickness of the exemplary model designed by the node CAD (304). For example, the exemplary node 306 may be a generic measurement node, having input variables identified with an exemplary subscript“ meas.” For example, the exemplary node 308 may be representative of one or more software functions coded in the statistical computing environment R (C) (The R foundation, www.R-project.org). For example, the R-based functions may include functions programmed to execute within a graphical environment at least one of: linear and generalized linear models, nonlinear regression models, time series analysis, classical parametric and nonparametric tests, or clustering and smoothing. For example, the exemplary node 310 may be representative of one or more software functions coded in the MATLAB (R) (The MathWorks, Inc., Natick, MA) computing environment. For example, the exemplary nodes 308 and 310 may compute the difference (e.g., input/output values identified with the subscript“ diff’) between the output value(s) of the node CAD (304) and the output measured values obtained by the node 306.

[00056] In some embodiments, as utilized for the Additive Manufacture (“AM”) management detailed below, the node CAD (304) may be configured to include one or more embedded AM part build instructions that may utilize the Finite (Element) Analysis for determining the geometric information for the AM part to be built.

[00057] Fig. 4 shows an illustrative example of a recursive construction workflow that may be executed by the exemplary inventive database-driven recursive workflow generation system. In some embodiments, the recursive construction workflow may be configured to provide optional functionalities related to graphics user interfaces (GUI) and configuration control.

[00058] In some embodiments, upon construction of the exemplary node-based data taxonomy structure 202 of Fig. 2 or 302 of Fig. 3, in the following step, a workflow 400 may be configured to parse the node-based data taxonomy structure 202 of Fig. 2 by looping through its rows in a recursive fashion, and execute each node as defined in any given row.

[00059] Specifically, the process of the workflow 400 starts at step 402. In some embodiments, the starting step may include, for example, without limitation, a launch of a web page configured to obtain credentials and/or initialization. In some embodiments, the starting step may include checking working data from a configuration control server (not shown). [00060] For example, at step 404, the exemplary inventive database-driven recursive workflow generation system may start with an entry of Column 1 of the node-based data taxonomy structure of the exemplary database 202 of Fig. 2 to determine if Column 1 may contain an indicator that flags the end or terminal node of the workflow. For example, the exemplary inventive database-driven recursive workflow generation system may be configured to determine that a value of the current entry would be representative of the end of the workflow. If the current entry is not indicative of the end of the workflow, the exemplary inventive database-driven recursive workflow generation system parses node for the current entry. At step 406, the exemplary inventive database-driven recursive workflow generation system may then sequence the node by searching for the next node in sequence upon a defined sequence value in Column 3 of the node- based data taxonomy structure 202 of Fig. 2. Upon sequencing the node, at step 408, the exemplary inventive database-driven recursive workflow generation system may be configured to assign an executable function or call executable software according to the function defined node in column 2 of the node-based data taxonomy structure 202 of Fig. 2. Then, at step 410, the exemplary inventive database-driven recursive workflow generation system may be configured to obtain input from value(s) in Column 4 of the node-based data taxonomy structure 202 of Fig. 2. At step 412, the exemplary inventive database-driven recursive workflow generation system may be configured to establish a data pipe to column 5 of the node-based data taxonomy structure 202 of Fig. 2. At step 414, the exemplary inventive database-driven recursive workflow generation system may be configured to run the above steps recursively for a next row of the node-based data taxonomy structure 202 of Fig. 2 until the exemplary inventive database-driven recursive workflow generation system may determine that the current entry would be equal to an end of the workflow. [00061] In some embodiments, the exemplary inventive database-driven recursive workflow generation system may be configured to utilize a workflow graphical user interface to allow a user to, define the recursive workflow whose definition may be then saved in the format of the node-based data taxonomy structure 202. For example, the workflow GUI may be Internet web based and may be launched through a node early on during the execution of the illustrative recursive construction workflow.

[00062] In some embodiments, the exemplary inventive database-driven recursive workflow generation system may be configured to initiate any data flow by performing a checkout procedure with a configuration server and to end the workflow by returning the output data to the same repository (check-in and commit) by action(s) programmed in the workflow itself.

[00063] In some embodiments, the illustrative the node-based data taxonomy structures 202 of Fig. 2 and 302 of Fig. 3 may be implemented in any database system, including but not limited to various instances of SQL (e.g., MS-SQL, My-SQL, Postgres) and Mongo-DB. In some embodiments, the workflow representation may leverage executable mark-up languages such as but not limited to BPMN, XML, and/or sysML.

[00064] In some embodiments, optionally, the dataflow definition may be automated by reusing a library of pre-defmed entities that follow a given taxonomy. In an exemplary embodiment of a workflow intended to represent a manufacturing flow path, each processing point may be programmed into a respective taxonomy, in which all candidate inputs and outputs of the workflow may be pre-defmed and activated when the corresponding node would be inserted. In some embodiments, the exemplary inventive database-driven recursive workflow generation system may encompass a taxonomy building module, in which rules to define inputs, outputs, and transfer functions would be structured according to a pre-defmed data schema and/or method. For example, an exemplary taxonomy building method may be, but not limited to, SIPOC (Supplier- lnput-Process-Output-Customer) method based on a SIPOC diagram of Fig. 5.

[00065] In some embodiments, the exemplary inventive database-driven recursive workflow generation system may be configured to have an authoring module that may be configured to interface with computer systems of equipment manufacturers to obtain taxonomy templates of their respective equipment.

[00066] In some embodiments, alternative to the relational database, input data (e.g., respective workflow design data, pre-defined node structure data, and/or respective node input data) for generating and/or executing a workflow can be provided verbally (e.g., verbal instruction), through, but not limited to, voice-activated sound processing devices, such that a NLP (Natural Language Processing) decoder that decodifies the speech and a NLU (Natural Language Understanding) software engine of the exemplary inventive database-driven recursive workflow generation system that would take an action upon the decodified content to generate node structures accordingly. In some embodiments, the exemplary inventive database-driven recursive workflow generation system may be configured/programed to utilize a NLG (Natural Language Generation) software engine that may be setup to utilize, whereas the voice commands, instead of text, to generate the workflows themselves.” Figs. 6A and 6B show screenshots with an exemplary desktop and web versions of the inventive workflow generation by the exemplary inventive database-driven recursive workflow generation system respectively which may be implemented in Kepler (an open source platform) based on the recursive element. Such exemplary desktop and web versions of the inventive workflow generation may implement based on verbally input data as described above. [00067] Illustrative use of generic nodes inputs and outputs in the inventive hierarchical workflow processing (e.g.. generation execution etc.)

[00068] In some embodiments, as illustrated in Fig. 9, at least some inventive workflows that may have, without limitation, a nested configuration such that, for example, one or more nodes of such nested inventive workflow may include another entire inventive workflow, hence defining workflows of workflows within a hierarchy (the nested workflow taxonomy). In some embodiments, a number of layers in a respective inventive hierarchy of each nested workflow taxonomy are suitable to capture all steps and/or all parameters a targeted process (e.g., a targeted manufacturing process).

[00069] For example, Fig. 9 illustrates an inventive single-layer node-based data taxonomy structure 900 that may be employed for the Additive Manufacture (“AM”) management to manufacture an AM part as detailed below. For example, Fig. 9 illustrates four exemplary nodes 901-904 and their respective illustrative input and output structures. For example, the exemplary Node 3 (903), as illustrated by an“zoomed-in” diagram, may be defined as its own inventive workflow with a plurality of subnodes 905-908, forming the respective inventive single-layer hierarchy. In some embodiments, the subnode CAD (905) may be configured to include one or more embedded AM part build instructions that may utilize the Finite (Element) Analysis for determining the geometric information for the AM part to be built. For example, an input variable “Id CAD” may be used for inputting an inner diameter of an exemplary AM part to be designed by the subnode“CAD” (905). For example, an input variable“Od CAD” may be used for inputting an outer diameter and an input variable“t_CAD” may be used for inputting for thickness of the exemplary AM part to be designed by the subnode CAD (905). For example, the exemplary subnode 906 may be a generic measurement node, having input variables identified with an exemplary subscript“_meas.” For example, the exemplary subnode 907 may be representative of one or more software functions coded in the statistical computing environment R (C) (The R foundation, www.R-project.org). For example, the exemplary subnode 908 may be representative of one or more software functions coded in the MATLAB (R) (The MathWorks, Inc., Natick, MA) computing environment. For example, the exemplary subnodes 907 and 908 may compute the difference (e.g., input/output values identified with the subscript“ diff’) between the output value(s) of the subnode CAD (905) and the output measured values obtained by the subnode 906.

[00070] Illustrative use of the inventive workflow processing (e.g.. generation execution etc.) for an AM process

[00071] Additive Manufacturing

[00072] As used herein,“additive manufacturing” means“a process of joining materials to make objects from 3D model data, usually layer upon layer, as opposed to subtractive manufacturing methodologies”, as defined in ASTM F2792-l2a entitled“Standard Terminology for Additively Manufacturing Technologies”. The AM parts described herein may be manufactured via any appropriate additive manufacturing technique described in this ASTM standard, such as binder jetting, directed energy deposition, material extrusion, material jetting, powder bed fusion, or sheet lamination, among others. In one embodiment, an additive manufacturing process includes depositing successive layers of one or more materials (e.g., powders of materials) and then selectively melting and/or sintering the materials to create, layer- by-layer, an AM part/product. In one embodiment, an additive manufacturing processes uses one or more of Selective Laser Sintering (SLS), Selective Laser Melting (SLM), and Electron Beam Melting (EBM), among others. In one embodiment, an additive manufacturing process uses an EOSINT M 280 Direct Metal Laser Sintering (DMLS) additive manufacturing system, or comparable system, available from EOS GmbH (Robert-Stirling-Ring 1, 82152 Krailling/Munich, Germany). Additive manufacturing techniques (e.g. when utilizing metallic feedstocks) may facilitate the selective heating of materials above the liquidus temperature of the particular alloy, thereby forming a molten pool followed by rapid solidification of the molten pool. Non-limiting examples of additive manufacturing processes useful in producing AM products include, for instance, DMLS (direct metal laser sintering), SLM (selective laser melting), SLS (selective laser sintering), and EBM (electron beam melting), among others. Any suitable feedstocks may be used, including one or more materials, one or more wires, and combinations thereof. In various embodiments, AM is configurable to utilize various feedstocks - e.g. metallic feedstocks (e.g. with additives to promote various properties, e.g. grain refiners and/or ceramic materials), plastic feedstocks, and polymeric feedstocks (or reagent-based feedstock materials which form polymeric AM builds/ AM parts), to name a few. In some embodiments the additive manufacturing feedstock is comprised of one or more materials. Shavings are types of particles. In some embodiments, the additive manufacturing feedstock is comprised of one or more wires. A ribbon is a type of wire.

[00073] In one approach, the AM parts metal alloys described herein are in the form of an additive manufacturing feedstock.

[00074] As noted above, additive manufacturing may be used to create, layer-by-layer, an AM part/product. In one embodiment, a powder bed is used to create an AM part/product (e.g., a tailored alloy product and/or a unique structure unachievable through traditional manufacturing techniques (e.g. without excessive post-processing machining)).

[00075] In one approach, a method comprises (a) dispersing an AM feedstock (e.g. metal alloy powder in a bed), (b) selectively heating a portion of the material (e.g., via an energy source or laser) to a temperature above the liquidus temperature of the particular AM part/product to be formed, (c) forming a molten pool and (d) cooling the molten pool at a cooling rate of at least 1000 °C per second. In one embodiment, the cooling rate is at least 10,000 °C per second. In another embodiment, the cooling rate is at least 100,000 °C per second. In another embodiment, the cooling rate is at least 1,000,000 °C per second. Steps (a)-(d) may be repeated as necessary until the AM part/product is completed.

[00076] In another approach, a method comprises (a) dispersing a feedstock (e.g. AM material powder) in a bed, (b) selectively binder jetting the AM material powder, and (c) repeating steps (a)-(b), thereby producing a final additively manufactured product (e.g. including optionally heating to burn off binder and form a green form, followed by sintering to form the AM part).

[00077] In another approach, electron beam (EB) or plasma arc techniques are utilized to produce at least a portion of the AM part/product. Electron beam techniques may facilitate production of larger parts than readily produced via laser additive manufacturing techniques. An illustrative example provides feeding a to the wire feeder portion of an electron beam gun. The wire may comprise a metal feedstock (e.g. metal alloy including titanium, cobalt, iron, nickel, aluminum, or chromium alloys to name a few). The electron beam heats the wire or tube, as the case may be, above the liquidus point of the alloy to be formed, followed by rapid solidification of the molten pool to form the deposited material.

[00078] The alloy may be, for instance, an aluminum-based alloy, a titanium-based alloy (including titanium aluminides), a nickel-based alloy, an iron-based alloy (including steels), a cobalt-based alloy, or a chromium-based alloy, among others.

[00079] Any suitable alloy composition may be used with the techniques described above to produce AM part/product. Some non-limiting examples of alloys that may be utilized are described below. However, other alloys may also be used, including copper-based, zinc-based, silver-based, magnesium-based, tin-based, gold-based, platinum-based, molybdenum-based, tungsten-based, and zirconium-based alloys, among others.

[00080] As used herein,“aluminum alloy” means a metal alloy having aluminum as the predominant alloying element. Similar definitions apply to the other corresponding alloys referenced herein (e.g. titanium alloy means a titanium alloy having titanium as the predominant alloying element, and so on).

[00081] In some embodiments, the exemplary inventive processes of the present disclosure are directed towards applying database-driven recursive workflow generation systems and computer-implemented automatic recursive workflow generation methods for building AM parts/bodies. In some embodiments, the configuration management of the digital twin throughout its modification(s) may be assured via employing the exemplary taxonomy model. For example, an exemplary AM process may be a flow path of producing an AM part and a digital twin may be simulation model(s) representing the actual flow path. For example, in some embodiments, the AM process may include one or more steps detailed, without limitation, in U.S. Patent Pub. No. 2016/0224017 which is hereby incorporated herein by reference. For example, the AM process may be a process of joining materials to make objects from 3D model data, usually layer upon layer. In some embodiments, additive manufacturing includes building successive layers of an AM material (e.g., aluminium alloy powder) by depositing a feed stock powder of the AM material (e.g., metal powder) and then selectively melted and/or sintered (e.g. with a laser or other heat source) to create, layer-by-layer, an AM part (e.g., an aluminium alloy product, a titanium alloy product, a nickel alloy product). Additive build processes utilizing a powder feedstock that can employ one or more of the embodiments of the instant disclosure include: direct metal laser sintering (e.g. a powder bed fusion process used to make metal AM parts directly from metal powders without intermediate“green” or“brown” parts); directed energy deposition (e.g., an AM process in which focused thermal energy is used to fuse materials by melting as they are being deposited); powder bed fusion (e.g. an AM process in which thermal energy selectively fuses regions of a powder bed); or laser sintering (e.g., a powder bed fusion process used to produce objects from powdered materials using one or more lasers to selective fuse or melt the particles at the surface, layer by layer, in an enclosed chamber) to name a few. Some non-limiting examples of suitable additive manufacturing systems include the EOSINT M 280 Direct Metal Laser Sintering (DMLS) additive manufacturing system, available from EOS GmbH (Robert-Stirling- Ring 1, 82152 Krailling/Munich, Germany). Other suitable additive manufacturing systems include Selective Laser Sintering (SLS) systems, Selective Laser Melting (SLM) systems, and Electron Beam Melting (EBM) systems, among others.

[00082] Fig. 7 shows an illustrative example of an overall architecture 700 of various AM activities within an exemplary AM system 702 whose workflows may be generated by utilizing the exemplary inventive database-driven recursive workflow generation system. While some activities identified in Fig. 7 are detailed herein as occurring in sequential order, such description is done for purposes of convenience and should not be viewed as being limited since, as a skilled practitioner would readily recognize, at least some activities may occur concurrently, in reverse order, or not occur at al under certain condition(s).

[00083] Referring to item 704 of Fig. 7, in at least some embodiments, the exemplary inventive database-driven recursive workflow generation system may receive/obtain electronical data describing one or more AM parts to be manufactured (“part data”). In some embodiments, the exemplary inventive database-driven recursive workflow generation system may analyze the part data to determine one or more functions that are desired for each AM part to build respective node taxonomy. In some embodiments, when a AM part may be constructed from a plurality of sub-parts and/or when the AM part may be intended to be combined with at least one other part, which may or may not be manufactured utilizing an AM process, to perform its intended function, the exemplary inventive database-driven recursive workflow generation system may further determine one or more characteristics that may influence how the AM part would perform for its intended purpose(s) and create additional node structures to reflect those characteristics.

[00084] In some embodiments, any individual part manufactured via AM may be subject to one or more additional processes, such as machining for finishing purposes and/or forging for inducing desired microstructural properties. In some embodiments, at least one sub-part may not be manufactured via AM. In some embodiments, the exemplary inventive database-driven recursive workflow generation system may be configured to perform such analysis/determination as part of generating a workflow that may include software instructions and/or software model(s) that may direct how the AM part is created during the AM process. In some embodiments, the exemplary inventive database-driven recursive workflow generation system may be configured to perform the above analysis/determination as part of generating a workflow that may include a real- time feedback mechanism that may be configured to utilize the analysis/determination performed during the activity of item 704 to influence, in real time, how the AM process performs during one or more preceding and/or subsequent activities of the AM system of Fig. 7.

[00085] Referring to, for example, item 706 of Fig. 7, in at least some embodiments, based on the part data and additional data generated at preceding stage(s), the exemplary inventive database-driven recursive workflow generation system may generate at least one workflow that may analyze/determine how a proposed (initial) design of the AM part in the part data received/obtained by the AM system would be suitable/fit to perform its intended function(s). In some embodiments, the exemplary inventive database-driven recursive workflow generation system may generate at least one workflow that may be configured to be utilized to analyze/determine how the design of the AM part would influence the overall performance of the AM system. In some embodiments, a part of the activity of item 706, the exemplary inventive database-driven recursive workflow generation system may generate at least one workflow that may be configured to be utilized to dynamically alter the material composition of the initial design of the AM part to improve performance of the AM system during one or more subsequent activities without sacrificing and/or improving how the AM part would perform for its intended function(s). In some embodiments, the exemplary inventive database-driven recursive workflow generation system may generate at least one workflow that may be configured to be utilized to perform such analysis/determination as part of a real-time feedback mechanism that may be configured to utilize the analysis/determination during the activity of item 706 to influence, in real time, how the exemplary AM process performs during one or more preceding and/or subsequent activities of the AM system of Fig. 7.

[00086] Referring to item 708 of Fig. 7, in at least some embodiments, based on the part data and additional data generated at preceding stage(s), the exemplary inventive database-driven recursive workflow generation system may generate at least one workflow that may select at least one of: i) feedstock (e.g., usable material) processing paths, ii) material composition(s) from one or more pre-determined material compositions that would be sufficiently suitable to the intended function(s) of the AM part, and/or iii) AM processing path(s).

[00087] In some embodiments, the exemplary inventive database-driven recursive workflow generation system may generate at least one workflow that may be configured to be utilized to analyze how the material composition of the AM part would influence the overall performance of the AM system. For example, the exemplary inventive database-driven recursive workflow generation system may generate at least one workflow that may be configured to be utilized to analyze life expectancy, cost, weight, corrosion resistance, and other parameter(s) of AM part.

[00088] In some embodiments, a part of the activity of item 708, the exemplary inventive database-driven recursive workflow generation system may generate at least one workflow that may be configured to be utilized to select, from one or more pre-determined material compositions, an initial material composition of the AM part in the part data to improve performance of the AM system during one or more subsequent activities without sacrificing and/or improving how the AM part would perform for its intended function(s). In some embodiments, the exemplary inventive database-driven recursive workflow generation system may generate at least one workflow that may be configured to be utilized to perform such analysis/determination as part of a real-time feedback mechanism that may be configured to utilize the analysis/determination during the activity of item 108 to influence, in real time, how the AM process performs during one or more preceding and/or subsequent activities of the AM system of Fig. 7.

[00089] Referring to item 710 of Fig. 7, in at least some embodiments, based on the part data and additional data generated at preceding stage(s), the exemplary inventive database-driven recursive workflow generation system may generate at least one workflow that may run one or more part build simulations to analyze/test how, for example without limitation, one or more characteristics of the AM part would influence and/or be influenced by one or more subsequent activities of the AM system. In some embodiments, as a part of the activity 710, the generated workflow may be configured to dynamically alter, in real-time, the one or more part build simulation parameters based, at least in part, on one or more real-time characteristics of the AM system and/or one or more real-time internal and/or external conditions associated with the AM system (e.g., a temperature inside of an AM machine). In some embodiments, the exemplary inventive database-driven recursive workflow generation system may generate at least one workflow that may be configured to be utilized to perform such analysis/determination as part of a real-time feedback control mechanism that may be configured to utilize the one or more AM part build simulations developed during the activity of item 710 to influence, in real time, how the AM process performs during one or more preceding and/or subsequent activities of the AM system of Fig. 7. In some embodiments, the one or more AM part build simulations may be based, at least in part, on at least in part, any given simulation of any given part, may be influenced by and compared to simulation(s) of other sufficiently similar AM part(s).

[00090] In some embodiments, during the activity of item 710, the exemplary inventive database-driven recursive workflow generation system may generate at least one workflow that may be configured to be utilized to generate a dynamically adjustable digital representation (“digital twin”) 738 of the AM part that would be manufactured. In some embodiments, the digital twin 738 includes current and/or historical data related to function(s) of the AM part; the design of the AM part, and/or the material composition of the AM part (the part-centered data such as design data 728 and material data 730). In some embodiments, in addition to the part-centered data, the digital twin 738 may include AM process parameter(s) associated with the exemplary AM process to be employed to manufacture the AM part and/or code instructions that are configured to direct an exemplary AM machine to build the AM part (the build-centered data such as simulation data 732 and process data 734). In some embodiments, the build-centered data may include historical error data generated during the additive manufacturing of other similar AM part(s) (i.e., digital twin(s) of previously manufactured other similar AM part(s)). [00091] In some embodiments, in addition to the part-centered data and the build-centered data, the digital twin 738 may include certification requirement data (e.g., defect determination parameter(s)) that may be employed to certify that the AM part would be fit for its intended function(s) in connection with the in-situ monitoring (item 716) and post-build inspection (item 718) (the certification-centered data such as inspection data 736). In some embodiments, the digital twin 738 may be configured to be self-contained, self-adjustable, and/or self-executing computer entity that is agnostic to a type of an AM machine that may be employed to build the AM part.

[00092] Referring to item 712 of Fig. 7, in at least some embodiments, the exemplary inventive database-driven recursive workflow generation system may generate at least one workflow that may be configured to be utilized to utilize the digital twin to determine one or more settings for the exemplary AM machine for building the AM part (AM machine setting data). In some embodiments, the exemplary inventive database-driven recursive workflow generation system may generate at least one workflow that may be configured, during the activity of item 712 to incorporate the AM machine setting data into the digital twin 738. In some embodiments, the AM machine setting data may include data that cause the exemplary machine to calibrate itself in a particular way prior to building the AM part (AM machine calibration data). In some embodiments, as a part of the activity of item 712, the exemplary inventive computer-based AM system may be configured to utilize the monitoring data collected, in real-time, about the exemplary AM machine, while the exemplary AM machine builds other AM part(s), to dynamically adjust the AM machine setting data in the digital twin 738 of the AM part to account, without limitation, for machine-to-machine parameter variability. [00093] In some embodiments, the monitoring data may include at least one of: i) operational parameter(s) of the exemplary AM machine, ii) internal (in-situ) conditions of the exemplary AM machine (e.g., temperature within a build chamber, 02 concentration, etc.), which may be generated, for example without limitation, during activity of item 716, and/or iii) external conditions associated with the exemplary AM machine (e.g., environmental conditions (e.g., surrounding temperature, atmospheric pressure, humidity, etc.)).

[00094] Referring to item 714 of Fig. 7, the exemplary inventive database-driven recursive workflow generation system may generate at least one workflow that may be configured to be utilized to execute the digital twin 718 so that the AM machine may be instructed to build the AM part in accordance with the corresponding digital twin 718. For example, based on the digital twin 738, the AM machine may be instructed to deposit an initial layer of AM part based on an estimated build position, extract actual coordinates of the build layer, compare the coordinates of the initial build layer with the estimated coordinates sent to the AM machine, and determining a deviation, if any, between an ideal (estimated) build of the digital twin 738 and the actual build layer.

[00095] In some embodiments, as a part of activity of item 714, based on the digital twin 738, if particular point(s) in the build portion of the AM part is/are determined to deviate from a threshold condition to a tolerable degree (out-of-compliance-but-reparable condition), the exemplary inventive database-driven recursive workflow generation system may generate at least one workflow that may be configured to be utilized to mitigate such noncompliance by adjusting build instruction(s) for next build layer(s) and/or build portion(s) of the same layer in which the noncompliance has been determined. In some embodiments, the out-of-compliance-but-reparable condition may be a condition in which repair would not be needed. In one embodiment, the out- of-compliance-but-reparable condition may be a condition that would be within tolerances without need to repair. In one embodiment, the out-of-compliance-but-reparable condition may be a condition that would be outside of tolerances but still repairable.

[00096] In some embodiments, as a part of activity of item 714, based on the digital twin 738, if particular point(s) in the build portion of the AM part is/are determined to deviate from a threshold condition to a non-tolerable degree (unrepairable condition), the exemplary inventive database-driven recursive workflow generation system may generate at least one workflow that may be configured to be utilized to cause the exemplary AM machine to stop the build process. In such case, the defective intermediate may be discarded, avoiding deposition of additional layers which would save cost associated with material for those layers and the time to complete them.

[00097] In some embodiments, the exemplary inventive database-driven recursive workflow generation system may generate at least one workflow that may be configured to be utilized to execute an active feedback control mechanism (item 726 of Fig. 7) which may be triggered based, at least in part, on the in-situ monitoring data (item 716) whenever there is/are discrepancy(ies)/deviation(s) within at least one of: i) definitions determined during the material selection activity (item 708), with or without executing the iterative adjustment of build material selection (item 722 of Fig. 1); ii) definitions determined during the part build simulation activity (item 710), with or without the interposition of the optimization step 724); and/or iii) definitions determined during the AM machine’s set points determination (item 712).

[00098] In some embodiments, independently of the discrepancies identified during the material selection activity (item 708) (optionally influenced by item 722), during the part build simulation activity (item 710) (optionally influenced by item 724) and during the AM machine’s set points determination (item 712) being known or quantifiable, the inventive active feedback control mechanism (item 726) may be configured to either interrupt the build process of the AM part and/or re-run the iterative adjustments (items 722 and/or 724) to affect values of items 708, 710, and 712 of Fig. 7 until quality metrics identified in item 716 meet the specification. Consequently, in at least some embodiments, the in-situ monitoring (item 716) drives the inventive active feedback control mechanism (item 726) to dynamically specify machine set points that result in a successful completion of the build or in sufficiently earlier stop of the build process to minimize the waste of material and/or time. In some embodiments, the inventive active feedback control mechanism (item 726) may be configured as at least one of suitable control strategies such as, without limitation, classical Proportional-Integral-Derivative (PID) control, adaptive control, optimal control, and combinations thereof, etc.

[00099] Referring to item 718 of Fig. 7, in at least some embodiments, the exemplary inventive database-driven recursive workflow generation system may generate at least one workflow that may be configured to be utilized to generate and/or modify a final state of the digital twin 738 after the physical AM part (item 720: the physical twin) has passed the post-build inspection (item 718) so that the final state of the digital twin 738 is utilized to certify a subsequently built AM part as being fit for its intended function(s) (e.g., compliance with the certification requirements and other desired requirement(s)) without actual/physical evaluation of the subsequent AM part itself. In some embodiments, the post-build inspection (item 718) may include non-destructive testing, destructive testing (completed on parts), or both.

[000100] Referring to at least activities of items 714 and 716 of Fig. 7, the exemplary inventive database-driven recursive workflow generation system may generate at least one workflow that may be configured to be utilized to be utilized to dynamically adjust, in real-time, the digital twin 738 and/or the AM build process based, at least in part, on and may include at least one of: i) the part design data (item 728 of Fig. 7), ii) the material composition data (item 730 of Fig. 7), iii) the part-build simulation data (item 732 of Fig. 7), iv) the AM process data (item 734 of Fig. 7), and/or v) the inspection/certification data (item 736 of Fig. 7).

[000101] In some embodiment, the AM process data may be the process data collected during the production and/or certification of similar AM part(s), which may be then used to complete one or more of i) the part design data 728, ii) the material composition data 730, and/or iii) the part- build simulation data 732. In some embodiment, the inspection/certification data 736 is used to adjust one or more of i) the part design data 728, ii) the material composition data 730, and/or iii) the part-build simulation data 732.

[000102] In some embodiment, the digital twin 738 may be stored according to a predetermined data model and/or schema and include, for example without limitation, data items 728-736. In some embodiment, the digital twin 738 may include data that describes the machine setup changes resulting from the inventive active feedback control mechanism (item 726). In some embodiments, the digital twin 738 of AM process parts may be configured to be processed by applying at least one of suitable analytical techniques such as, without limitation, machine learning algorithms, neural networks, and/or predictive modelling techniques.

[000103] Production and Processing

[000104] In some embodiments, the AM part/product may be subject to any appropriate dissolving (e.g. includes homogenization), working and/or precipitation hardening steps. If employed, the dissolving and/or the working steps may be conducted on an intermediate form of the additively manufactured body and/or may be conducted on a final form of the additively manufactured body. If employed, the precipitation hardening step is generally conducted relative to the final form of the AM part/product. [000105] After or during production, an AM part/product may be deformed (e.g., by one or more of rolling, extruding, forging, stretching, compressing). The final deformed product may realize, for instance, improved properties due to the tailored regions and thermo-mechanical processing of the final deformed AM part/product. Thus, in some embodiments, the final product is a wrought AM part/product, the word“wrought” referring to the working (hot working and/or cold working) of the AM part/product, wherein the working occurs relative to an intermediate and/or final form of the AM part/product. In other approaches, the final product is a non-wrought product, i.e., is not worked during or after the additive manufacturing process. In these non- wrought product embodiments, any appropriate number of dissolving and precipitating steps may still be utilized.

[000106] Product Applications

[000107] The resulting AM part/products made in accordance with the systems and methods described herein may be used in a variety of product applications. In one embodiment, the AM parts (e.g. metal alloy parts) are utilized in an elevated temperature application, such as in an aerospace or automotive vehicle. In one embodiment, an AM part or product is utilized as an engine component in an aerospace vehicle (e.g., in the form of a blade, such as a compressor blade incorporated into the engine). In another embodiment, the AM part or product is used as a heat exchanger for the engine of the aerospace vehicle. The aerospace vehicle including the engine component / heat exchanger may subsequently be operated. In one embodiment, the AM part or product is an automotive engine component. The automotive vehicle including an automotive component (e.g. engine component) may subsequently be operated. For instance, the AM part or product may be used as a turbo charger component (e.g., a compressor wheel of a turbo charger, where elevated temperatures may be realized due to recycling engine exhaust back through the turbo charger), and the automotive vehicle including the turbo charger component may be operated. In another embodiment, an AM part or product may be used as a blade in a land based (stationary) turbine for electrical power generation, and the land-based turbine included the AM part or product may be operated to facilitate electrical power generation. In some embodiments, the AM part or products are utilized in defense applications, such as in body armor, and armed vehicles (e.g., armor plating). In other embodiments, the AM part or products are utilized in consumer electronic applications, such as in consumer electronics, such as, laptop computer cases, battery cases, cell phones, cameras, mobile music players, handheld devices, computers, televisions, microwaves, cookware, washers/dryers, refrigerators, and sporting goods, among others.

[000108] In another aspect, the AM part or products are utilized in a structural application. In one embodiment, the AM part or products are utilized in an aerospace structural application. For instance, the AM part or products may be formed into various aerospace structural components, including floor beams, seat rails, fuselage framing, bulkheads, spars, ribs, longerons, and brackets, among others. In another embodiment, the AM part or products are utilized in an automotive structural application. For instance, the AM part or AM part or products may be formed into various automotive structural components including nodes of space frames, shock towers, and subframes, among others. In one embodiment, the AM part or product is a body-in white (BIW) automotive product.

[000109] In another aspect, the AM part or products are utilized in an industrial engineering application. For instance, the AM part or products may be formed into various industrial engineering products, such as tread-plate, tool boxes, bolting decks, bridge decks, and ramps, among others. [000110] Fig. 8 shows an illustrative example of an overview of a distributed computer network system 800 including an exemplary inventive database-driven recursive workflow generation system that may generate at least one workflow that may be configured to be utilized to control an operation of an exemplary computer-based AM system in accordance with at least some embodiments and principles of the present disclosure detailed herein. In some embodiments, the exemplary AM system may include several different entities, such as an AM operator’s terminal 808 and customers 804 that are operatively communicable via a shared communication network 806, such that data, such as the AM digital twin files, may be transferred between any one of the aforementioned connected entities 802 and 804. In some embodiments, the customer logical environment 804 may include an authentication server that may be arranged to authenticate if a customer entity is authorized to access a relevant data file, such as a particular AM digital twin. In some embodiments, the shared communication network 806 may relate to the Internet, a LAN, a WAN, or any other suitable computer network. In some embodiments, the AM process logic environment 802 may effectively be a print farm, comprising one or more different operatively connected AM Machines/3D printers 810. Accordingly, the terms“AM machines” and“3D print farm” may be used interchangeably to refer to the same physical entity(ies) in the ensuing description, and the term“3D print farm” is analogous to the term“3D printing bureau.”

[000111] The customer environment 804 may include a server 818 operatively connected to the communication network 806, enabling direct data connections and communication with the attached terminal 808 and the 3D print farm 802. In addition, the server 818 may host a website through which a user using any one of the different operatively connected terminals 802 and 808, may interact with the customer environment 804 using standard web browsers. [000112] In some embodiments, the server 818 may be operatively connected to a database 820, which may be stored in a storage device local to the server 818, or in an external storage unit (not shown). In some embodiments, the exemplary AM system may be configured so that the customer environment 804 provides several different functions. For example, the exemplary inventive database-driven recursive workflow generation system that may generate at least one workflow that may be configured to be utilized to require a registration capability in order for each operatively connected entity to be uniquely identifiable by the customer environment 804, to thereby enable the customer environment 804 to manage access rights to encrypted content such as AM digital twin files, AM parameter settings, and other content. Such content may also relate to CAD software made available by a software developer who can be the AM operator.

[000113] In some embodiments, the exemplary inventive automatic recursive workflow generation system may generate at least one workflow that may be configured to be utilized to control the access to information included in an exemplary AM digital twin file via the customer environment 804, using a combination of unique identifier(s) and data encryption. By unique identifiers is intended any electronically verifiable identifier. For example, the unique identifier associated with a 3D printer may relate to the printer's serial number. The database 820 maintains a record of parties registered to use the 3D printers (AM machines). Such parties may include, but are not limited to registered AM operators 808. This information may be stored as one or more records and/or tables within the database 820.

[000114] In some embodiments, the exemplary inventive database-driven recursive workflow generation system that may generate at least one workflow that may be configured to be utilized to require a registration capability in order for each operatively connected entity to be uniquely identifiable in the customer environment 804, to thereby enable the customer environment 804 to manage access rights to encrypted content. For example, to manage access rights to the encrypted content of exemplary AM digital twin files.

[000115] In some embodiments, the exemplary AM system may be configured so that the exemplary 3D print farm 802 may include a server 812, which is operatively connected to the shared communication network 806. The server 812 may itself be operatively connected to one or more different AM machines/3D printers 810. In some embodiments, the function of the server 812 is to execute one or more activities identified in Fig. 7 such as dynamically instructing an appropriate AM machine 810 to AM produce an exemplary AM part based on exemplary AM digital twin.

[000116] Aspects of the invention have been described with reference to the following numbered clauses.

[000117] 1. A method, comprising:

providing, by a computer, a taxonomy library of candidate node structures to at least one user;

wherein each respective candidate node structure represents each respective workflow activity and comprises:

i) at least one node-definition element, identifying the at least one respective workflow activity associated with each respective candidate node, ii) at least one node-function element, identifying at least one respective software function to be executed in performing the at least one respective workflow activity, iii) at least one node-input parameter, identifying at least one input parameter that the at least one respective computer function requires to receive to perform the at least one respective workflow activity, and iv) at least one node-output parameter, identifying at least one output parameter that the at least one respective computer function outputs after performing the at least one respective workflow activity;

receiving, by the computer, from the at least one user, a respective workflow design data that defines a respective workflow taxonomy for a respective manufacturing process;

wherein the workflow design data comprises:

i) a node selection, identifying a plurality of selected node structures from the taxonomy library of candidate node structures, and

ii) a node sequence, identifying a sequence in which the plurality of selected node structures to be executed;

generating, by the computer, a respective workflow data object for the respective manufacturing process based at least in part on the respective workflow taxonomy; and

causing, by the computer, a performance of the respective manufacturing process in accordance with the respective workflow data object.

[000118] 2. The method of Claim 1, wherein the at least one respective workflow activity is associated with at least one machinery utilized by a respective manufacturing process.

[000119] 3. The method of Claim 1, further comprising:

receiving, by the computer, a pre-defmed node structure data for a plurality of manufacturing processes, manufacturing machinery, or both;

wherein the pre-defmed node structure data defines each of:

i) the at least one node-definition element,

ii) the at least one node-function element,

iii) the at least one node-input parameter, and iv) at least one node-output parameter; and

populating, by the computer, the taxonomy library of candidate node structures based at least in part on the pre-defmed node structure data.

[000120] 4. The method of Claim 1,

wherein the respective workflow data object is a computer simulation of the respective manufacturing process.

[000121] 5. The method of Claim 1, wherein the respective workflow data object comprises a graphical interface configured to display the performance of the respective manufacturing process in accordance with the respective workflow data object.

[000122] 6. The method of Claim 4, wherein the respective workflow data object comprises a graphical interface configured to display the computer simulation of the performance of the respective manufacturing process in accordance with the respective workflow data object.

[000123] 7. The method of Claim 1, wherein the receiving, from the at least one user, the respective workflow design data for the respective workflow taxonomy for the respective manufacturing process, comprising:

receiving, by the computer, via a workflow design graphical user interface, the respective workflow design data.

[000124] 8. The method of Claim 1, wherein the receiving, from the at least one user, the respective workflow design data for the respective workflow taxonomy for the respective manufacturing process, comprising:

receiving, by the computer, via at least one verbal instruction, the respective workflow design data. [000125] 9. The method of Claim 8, wherein the receiving, via the at least one verbal instruction, the respective workflow design data, comprising:

generating, by at least one sound processing device, the respective workflow design data based at least in part on the at least one verbal instruction; and

wherein the at least one sound processing device comprises at least one of:

i) a speech decoder,

ii) a Natural Language Understanding software engine, or

iii) a Natural Language Generation software engine.

[000126] 10. The method of Claim 3, wherein the receiving the pre-defmed node structure data, comprising:

receiving, by at least one sound processing device, at least one verbal instruction;

generating, by the at least one sound processing device, the pre-defmed node structure data based at least in part on the at least one verbal instruction; and

wherein the at least one sound processing device comprises at least one of:

i) a speech decoder,

ii) a Natural Language Understanding software engine, or

iii) a Natural Language Generation software engine.

[000127] 11. The method of Claim 1, wherein the respective manufacturing process is an

Additive Manufacture (AM) build process of building an AM part by an AM machine.

[000128] 12. The method of Claim 1, wherein the respective workflow taxonomy is a nested workflow taxonomy.

[000129] 13. A system, comprising:

at least one processor; and a non-transitory computer readable storage medium storing thereon program logic, wherein, when executing the program logic, the at least one processor is configured to:

provide a taxonomy library of candidate node structures to at least one user;

i) at least one node-definition element, identifying the at least one respective workflow activity associated with each respective candidate node, ii) at least one node-function element, identifying at least one respective software function to be executed in performing the at least one respective workflow activity, iii) at least one node-input parameter, identifying at least one input parameter that the at least one respective computer function requires to receive to perform the at least one respective workflow activity, and

iv) at least one node-output parameter, identifying at least one output parameter that the at least one respective computer function outputs after performing the at least one respective workflow activity;

receive, from the at least one user, a respective workflow design data that defines a respective workflow taxonomy for a respective manufacturing process;

wherein the workflow design data comprises:

ii) a node sequence, identifying a sequence in which the plurality of selected node structures to be executed; generate a respective workflow data object for the respective manufacturing process based at least in part on the respective workflow taxonomy; and

cause a performance of the respective manufacturing process in accordance with the respective workflow data object.

[000130] 14. The system of Claim 13, wherein the at least one respective workflow activity is associated with at least one machinery utilized by a respective manufacturing process.

[000131] 15. The system of Claim 13, wherein the at least one processor is further configured to:

receive a pre-defmed node structure data for a plurality of manufacturing processes, manufacturing machinery, or both;

wherein the pre-defmed node structure data defines each of:

i) the at least one node-definition element,

ii) the at least one node-function element,

iii) the at least one node-input parameter, and

iv) at least one node-output parameter; and

populate the taxonomy library of candidate node structures based at least in part on the pre- defmed node structure data.

[000132] 16. The system of Claim 13,

[000133] 17. The system of Claim 13, wherein the respective workflow data object comprises a graphical interface configured to display the performance of the respective manufacturing process in accordance with the respective workflow data object. [000134] 18. The system of Claim 16, wherein the respective workflow data object comprises a graphical interface configured to display the computer simulation of the performance of the respective manufacturing process in accordance with the respective workflow data object.

[000135] 19. The system of Claim 13, wherein the at least one processor is further configured to:

[000136] receive, via a workflow design graphical user interface, the respective workflow design data.

[000137] 20. The system of Claim 13, wherein the at least one processor is further configured to:

[000138] receive, via at least one verbal instruction, the respective workflow design data.

[000139] 21. The system of Claim 20, further comprising:

at least one sound processing device, configured to generate the respective workflow design data based at least in part on the at least one verbal instruction; and

wherein the at least one sound processing device comprises at least one of:

i) a speech decoder,

ii) a Natural Language Understanding software engine, or

iii) a Natural Language Generation software engine.

[000140] 22. The system of Claim 15, further comprising:

at least one sound processing device, configured to:

receive at least one verbal instruction;

generated the pre-defmed node structure data based at least in part on the at least one verbal instruction; and wherein the at least one sound processing device comprises at least one of:

i) a speech decoder,

ii) a Natural Language Understanding software engine, or iii) a Natural Language Generation software engine.

[000141] 23. The system of Claim 13, wherein the respective manufacturing process is an Additive Manufacture (AM) build process of building an AM part by an AM machine.

[000142] 24. The system of Claim 13, wherein the respective workflow taxonomy is a nested workflow taxonomy.

[000143] All examples and conditional language recited herein are intended for pedagogical purposes to aid the reader in understanding the principles of the invention and the concepts contributed by the inventor to furthering the art, and are to be construed as being without limitation to such specifically recited examples and conditions. Moreover, all statements herein reciting principles, aspects, and embodiments of the invention, as well as specific examples thereof, are intended to encompass both structural and functional equivalents thereof. Additionally, it is intended that such equivalents include both currently known equivalents as well as equivalents developed in the future, i.e., any elements developed that perform the same.

Claims

CLAIMS: What is claimed is

1. A method, comprising:

wherein the workflow design data comprises:

i) a node selection, identifying a plurality of selected node structures from the taxonomy library of candidate node structures, and ii) a node sequence, identifying a sequence in which the plurality of selected node structures to be executed;

2. The method of Claim 1, wherein the at least one respective workflow activity is associated with at least one machinery utilized by a respective manufacturing process.

3. The method of Claim 1, further comprising:

wherein the pre-defmed node structure data defines each of:

i) the at least one node-definition element,

ii) the at least one node-function element,

iii) the at least one node-input parameter, and

iv) at least one node-output parameter; and

4. The method of Claim 1,

5. The method of Claim 1 , wherein the respective workflow data obj ect comprises a graphical interface configured to display the performance of the respective manufacturing process in accordance with the respective workflow data object.

6. The method of Claim 4, wherein the respective workflow data obj ect comprises a graphical interface configured to display the computer simulation of the performance of the respective manufacturing process in accordance with the respective workflow data object.

7. The method of Claim 1, wherein the receiving, from the at least one user, the respective workflow design data for the respective workflow taxonomy for the respective manufacturing process, comprising:

8. The method of Claim 1, wherein the receiving, from the at least one user, the respective workflow design data for the respective workflow taxonomy for the respective manufacturing process, comprising:

receiving, by the computer, via at least one verbal instruction, the respective workflow design data.

9. The method of Claim 8, wherein the receiving, via the at least one verbal instruction, the respective workflow design data, comprising:

wherein the at least one sound processing device comprises at least one of:

i) a speech decoder,

10. The method of Claim 3, wherein the receiving the pre-defmed node structure data, comprising:

wherein the at least one sound processing device comprises at least one of:

i) a speech decoder,

ii) a Natural Language Understanding software engine, or

iii) a Natural Language Generation software engine.

11. The method of Claim 1, wherein the respective manufacturing process is an Additive Manufacture (AM) build process of building an AM part by an AM machine.

12. The method of Claim 1, wherein the respective workflow taxonomy is a nested workflow taxonomy.

13. A system, comprising:

at least one processor; and

a non-transitory computer readable storage medium storing thereon program logic, wherein, when executing the program logic, the at least one processor is configured to:

provide a taxonomy library of candidate node structures to at least one user;

wherein the workflow design data comprises:

generate a respective workflow data object for the respective manufacturing process based at least in part on the respective workflow taxonomy; and

14. The system of Claim 13, wherein the at least one respective workflow activity is associated with at least one machinery utilized by a respective manufacturing process.

15. The system of Claim 13, wherein the at least one processor is further configured to: receive a pre-defmed node structure data for a plurality of manufacturing processes, manufacturing machinery, or both;

wherein the pre-defmed node structure data defines each of:

i) the at least one node-definition element,

ii) the at least one node-function element,

iii) the at least one node-input parameter, and

iv) at least one node-output parameter; and

16. The system of Claim 13,

17. The system of Claim 13, wherein the respective workflow data object comprises a graphical interface configured to display the performance of the respective manufacturing process in accordance with the respective workflow data object.

18. The system of Claim 16, wherein the respective workflow data object comprises a graphical interface configured to display the computer simulation of the performance of the respective manufacturing process in accordance with the respective workflow data object.

19. The system of Claim 13, wherein the at least one processor is further configured to:

receive, via a workflow design graphical user interface, the respective workflow design data.

20. The system of Claim 13, wherein the at least one processor is further configured to:

receive, via at least one verbal instruction, the respective workflow design data.

21. The system of Claim 20, further comprising:

wherein the at least one sound processing device comprises at least one of:

i) a speech decoder,

ii) a Natural Language Understanding software engine, or

iii) a Natural Language Generation software engine.

22. The system of Claim 15, further comprising:

at least one sound processing device, configured to:

receive at least one verbal instruction;

generated the pre-defmed node structure data based at least in part on the at least one verbal instruction; and

wherein the at least one sound processing device comprises at least one of:

i) a speech decoder,

23. The system of Claim 13, wherein the respective manufacturing process is an Additive Manufacture (AM) build process of building an AM part by an AM machine.

24. The system of Claim 13, wherein the respective workflow taxonomy is a nested workflow taxonomy.