Digital Twin Dynamics Model Evaluation Method and System for Intelligent Manufacturing

Abstract

Digital twin dynamics model evaluation method and system for intelligent manufacturing, including: obtaining n indicators for digital twin dynamics model evaluation, and determining the weight of the first-level evaluation indicators for digital twin dynamics model evaluation; the n evaluation indicators correspond to n evaluations, each evaluation is divided into multiple secondary evaluation indicators, and the weight of the secondary indicators for each model evaluation is obtained according to the secondary evaluation indicators; the indicator evaluation scale is calculated based on all the secondary evaluation indicators, the secondary score is calculated in combination with the weight of the secondary indicators, and the score of each model evaluation is obtained; the comprehensive score is obtained by comprehensively scoring according to the scores of each module evaluation. The technical system architecture and relevant specification standards adopted by the present invention are comprehensively evaluated to improve the accuracy and reliability of constructing the digital twin dynamics model, and ensure the reuse and sharing of the model.

Description

Technical Field

[0001] The present invention belongs to the technical field of digital twin model evaluation, and particularly relates to a digital twin dynamics model evaluation method and system for intelligent manufacturing. Background Art

[0002] With the rapid development of intelligent manufacturing technology, the importance of digital twin technology in practical applications has become increasingly prominent. However, existing digital twin dynamics model evaluation methods are often limited to specific fields or single data types, and do not fully consider the comprehensive impact of different data sources, thus limiting their accuracy and reliability in practical applications. In the process of modeling and simulation of digital twin systems, there are various problems and uncertainties. For example, there may be errors in the parameter estimation and calibration process of the model, the construction and connection of the model may be different from the actual system, the input data of the model may be missing, and the accuracy of the model parameters may not be fine enough. The non-standardization and non-uniformity of these problems and uncertainties will affect the accuracy and reliability of the model, thus affecting the application effect of the digital twin system. To solve these problems and uncertainties, it is necessary to develop more comprehensive and integrated evaluation methods to evaluate the credibility of digital twin dynamics models.

[0003] Insufficient credibility: There is a lack of a comprehensive credibility evaluation method to ensure that the digital twin system can accurately reflect the physical system. The prior art proposes a digital twin device, a model evaluation system, and a model operation method including a data model interaction module, a model update module, and a resource call module, which can realize the establishment of physical attributes such as the digital twin model level and function, enabling communication equipment manufacturers to conduct simulation modeling of physical entity equipment while researching and developing physical entity equipment, guiding and verifying the research and development of physical entity equipment, but does not clearly propose how to conduct model evaluation, does not deeply study the evaluation rules of the model, and does not fully consider the comprehensive impact of different aspects, thus limiting its accuracy and reliability in practical applications. Summary of the Invention

[0004] The purpose of the present invention is to provide a digital twin dynamics model evaluation method and system for intelligent manufacturing to solve the problem that the comprehensive impact of different aspects is not fully considered, thus limiting its accuracy and reliability in practical applications.

[0005] To achieve the above purpose, the present invention adopts the following technical solutions:

[0006] In the first aspect, the present invention provides a digital twin dynamics model evaluation method for intelligent manufacturing, including:

[0007] Obtain n kinds of indicators for digital twin dynamics model evaluation, and determine the weight of the first-level evaluation indicators for digital twin dynamics model evaluation;

[0008] There are n evaluation indicators corresponding to n evaluations. Each evaluation is divided into multiple secondary evaluation indicators, and the weights of the secondary indicators for each model evaluation are obtained according to the secondary evaluation indicators.

[0009] The evaluation scale of the indicators is calculated based on all the secondary evaluation indicators, and the secondary scores are calculated by combining the weights of the secondary indicators to obtain the scores of each model evaluation.

[0010] The comprehensive score is obtained by comprehensively evaluating the scores of each module evaluation.

[0011] Optionally, obtain n indicators for evaluating the digital twin dynamics model:

[0012] The n indicators for evaluating the digital twin dynamics model include: evaluation rules for the basic characteristics of the dynamics model, evaluation rules for the preprocessing process, evaluation rules for the construction and connection of the rigid-flexible coupled multi-body model, evaluation rules for model-driven setting and result output, and evaluation rules for multi-body model verification.

[0013] Optionally, determine the weights of the first-level evaluation indicators for the digital twin dynamics model evaluation:

[0014] F = 0.2Abcd + 0.2Prcp + 0.2Mrcc + 0.2Mdro + 0.2Mbtv

[0015] Evaluation rules for the basic characteristics of the dynamics model Abcd; evaluation rules for the preprocessing process Prcp; evaluation rules for the construction and connection of the rigid-flexible coupled multi-body model Mrcc; evaluation rules for model-driven setting and result output Mdro; evaluation rules for multi-body model verification Mbtv.

[0016] Optionally, divide each evaluation into multiple secondary evaluation indicators:

[0017] The evaluation rules for the basic characteristics of the dynamics model are divided into: accuracy, precision, model complexity, and parameter sensitivity;

[0018] The evaluation rules for the preprocessing process are divided into: evaluation rules for STEP format components and evaluation rules for XML description files;

[0019] The evaluation rules for the construction and connection of the rigid-flexible coupled multi-body model are divided into: construction of rigid body models, construction of flexible body models, and rigid-flexible coupling connection;

[0020] The evaluation rules for model-driven setting and result output are divided into: setting accuracy, model credibility, result accuracy, and result interpretability;

[0021] The evaluation rules for multi-body model verification are divided into: geometric verification, dynamic verification, control system verification, experimental data comparison, and verification report.

[0022] Optionally, obtain the secondary index weights for each model evaluation according to the secondary evaluation indicators:

[0023] Abcd = 0.338Accy + 0.288Prec + 0.205Cmpl + 0.169Psns

[0024] Prcp = 0.5Step + 0.5Xml

[0025] Mrcc = 0.25Rbdm + 0.25Sfdm + 0.5Ccjc

[0026] Mdro = 0.239Seta + 0.254Mdlc + 0.295Accu + 0.212Expl

[0027] Mbtv = 0.166Geov + 0.228Dynv + 0.233Ctsv + 0.146Exdc + 0.226Vrep。

[0028] Optionally, the evaluation rules for STEP format components and the evaluation rules for XML description files:

[0029] Create a STEP file, organize the relevant information of the components into the STEP file. In the STEP file, define appropriate entities and attributes according to the STEP standard, and use standard naming regulations for each entity and attribute; in the STEP file, use appropriate structures and relationships to describe the organization and hierarchical relationships between components, including assembly relationships, connection relationships, and constraint conditions, reflecting the interactions between components in the actual system;

[0030] In the construction of the dynamic model, define an XML schema or use an existing general schema; according to the selected XML schema, construct a model description file, which includes the components, parameters, initial conditions, and boundary conditions of the model; describe the structure and characteristics of the model by organizing and naming XML elements and attributes; use XML elements and attributes to describe the components of the model; use XML elements and attributes to represent the equations and algorithms of the dynamic model; define the parameters and initial conditions in the model through XML elements and attributes, including physical parameters, material properties, initial positions, and velocities; use XML elements and attributes to describe the boundary conditions and external inputs, including applied forces, control signals, and environmental conditions; according to the complexity and hierarchical structure of the model, organize the structure and hierarchy of the XML description file, and use the nesting and reference mechanisms of XML to establish the hierarchical relationships and modularity of the model; use an XML validator and parser to validate and parse the model description file and convert it into a data structure available for model construction and simulation.

[0031] In a second aspect, the present invention provides a digital twin dynamics model evaluation system for intelligent manufacturing, including:

[0032] A data acquisition module, configured to acquire n indicators for evaluating a digital twin dynamics model and determine the weights of the first-level evaluation indicators for evaluating the digital twin dynamics model;

[0033] A secondary indicator weight acquisition module, configured to perform n evaluations corresponding to the n evaluation indicators, divide each evaluation into multiple secondary evaluation indicators, and obtain the weights of the secondary indicators for each model evaluation according to the secondary evaluation indicators;

[0034] A score acquisition module for model evaluation, configured to calculate an indicator evaluation scale according to all secondary evaluation indicators, calculate a secondary score in combination with the weights of the secondary indicators, and obtain the score of each model evaluation;

[0035] An evaluation output module, configured to perform a comprehensive evaluation based on the scores of each model evaluation to obtain a comprehensive evaluation score.

[0036] In a third aspect, the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the digital twin dynamics model evaluation method for intelligent manufacturing are implemented.

[0037] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the digital twin dynamics model evaluation method for intelligent manufacturing are implemented.

[0038] Compared with the prior art, the present invention has the following technical effects:

[0039] The present invention proposes a digital twin dynamics model evaluation method for intelligent manufacturing, which comprehensively judges aspects such as the processes and technical implementations adopted in modeling; comprehensively evaluates the technical system architecture and relevant specification standards adopted, improves the accuracy and reliability of constructing the digital twin dynamics model, and ensures the reuse and sharing of the model.

[0040] A multi-angle specific evaluation method. The present invention analyzes and evaluates based on the reliability of the digital twin dynamics model, considers the influence degree of different factors on the digital twin dynamics model, and uses the analytic hierarchy process for layer-by-layer analysis and evaluation, and performs weighted processing on each factor according to its importance to obtain a comprehensive score, which more completely and effectively reflects the credibility degree of the digital twin dynamics model.

[0041] Provide a relatively accurate judgment basis based on virtual model construction. Existing evaluation methods for digital twin dynamics models often lack comprehensive consideration and fail to fully take into account the impacts of different aspects on the construction of digital twin dynamics models. The non-standard and non-uniform construction processes may lead to errors and deviations in the models, thus limiting their accuracy and reliability in practical applications. The present invention proposes a digital twin dynamics model evaluation method for intelligent manufacturing, which comprehensively judges aspects such as the processes adopted in modeling and technical implementation; comprehensively evaluates the technical system architecture and relevant specification standards adopted, improves the accuracy and reliability of constructing digital twin dynamics models, and ensures the reuse and sharing of the models.

[0042] Specify the evaluation object and evaluation method. Starting from the process of constructing digital twin dynamics, the present invention divides the evaluation of digital twin dynamics models into five parts: evaluation of the basic characteristics of the dynamics model, evaluation of the preprocessing process, evaluation of the construction and connection of the rigid-flexible coupled multi-body model, evaluation of model-driven setting and result output, and evaluation of multi-body model verification. Based on these five parts, 58 evaluation objects and 58 evaluation methods are refined, covering various judgment criteria such as the standard usage methods of components, material properties, and written documents, and are more comprehensive in judging whether the virtual model is standard. Compared with existing patents, this patent has more comprehensive advantages. Description of the Drawings

[0043] Figure 1 This is the flowchart of the present invention.

[0044] Figure 2 This is the logic block diagram of the present invention.

[0045] Figure 3 This is the diagram of the division of secondary indicators of the present invention. Detailed Embodiment

[0046] The present invention is further described below with reference to the drawings:

[0047] Please refer to Figures 1 to 3 , the digital twin dynamics model evaluation method for intelligent manufacturing, includes:

[0048] Obtain n indicators for evaluating the digital twin dynamics model, and determine the weight of the first-level evaluation indicators for evaluating the digital twin dynamics model;

[0049] The n evaluation indicators correspond to n evaluations. Each evaluation is divided into multiple secondary evaluation indicators, and the weight of the secondary indicators for each model evaluation is obtained according to the secondary evaluation indicators;

[0050] Calculate the indicator evaluation scale according to all secondary evaluation indicators, and calculate the secondary score in combination with the weight of the secondary indicators to obtain the score of each model evaluation;

[0051] The comprehensive score is obtained by comprehensively scoring according to the scores evaluated for each module.

[0052] Specifically:

[0053] Method for determining primary indicators

[0054] The n indicators for evaluating the digital twin dynamics model include: evaluation rules for the basic characteristics of the dynamics model, evaluation rules for the preprocessing process, evaluation rules for the construction and connection of the rigid-flexible coupled multi-body model, evaluation rules for model-driven setting and result output, and evaluation rules for multi-body model verification.

[0055] Determine the weights of the primary evaluation indicators for evaluating the digital twin dynamics model:

[0056] F = 0.2Abcd + 0.2Prcp + 0.2Mrcc + 0.2Mdro + 0.2Mbtv

[0057] Evaluation rules for the basic characteristics of the dynamics model Abcd; evaluation rules for the preprocessing process Prcp; evaluation rules for the construction and connection of the rigid-flexible coupled multi-body model Mrcc; evaluation rules for model-driven setting and result output Mdro; evaluation rules for multi-body model verification Mbtv.

[0058] Secondary evaluation indicators

[0059] The evaluation rules for the basic characteristics of the dynamics model Abcd are divided into: accuracy Accy, precision Prec, model complexity Cmpl, and parameter sensitivity Psns;

[0060] The evaluation rules for the preprocessing process Prcp are divided into: evaluation rules for STEP format components Step and evaluation rules for XML description files Xml;

[0061] The evaluation rules for the construction and connection of the rigid-flexible coupled multi-body model Mrcc are divided into: rigid body model construction Rbdm, flexible body model construction Sfdm, rigid-flexible coupling connection Ccjc;

[0062] The evaluation rules for model-driven setting and result output Mdro are divided into: setting accuracy Seta, model credibility Mdlc, result accuracy Accu, result interpretability Expl;

[0063] The evaluation rules for multi-body model verification Mbtv are divided into: geometric verification Geov, dynamic verification Dynv, control system verification Ctsv, experimental data comparison Exdc, verification report Vrep.

[0064] Obtain the weights of the secondary indicators for evaluating each model according to the secondary evaluation indicators:

[0065] Abcd = 0.338Accy + 0.288Prec + 0.205Cmpl + 0.169Psns

[0066] Prcp = 0.5Step + 0.5Xml

[0067] Mrcc = 0.25Rbdm + 0.25Sfdm + 0.5Ccjc

[0068] Mdro = 0.239Seta + 0.254Mdlc + 0.295Accu + 0.212Expl

[0069] Mbtv = 0.166Geov + 0.228Dynv + 0.233Ctsv + 0.146Exdc + 0.226Vrep

[0070] 1. Accuracy Accy, Precision Prec, Model Complexity Cmpl, and Parameter Sensitivity Psns;

[0071]

[0072] Abcd = 0.338Accy + 0.288Prec + 0.205Cmpl + 0.169Psns

[0073] 2. Evaluation Rules for STEP - format Parts Step and Evaluation Rules for XML Description Files Xml;

[0074]

[0075] Prcp = 0.5Step + 0.5Xml

[0076] 3. Rigid - body Model Construction Rbdm, Flexible - body Model Construction Sfdm, Rigid - Flexible Coupling Connection Ccjc;

[0077]

[0078]

[0079] Mrcc = 0.25Rbdm + 0.25Sfdm + 0.5Ccjc

[0080] 4. Setting Accuracy Seta, Model Credibility Mdlc, Result Accuracy Accu, Result Interpretability Expl;

[0081]

[0082] Mdro = 0.239Seta + 0.254Mdlc + 0.295Accu + 0.212Expl

[0083] 5. Geometric Verification Geov, Dynamic Verification Dynv, Control System Verification Ctsv, Experimental Data Comparison Exdc, Verification Report Vrep.

[0084]

[0085] Mbtv = 0.166Geov + 0.228Dynv + 0.233Ctsv + 0.146Exdc + 0.226Vrep

[0086] The evaluation scale of the third-level indicators determines that each detailed rule has five levels of evaluation. Through the evaluation of each detailed rule, the overall evaluation score is finally obtained.

[0087] Evaluation level Score Completely non-compliant 0.0 Basically non-compliant 0.3 Basically compliant 0.6 Relatively compliant 0.8 Completely compliant 1.0

[0088] Evaluation Rules for the Basic Characteristics of the Dynamic Model

[0089] In the construction process of the digital twin model, the basic characteristics of the dynamic model play a crucial role. Because this model not only provides a basis for subsequent performance analysis, but also lays a necessary foundation for the construction of the entire digital twin system. Through the analysis of the basic characteristics of the dynamic model, the model complexity can be calculated in advance, and the model can be simplified as much as possible to improve the calculation efficiency and operability; the dynamic characteristics of the machine tool can be deeply understood, relevant parameters can be obtained, and the dynamic response of the machine tool under different working conditions can be accurately predicted. The analysis of the dynamic model is of great significance for optimizing the machine tool design, predicting the machine tool performance, optimizing the machining process, and fault diagnosis and prevention, which can improve the performance and reliability of the machine tool, and improve the machining efficiency and quality.

[0090] Evaluation Rules for the Pretreatment Process

[0091] In the construction process of the digital twin dynamic model, the pretreatment process is particularly crucial. It is necessary to clarify the system for modeling, the STEP format specification, and the XML description file specification. The evaluation rules for pretreatment include the evaluation rules for STEP format components, the evaluation rules for XML description files, etc. This key process can provide a unified format, making the model construction process more standardized and normalized. This helps to improve the readability and maintainability of the model. Not only can the components and parts of the model be reused, but also the management and maintenance of the model can be simplified and made more efficient.

[0092] In the construction of digital twin dynamic models, the STEP format provides a unified way to define the geometric shapes, material properties, dimensions, and other relevant information of components. This information can be used to construct components in digital twin dynamic models. Using the STEP format, a component library can be created and managed. By storing components in the STEP format, a large amount of component data can be easily organized and managed, which can improve the reusability and scalability of the model and reduce the workload of repeated modeling.

[0093] In the construction of digital twin dynamic models, XML description files can be used to define and describe the structure, parameters, and behaviors of the model. XML description files can be used to define the structure of the model, including the components, connection relationships, and hierarchical structures of the model. Through XML description files, the organizational structure of the model can be clearly represented, facilitating subsequent model construction and analysis; the parameters of the model can be easily modified and adjusted to adapt to different application scenarios and experimental conditions.

[0094] STEP Format Component Evaluation Rules

[0095] In the construction of dynamic models, using the STEP format can help standardize and unify the description and data exchange of components. Understand the basic principles, structure, and specifications of the STEP format; create STEP files. Organize the relevant information of components into STEP files, and professional CAD software or STEP editors can be used to create and edit STEP files; in the STEP files, define appropriate entities and attributes according to the STEP standard, and use standard naming rules for each entity and attribute; in the STEP files, use appropriate structures and relationships to describe the organizational and hierarchical relationships between components, including assembly relationships, connection relationships, constraint conditions, etc., to ensure that these relationships can accurately reflect the interactions between components in the actual system; export and import STEP files. When using the STEP format to standardize and unify components, follow relevant standards and best practices. Refer to relevant documents, guidelines, and industry specifications to ensure the correct use of the STEP format.

[0096] XML Description File Evaluation Rules

[0097] In the construction of a dynamics model, using an XML description file can help standardize and unify the structure and data of the model. Define an XML schema or use an existing general schema; according to the selected XML schema, construct a model description file, which includes the components, parameters, initial conditions, boundary conditions, etc. of the model; describe the structure and characteristics of the model by reasonably organizing and naming XML elements and attributes; use standard naming conventions for XML elements and attributes to promote consistency and readability. You can refer to relevant standards and guidelines, such as XML namespaces, XML Schema conventions, etc., to select appropriate naming rules and namespaces; use XML elements and attributes to describe the components of the model, such as objects, systems, forces, and constraints, and specify information such as their attributes, positions, masses, inertias, etc.; use XML elements and attributes to represent the equations and algorithms of the dynamics model; define the parameters and initial conditions in the model through XML elements and attributes, including physical parameters, material properties, initial positions, velocities, etc.; use XML elements and attributes to describe boundary conditions and external inputs, including applied forces, control signals, environmental conditions, etc.; according to the complexity and hierarchical structure of the model, reasonably organize the structure and hierarchy of the XML description file, and use the nesting and reference mechanisms of XML to establish the hierarchical relationship and modularity of the model; use an XML validator and parser to validate and parse the model description file, which helps to check whether the XML file conforms to the predefined schema and convert it into a data structure that can be used for model construction and simulation.

[0098] Evaluation Rules for the Construction and Connection of Rigid-Flexible Coupled Multibody Models

[0099] In a digital twin dynamics model, a rigid-flexible coupled multibody model can be used to describe a system composed of rigid bodies and flexible components. The rigid body part is usually composed of rigid body connectors, while the flexible components are usually composed of elastic materials or spring-dampers. By establishing a rigid-flexible coupled multibody model, the dynamic behavior of the actual system can be simulated and analyzed more accurately. The rigid-flexible coupled multibody model can be used to describe the connection and coupling relationships between different components. By defining the connection methods and parameters between rigid body connectors and flexible components, the connection of the rigid-flexible coupled model can be achieved. This helps to construct a more realistic and comprehensive model, thereby more accurately simulating and analyzing the behavior of the actual system.

[0100] Evaluation Rules for Model-Driven Setting and Result Output

[0101] In the digital twin dynamics model, model-driven setting can be used to verify and calibrate the digital twin dynamics model. By comparing the operation data of the actual system with the output of the model, the accuracy and reliability of the model can be evaluated, and the model can be calibrated and adjusted to improve its prediction ability. The result output is an important link in the construction of the digital twin dynamics model. By comparing and analyzing the output results of the model with the data of the actual system, the performance and effectiveness of the system can be evaluated, and decision-making support can be provided.

[0102] Multi-body model verification and evaluation rules

[0103] The multi-body model is the core component of the digital twin dynamics model. By verifying the multi-body model, it can be ensured that the model can accurately describe the dynamics and kinematic behavior of the machine tool. During the verification process, including geometric verification, dynamic verification, kinematic verification, control system verification, etc., the accuracy of the model can be evaluated, and the model can be calibrated and adjusted. By verifying the multi-body model, the accuracy of the digital twin dynamics model can be improved, making it better reflect the behavior of the actual machine tool. By judging the verification results, it is decided whether to construct the digital twin dynamics model system.

[0104] In another embodiment of the present invention, a digital twin dynamics model evaluation system for intelligent manufacturing is provided, which can be used to implement the above-mentioned digital twin dynamics model evaluation method for intelligent manufacturing. Specifically, the system includes:

[0105] A data acquisition module, which is used to acquire n indicators for evaluating the digital twin dynamics model and determine the weight of the first-level evaluation indicators for evaluating the digital twin dynamics model;

[0106] A secondary index weight acquisition module, which is used for n evaluation indicators corresponding to n evaluations. Each evaluation is divided into multiple secondary evaluation indicators, and the weight of the secondary indicators for each model evaluation is obtained according to the secondary evaluation indicators;

[0107] A score acquisition module for model evaluation, which is used to calculate the index evaluation scale according to all secondary evaluation indicators, calculate the secondary score in combination with the weight of the secondary indicators, and obtain the score of each model evaluation;

[0108] An evaluation output module, which is used to obtain the comprehensive score according to the scores of each model evaluation.

[0109] The division of modules in the embodiments of the present invention is illustrative, only a logical function division. In actual implementation, there may be other division methods. In addition, in each embodiment of the present invention, each functional module can be integrated in a processor, or can exist separately physically, or two or more modules can be integrated in one module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules.

[0110] In another embodiment of the present invention, a computer device is provided. The computer device includes a processor and a memory. The memory is used to store a computer program, and the computer program includes program instructions. The processor is used to execute the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function. The processor described in the embodiment of the present invention can be used for the operation of the digital twin dynamics model evaluation method for intelligent manufacturing.

[0111] In another embodiment of the present invention, a storage medium is also provided, specifically a computer-readable storage medium (Memory). The computer-readable storage medium is a memory device in the computer device and is used to store programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and, of course, the extended storage medium supported by the computer device. The computer-readable storage medium provides a storage space that stores the operating system of the terminal. And in this storage space, one or more instructions suitable for being loaded and executed by the processor are also stored. These instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. One or more instructions stored in the computer-readable storage medium can be loaded and executed by the processor to implement the corresponding steps of the digital twin dynamics model evaluation method for intelligent manufacturing in the above embodiments.

[0112] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0113] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0114] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing devices to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0115] These computer program instructions can also be loaded onto a computer or other programmable data processing devices, such that a series of operation steps are executed on the computer or other programmable devices to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable devices provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications or equivalent replacements can still be made to the specific implementation manners of the present invention, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered by the protection scope of the claims of the present invention.

Claims

1. A method for evaluating a digital twin dynamics model for intelligent manufacturing, characterized in that, Including: Obtain n indicators for evaluating the digital twin dynamics model, and determine the weights of the first-level evaluation indicators for the digital twin dynamics model evaluation; The n evaluation indicators correspond to n evaluations. Each evaluation is divided into multiple secondary evaluation indicators, and the weights of the secondary indicators for each model evaluation are obtained according to the secondary evaluation indicators; Calculate the indicator evaluation scale based on all secondary evaluation indicators, calculate the secondary scores by combining the weights of the secondary indicators, and obtain the scores of each model evaluation; Obtain the comprehensive score based on the scores of each model evaluation; Obtain n indicators for evaluating the digital twin dynamics model: The n indicators for evaluating the digital twin dynamics model include: Evaluation Rules for Basic Characteristics of Dynamics Model Abcd, Evaluation Rules for Pretreatment Process Prcp, Evaluation Rules for Rigid-Flexible Coupled Multibody Model Construction and Connection Mrcc, Evaluation Rules for Model Driving Setting and Result Output Mdro, and Evaluation Rules for Multibody Model Verification Mbtv; Divide each evaluation into multiple secondary evaluation indicators: The Evaluation Rules for Basic Characteristics of Dynamics Model Abcd are divided into: Accuracy Accy, Precision Prec, Model Complexity Cmpl, and Parameter Sensitivity Psns; The Evaluation Rules for Pretreatment Process Prcp are divided into: Evaluation Rules for STEP Format Parts Step and Evaluation Rules for XML Description File Xml; The Evaluation Rules for Rigid-Flexible Coupled Multibody Model Construction and Connection Mrcc are divided into: Rigid Body Model Construction Rbdm, Flexible Body Model Construction Sfdm, and Rigid-Flexible Coupled Connection Ccjc; The Evaluation Rules for Model Driving Setting and Result Output Mdro are divided into: Setting Accuracy Seta, Model Credibility Mdlc, Result Accuracy Accu, and Result Interpretability Expl; The Evaluation Rules for Multibody Model Verification Mbtv are divided into: Geometric Verification Geov, Dynamic Verification Dynv, Control System Verification Ctsv, Experimental Data Comparison Exdc, and Verification Report Vrep; Evaluation Rules for STEP Format Parts Step and Evaluation Rules for XML Description File Xml: Create a STEP file, organize the relevant information of the parts into the STEP file. In the STEP file, define entities and attributes according to the STEP standard, and use the standard naming regulations for each entity and attribute; in the STEP file, use structures and relationships to describe the organization and hierarchical relationships between parts, including assembly relationships, connection relationships, and constraint conditions, reflecting the interactions between parts in the actual system; In the construction of the kinetic model, define an XML schema or use an existing general schema; according to the selected XML schema, construct a model description file, including the components, parameters, initial conditions, and boundary conditions of the model; describe the structure and characteristics of the model by organizing and naming XML elements and attributes; use XML elements and attributes to describe the components of the model; use XML elements and attributes to represent the equations and algorithms of the kinetic model; define the parameters and initial conditions in the model through XML elements and attributes, including physical parameters, material properties, initial positions, and velocities; use XML elements and attributes to describe the boundary conditions and external inputs, including applied forces, control signals, and environmental conditions; according to the complexity and hierarchical structure of the model, organize the structure and hierarchy of the XML description file, and use the nesting and reference mechanisms of XML to establish the hierarchical relationship and modularity of the model; use an XML validator and parser to validate and parse the model description file and convert it into a data structure for model construction and simulation.

2. The digital twin dynamics model evaluation method for intelligent manufacturing according to claim 1, wherein Determine the weights of the first-level evaluation indicators for the digital twin kinetic model evaluation: F = 0.2Abcd + 0.2Prcp + 0.2Mrcc + 0.2Mdro + 0.2Mbtv.

3. The digital twin dynamics model evaluation method for intelligent manufacturing according to claim 1, wherein Obtain the weights of the second-level indicators for each model evaluation according to the second-level evaluation indicators: Abcd = 0.338 Accy + 0.288 Prec + 0.205 Cmpl + 0.169 Psns Prcp = 0.5 Step + 0.5 Xml Mrcc = 0.25 Rbdm + 0.25 Sfdm + 0.5 Ccjc Mdro = 0.239 Seta + 0.254 Mdlc + 0.295 Accu + 0.212 Expl Mbtv = 0.166 Geov + 0.228 Dynv + 0.233 Ctsv + 0.146 Exdc + 0.226 Vrep.

4. A digital twin dynamics model evaluation system for intelligent manufacturing, which is used to execute the digital twin dynamics model evaluation method for intelligent manufacturing as described in claim 1, characterized in that, Including: A data acquisition module for acquiring n indicators for the digital twin kinetic model evaluation and determining the weights of the first-level evaluation indicators for the digital twin kinetic model evaluation; A second-level indicator weight acquisition module for corresponding n evaluations to n evaluation indicators, dividing each evaluation into multiple second-level evaluation indicators, and obtaining the weights of the second-level indicators for each model evaluation according to the second-level evaluation indicators; A score acquisition module for model evaluation, which is used to calculate the indicator evaluation scale according to all the second-level evaluation indicators, calculate the second-level scores in combination with the weights of the second-level indicators, and obtain the scores of each model evaluation; An evaluation output module for obtaining a comprehensive score through comprehensive scoring according to the scores of each model evaluation.

5. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the digital twin kinetic model evaluation method for intelligent manufacturing according to any one of claims 1 to 3.

6. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the digital twin dynamics model evaluation method for intelligent manufacturing according to any one of claims 1 to 3.

Images