Reverse Design Method and System for Mechatronic Products Integrating Knowledge Graph and Digital Twin

Abstract

This application belongs to the field of intelligent manufacturing technology, and specifically relates to a reverse design method and system for electromechanical products that integrates knowledge graphs and digital twins. The reverse design method and system for electromechanical products that integrates knowledge graphs and digital twins realizes the semantic unification and dynamic mapping of multi-source heterogeneous data throughout the life cycle by constructing a semantics-driven digital twin model, and enhances the reliability and adaptability of the model in the design, manufacturing, and operation and maintenance processes of electromechanical products.

Description

Technical Field

[0001] This application belongs to the technical field of intelligent manufacturing, and specifically relates to a reverse design method and system for electromechanical products that integrates knowledge graphs and digital twins. Background Technique

[0002] With the improvement of the automation level of industrial products, users' demands for personalized design and rapid iteration are increasing. In the design and development process of complex electromechanical products, a one-way data flow method is usually adopted, that is, the product goes through a complete life cycle from design, manufacturing, operation and maintenance to scrapping. During this process, the life cycle data and experience of the product are not fully utilized, resulting in low design efficiency and reduced product adaptability. In this context, the method of reverse design emerged. The concept of reverse design is to integrate information data at different stages into the design end, so as to consider the adaptability of the product at the beginning of the design, in order to achieve feedback optimization and iterative upgrade of the product.

[0003] Due to the multi-dimensional, structurally different, and format-inconsistent data generated during the design, production, testing, and operation of electromechanical products, it hinders the sharing, flow, and efficient utilization among knowledge models. Moreover, the existing models lack effective data management and semantic association methods, which affect the adaptability and comprehensiveness of the design results. To solve this problem, the Knowledge Graph (KG) provides a knowledge management method that can transform, classify, store, and query semantic knowledge at different life cycle stages of the product, effectively solving the problem of information silos. On the other hand, Digital Twin (DT) constructs a virtual model that is synchronized with the physical product, making it possible for data to flow and models to evolve during the design process. DT can use real-time operation data collected by sensors to dynamically correct the virtual model, thus accurately reflecting the state of the physical system. Therefore, the present invention integrates the structured knowledge management of KG and the dynamic update ability of DT, and proposes a reverse design method and system for electromechanical products Summary of the Invention

[0004] Aiming at the problems of inconsistent formats and semantics of multi-source data, difficult dynamic adjustment of model parameters, and difficult mapping of the association between models and data faced in the traditional design process, a reverse design method and system for electromechanical products that integrates knowledge graphs and digital twins are proposed. The technical solution is as follows

[0005] A reverse design method for electromechanical products that integrates knowledge graphs and digital twins, comprising the following steps:

[0006] S1. Construct a digital twin model with multi-dimensional information association;

[0007] The digital twin model is divided into three dimensions: the information model, the mechanism model, and the domain model. The meta-models corresponding to the three together constitute the complete digital twin model DTM;

[0008] S2. Establish a knowledge graph-based information management mechanism for the digital twin model;

[0009] In the digital twin model, the interaction mode between the information model IM, the mechanism model PM, and the domain model FM determines the mapping mode of the information flow; the knowledge graph helps to achieve information interconnection in the product design, manufacturing, and operation processes through the access, integration, and transformation of multi-dimensional information;

[0010] S3. Establish a knowledge graph-based information-model mapping mechanism;

[0011] Analyze the multi-dimensional information data in different stages of the product life cycle, use the knowledge graph to uniformly manage multi-source heterogeneous information, and establish multiple semantic mapping relationships between information and models;

[0012] S4. Integrate the reverse design optimization process of the knowledge graph and the digital twin;

[0013] The knowledge graph is used for querying and reasoning about knowledge, and updates the digital twin model by mining implicit design knowledge and requirement information through data association, forming a continuously feedback knowledge update loop and enhanced reverse optimization design.

[0014] Preferably, in step S1, the digital twin model expression is as follows:

[0015] ;

[0016] The information model IM refers to a logical data set formed by organizing and structuring the original data according to a certain information modeling framework and semantic rules; where:

[0017] IMI is the input for digital twin model simulation and mapping, IMO represents the virtual simulation prediction results and system response information obtained in the digital space, and IMDT is the information data generated during the mapping and feedback process of the digital twin;

[0018] The mechanism model PM is a quantitative description of the physical behavior and internal mechanism of a product or system;

[0019] The domain model FM is a set of models constructed for different behavioral characteristics and engineering application requirements of the equipment during its entire life cycle.

[0020] Preferably, the knowledge graph-based digital model information management mechanism established in step S2 includes the following three modules:

[0021] Data processing module: responsible for processing physical space data in different formats;

[0022] The key technology module fills the instance information into the corresponding ontology structure;

[0023] Knowledge ontology module: includes IM, PM, and FM multi-dimensional information ontologies, which are used to uniformly store the monitoring data, design parameters, manufacturing status, and simulation results of the model from the physical space.

[0024] Preferably, the mapping mechanism in step S3 includes inheritance mapping:

[0025] ;

[0026] IM 1 O represents the 1 th information model IM 1 the actual input information contained in; IM 2 I represents the 2 th information model IM 2 the model virtual simulation information contained in; in the knowledge graph, it is manifested as the attribute inheritance of the same entity, that is, the information output in IM1O directly corresponds to the information input in IM2I; this mapping is manifested as the direct relationship between "requirements analysis" and "conceptual design", without additional knowledge reasoning.

[0027] Preferably, the mapping mechanism in step S3 includes aggregation mapping:

[0028] ;

[0029] IM i O represents the i th information model IM i the model virtual simulation information contained in, the integration of multi-entity information in the knowledge graph, that is, the data of multiple information sources are combined through an aggregation relationship to form a new information model input.

[0030] Preferably, the mapping mechanism in step S3 includes addition mapping:

[0031] ;

[0032] Adding a mapping is manifested as the property extension of an entity in the knowledge graph, that is, the output information cannot fully meet the requirements of the target twin model, and additional information A needs to be supplemented; adding a mapping is manifested as the association between "optimized design results" and "user requirements", and a complete input information model is generated through knowledge supplementation.

[0033] Preferably, the mapping mechanism in step S3 includes extraction mapping:

[0034] ;

[0035] Only some data items in the information model output in IM1I are required by the information model input in IM2I; Indicates extraction IM 1 O Specific data items in a i A total of k items. In the knowledge graph, extraction mapping is carried out through "attribute screening", that is, specific data items are extracted as the information input of the digital twin model.

[0036] Preferably, step S4 integrates the reverse design optimization process of the knowledge graph and the digital twin, and the specific steps are as follows:

[0037] S41: Define the initial one-way design process as , is an approximate parameter obtained by analyzing design requirements or empirical data. The system parameter is used as a variable related to system conditions and states in the input information model IMI, and is transmitted to PM through the mapping process of the knowledge graph; in PM, a simulation model is called to perform virtual analysis on the structure to obtain performance prediction information , and is input into FM to achieve the one-way optimization of the design parameter ;

[0038] S42: Assuming is known a priori, an optimization algorithm can be used to solve to make optimal to obtain the next-generation product design scheme X*. Due to cannot fully and accurately reflect the actual situation of the product and the design requirements, resulting in having a deviation from the design performance finally shown by the design scheme;

[0039] S43: Define the reverse design model as:

[0040] ;

[0041] Denote the actual response Y obtained by querying and reasoning through the knowledge graph IMI and the model prediction The deviation between Denote the optimized function after correcting the parameters for the deviation Specifically, the reverse process is as follows: Feed the actual response Y of the information model IMI IMI back to the knowledge graph, mine relevant potential relationships and abnormal information through ontology reasoning and rule engines, and continuously update to obtain the actual system parameters ; Use as the new design knowledge to replace the parameters in the original one-way mapping process, that is , thus forming a closed-loop process of design decision reverse feedback

[0042] An electromechanical product reverse design system integrating a knowledge graph and digital twin, including a data acquisition unit, a data processing unit, and a data output unit;

[0043] The electromechanical product physical data and real-time operation data collected by the data acquisition unit;

[0044] The data processing unit combines the structured knowledge management ability of the knowledge graph KG and the dynamic update characteristics of the digital twin DT, enabling the operation knowledge accumulated during the actual use of the electromechanical product to be real-time fed back to the design end, forming a reverse feedback path for continuous knowledge evolution;

[0045] Data output unit: Users can select visual outputs at different stages according to their needs.

[0046] Preferably, in the data processing unit, the digital twin DT enables the flow of data and the evolution of the model during the design process by constructing a virtual model that synchronously updates with the physical product; the knowledge graph DT can use the real-time operation data collected by sensors to dynamically correct the virtual model, thereby accurately reflecting the state of the physical system.

[0047] Compared with the prior art, the beneficial effects of this application are as follows:

[0048] 1. The present invention provides an electromechanical product reverse design method and system integrating a knowledge graph and digital twin, which realizes semantic unification and dynamic mapping of multi-source heterogeneous data in the whole life cycle by constructing a semantic-driven digital twin model, and enhances the reliability and adaptability of the model in the product design, manufacturing, and operation and maintenance processes.

[0049] 2. The effective implementation of the present invention can achieve the deep integration of multi-dimensional data information and knowledge reasoning, enabling the operation knowledge accumulated during the actual use of electromechanical products to be real-time fed back to the design end, forming a reverse feedback path for continuous knowledge evolution, and improving the accuracy and forward-looking of product design.

[0050] 3. The unified semantic modeling framework and knowledge ontology structure proposed in the method of the present invention have good reusability and scalability, can avoid repetitive design domain modeling and knowledge parsing tasks, ensure the consistent expression and efficient interaction of data among multiple stages and models, and improve the generality and reusability of model modeling. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 is the principle framework diagram of the KG-based DT model information management mechanism of the present invention;

[0052] Figure 2 is the principle framework diagram of the information-model mapping mechanism based on KG of the present invention;

[0053] Figure 3 is the reverse design optimization process integrating KG and DT of the present invention;

[0054] Figure 4 is the reverse design optimization flow chart integrating KG and DT for case introduction of the present invention;

[0055] Figure 5 is the partial ontology structure diagram of the high-speed train bogie KG for case introduction of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0056] The following detailed descriptions are all exemplary and are intended to provide further explanations of the present disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present disclosure belongs.

[0057] Aiming at the problems of inconsistent formats and semantics of multi-source data, difficult dynamic adjustment of model parameters, and difficult mapping of the association between models and data faced in the traditional design process, a reverse design method and system for electromechanical products integrating knowledge graph and digital twin are proposed, which includes 5 parts, S1 construction of a digital twin model with multi-dimensional information association, S2 KG-based DT model information management mechanism, S3 KG-based information-model mapping mechanism, and S4 reverse design optimization process integrating KG and DT.

[0058] S1. Construction of a digital twin model with multi-dimensional information association:

[0059] The digital twin model is divided into three dimensions: the information model, the mechanism model, and the domain model. The meta-models corresponding to the three together constitute the complete digital twin model DTM. DTM is the digital representation of a physical entity. This includes its characteristics, attributes, transmission status, parameters, data, and transmission capabilities. The mathematical expression form of the digital twin model defined in the present invention is shown in the following formula.

[0060] 。

[0061] Specifically, it includes the following three parts:

[0062] S11: IM refers to the logical data set formed by organizing and structuring the original data according to a certain information modeling framework and semantic rules, aiming to achieve the virtual representation and process tracking of physical objects. According to its different functional positions in the DTM model, IM can be divided into the following three types.

[0063] The input information model IMI in the digital twin model, the output information model IMO, and the twin information model IMDT generated during the mapping process of the digital twin model.

[0064] IMI is the input for the simulation and mapping of the DT model, containing information related to the physical system such as product structure parameters, boundary conditions, load distribution, environmental variables, material properties, etc. IMO represents the virtual simulation prediction results and system response information obtained in the digital space, such as displacement, stress, modal frequency, temperature rise data, operation status feedback, etc. IMDT is the information data generated by DT during the mapping and feedback process. Such as intermediate variables in the model identification process, mapping correlation relationships, adjustment records during the optimization process, model correction results, etc.

[0065] S12: PM represents the mechanism model in this twin model. PM is a quantitative description of the physical behavior and internal mechanism of a product or system. By modeling actual physical phenomena (such as structural stress, heat conduction, fluid flow, electromagnetic effects, etc.), PM abstracts physical laws into mathematical expression forms, such as partial differential equations, state space models, continuous mechanics models, etc. Further transformed into computational models available for simulation analysis, numerical calculation models such as the finite element method (FEM), multi-body dynamics (MBD), and computational fluid dynamics (CFD).

[0066] S13: FM represents the domain model in the digital twin model. FM is a set of models constructed for different behavioral characteristics and engineering application requirements of the device during its entire life cycle. FM covers multiple sub-domains such as design optimization, operation monitoring, status assessment, life prediction, fault diagnosis, and safety warning. Each domain model corresponds to a specific life cycle stage and engineering task. For example, in the design stage, FM can integrate models such as structural optimization models and parameter sensitivity analysis to explore the design space and quickly find the optimal solution for the optimal design of the product.

[0067] S2. KG-based DT model information management mechanism:

[0068] In the DT model, the interaction mode between the information model (IM), the mechanism model (PM), and the domain model (FM) determines the mapping mode of the information flow. The knowledge graph (KG) helps to achieve information intercommunication in the product design, manufacturing, and operation processes through the access, integration, and transformation of multi-dimensional information.

[0069] Since multi-dimensional information covers multiple key stages of the product life cycle, including geometric design, material selection, processing technology, and assembly process, etc. Therefore, it is first necessary to clarify the mapping direction of the information flow, determine the type of exchanged information, and classify the generated and applied information, such as geometric parameters, material properties, processing technology data, etc. The carriers of design, processing, and operation information include text, images, and files in specific formats. Considering the problems of diverse knowledge sources, heterogeneous data formats, large data volume, and uneven data quality, the DT model is combined with KG for the management of multi-dimensional information and the mapping transmission between the IM, PM, and FM sub-models, as Figure 1 shown.

[0070] The KG-based DT model information management mechanism mainly includes the following three modules.

[0071] Data processing module: Responsible for processing physical space data in different formats. This module uses a variety of data conversion and preprocessing technologies, including rule-based structured parsing, unstructured text information extraction based on natural language processing (NLP), normalization and time series interpolation processing of sensor data, and multi-source data fusion algorithms (such as principal component analysis PCA and multi-modal alignment technology) to uniformly standardize multi-source heterogeneous data into a standard format that can be parsed by the knowledge graph, improving the accuracy and efficiency of subsequent knowledge extraction, entity recognition, and relationship modeling.

[0072] Key technology module: It includes key technologies such as entity recognition and ambiguity resolution, and automatically fills instance information into the corresponding ontology structure. It uses named entity recognition models such as BiLSTM-CRF to extract entities from text and structured data, and combines context semantic embedding (such as BERT) to improve the context adaptation ability of recognition. At the same time, an ambiguity resolution mechanism based on vector space model and semantic similarity calculation is introduced to solve the problems of homonymy and cross-domain entity confusion. And through ontology matching and rule reasoning technologies, the extraction results are subjected to structure mapping and semantic verification to ensure the consistency and integrity of data and ontology, so as to realize the structured expression and dynamic update of knowledge in the design, manufacturing and operation stages of the physical world.

[0073] Knowledge ontology module: It includes multi-dimensional information ontologies such as IM (information model), PM (mechanism model), and FM (domain model), which are used to uniformly store monitoring data, design parameters, manufacturing status, and simulation results of models from the physical space. For example, the stress response, temperature rise data, and design performance evaluation results of structural components can be stored in the corresponding ontology instances. This module constructs the ontology architecture using the OWL language, uses Protégé for modeling and visualization management, and combines ontology alignment technologies (such as structure matching algorithms based on semantic similarity) to achieve structure docking and unified expression among multi-source knowledge. At the same time, SPARQL is used for efficient data query, and SWRL rules are integrated to realize ontology reasoning and dynamic knowledge expansion, improving the interpretability and flexibility of the knowledge graph.

[0074] S3. KG-based information-model mapping mechanism:

[0075] The product life cycle involves the interaction and sharing of multi-dimensional information, which affects the construction of the twin model. Therefore, it is necessary to analyze the information mapping process between models at different stages. Combining KG with the definition of the information model FM in S1, this mapping process can be expressed as a KG-based information-model mapping mechanism, as Figure 2 shown. It mainly includes the following four independent mapping methods.

[0076] Inheritance mapping: ;

[0077] In KG, it is manifested as the attribute inheritance of the same entity, that is, the information output in IM1O directly corresponds to the information input in IM2I. For example, the requirement information output by the requirement analysis DT model can be directly used as the input of the conceptual design DT model. In KG, this mapping is manifested as a direct relationship between "requirement analysis" and "conceptual design", without additional reasoning.

[0078] Aggregation mapping: ;

[0079] Multi-entity information integration in KG means that data from multiple information sources are combined through aggregation relationships to form a new information model input. For example, the input information of a manufacturing model may be composed of the knowledge of multiple design models (such as structural design, material design, process planning). In this case, it is necessary to integrate multiple information sources through aggregation relationships.

[0080] Add mapping: ;

[0081] Adding mapping is manifested as the attribute extension of entities in KG, that is, the output information cannot fully meet the requirements of the target twin model, and additional information A needs to be supplemented. For example, the output information of the optimized design DT model may also need to be combined with the personalized needs of users to form a complete decision-making plan. In KG, this mapping is manifested as the association between "optimized design results" and "user needs", and a complete input information model is generated through knowledge supplementation.

[0082] Extract mapping: ;

[0083] Only some data items in the information model output in IM1I are required by the information model input in IM2I. This is manifested as information screening and streamlining in KG. For example, in the mapping process from the structural design DT model to the process design DT model, only part of the information in the part structure diagram needs to be input into the process design stage. In KG, this mapping can be carried out through "attribute screening". That is, specific data items are extracted to make them the information input of the target DT model.

[0084] S4. Reverse design optimization process integrating KG and DT:

[0085] Traditionally, this process usually assumes model parameters or predefined module configurations, resulting in a lack of feedback process in the constructed design domain model. This leads to suboptimal configurations in terms of the adaptability of the design results and user requirements. Therefore, based on the construction and mapping of the KG multi-dimensional twin model, Figure 3 the reverse design process integrating KG and DT as shown is proposed. KG is used for knowledge management and reasoning, and through data feedback, latent design knowledge and requirement information are mined to achieve continuous iterative upgrading of products. The reverse design process is as follows.

[0086] S41: Define the initial one-way design process as , and use the system parameters as variables related to system conditions and states, etc. in the input information model IMI, such as load distribution, boundary conditions, material properties, etc. required in structural design. It is transmitted to the mechanism model PM through the mapping process of KG. In PM, simulation models (such as ANSYS, Abaqus, etc.) are called to perform virtual analysis on the structure, and performance prediction information such as stress, displacement, and mode is obtained. . It is input into the design domain model FM to achieve one-way optimization of design parameters.

[0087] S42: In S41, They are usually approximate parameters obtained through analysis based on design requirements or empirical data. For example, through DSE space exploration, combined with the DoE experimental design method, the initial parameter range is constructed under the condition of limited samples. Approximate parameters are estimated using regression analysis based on historical cases or machine learning prediction models (such as SVR, random forest, and other technical methods). . Then, assuming is known a priori, intelligent optimization techniques such as the particle swarm optimization algorithm (PSO) and genetic algorithm (GA) are used to solve to make optimal to obtain the next-generation product design scheme X*. However, due to it cannot fully and accurately reflect the actual situation of the product and the design requirements. This leads to a deviation between

[0088] S43: Therefore, based on the mapping of the DT model and the information management of KG in S1~S3, reverse design is defined as . In the formula, represents the actual response Y obtained through knowledge graph query and reasoning IMI and the model prediction between represents the optimization function after correcting the parameters for the deviation. The specific reverse process is as follows: The actual response Y of the information model IMI is fed back to KG. Through the ontology reasoning of KG (such as classification reasoning and instance reasoning based on description logic) and rule engines (such as SWRL rules), relevant potential relationships and abnormal information are mined. Combining correction methods such as Bayesian inversion, Kalman filtering, and particle filtering, IMI is continuously updated to obtain the actual system parameters . is used as the new design knowledge to replace the parameter in the original one-way mapping process, that is, , thus forming a closed-loop process of design decision reverse feedback.

[0089] S5. Case introduction for the high-speed train bogie:​​​

[0090] The bogie of a high-speed train is a large and complex structure, characterized by large structural dimensions, extremely complex shapes, and high safety margins. The components of this equipment are bulky, and the interaction relationships between them are complex, making the design extremely difficult. One of the key points in bogie design is to optimize its frame structure, reduce the mass while ensuring strength, and achieve low-carbon and low-cost transportation. Among them, the lightweight performance and strength performance are modeled as objective functions.

[0091] Due to the complexity of the bogie, parameters such as loads and material strengths are usually random and uncertain. This requires making assumptions based on prior experience or setting a high safety factor for structural design, resulting in design redundancy. At the same time, if the feedback analysis of actual operation data is ignored, there may be a risk of serious safety accidents when the natural frequency of the structure is within the actual operation frequency range and resonance occurs. Therefore, it is necessary to mine the actual data information and feedback it to the design end to form a reverse design to improve the adaptability and reliability of the design. The case implementation steps are as Figure 4 shown.

[0092] S51: First, it is necessary to manage various parameters included in the bogie, including multi-dimensional information such as geometric dimensions, material properties, boundary conditions, and vibration response data. Based on the composition of the DT model in S1, construct a multi-dimensional information knowledge ontology based on KG. It is necessary to identify the multi-dimensional information data contained in the information model IMI, the design domain model FM, and the mechanism model PM. These information cover the design scheme, response data, geometric shape, boundary conditions, modeling parameters, etc. of the bogie.

[0093] To effectively manage this information, use the named entity recognition (NER) technology that combines rules and statistical learning to extract key entities from unstructured text and sensor data. Perform semantic alignment in combination with the ontology dictionary, and use relationship extraction algorithms (such as techniques based on template matching or BERT semantic relation classifiers) to establish semantic connections between entities. According to the description logic rules and the OWL semantic model, automatically fill the three types of extracted knowledge instances into the corresponding FM, IMI, and PM ontologies. A partial display diagram of the constructed ontology structure is as Figure 5 shown.

[0094] S52: The FM ontology includes size parameters of structures such as the crossbeam, side beam, and inner plate of the bogie. The IMI knowledge ontology includes processing technologies of the bogie, acceleration monitoring signals, and force monitoring signals. The PM knowledge ontology includes parameters such as the density, elastic stiffness, and damping of the model. After the data processing and knowledge extraction steps, extract relevant instances and store them in the corresponding ontologies. All structured knowledge is imported into the Neo4j graph database to construct a multi-dimensional knowledge graph for the bogie.

[0095] S53: With the strength performance Y1 and the lightweight performance Y2 as the objective functions, based on the finite element theory, a mechanical analysis model of the high-speed train bogie is established to provide a mechanism model for structural optimization. Although numerical simulation can reflect its mechanical characteristics to a certain extent, system parameters need to be assumed according to empirical estimates or predefined ranges , including parameters such as density, elastic stiffness, and damping. These parameters are important factors affecting the performance of the high-speed train bogie. Correct the system parameters according to the actual data is the unique advantage of reverse design. By using the corrected to replace the assumed , it helps to improve the product and optimize the design.

[0096] Perform multi-dimensional information management through KG in S52 and map it to the mechanism model FM. By developing an intelligent correction algorithm, update parameters such as density, elastic stiffness, and damping to construct a twin IMDT model consistent with the actual output. At this time, more accurate predicted values of target performances such as strain and mass can be obtained , to guide the mechanism optimization of the bogie, that is . Map the optimization plan to the design domain model, and the structure can be further iteratively optimized according to the actual design requirements. For example Figure 4 analyze the actual train operation data in

[0097] A reverse design system for mechatronic products integrating knowledge graph and digital twin, including a data acquisition unit, a data processing unit, and a data output unit;

[0098] The data acquisition unit collects the physical data and real-time operation data of the mechatronic product;

[0099] The data processing unit combines the structured knowledge management ability of the knowledge graph KG and the dynamic update characteristics of the digital twin DT, enabling the operation knowledge accumulated during the actual use of the mechatronic product to be real-time fed back to the design end, forming a reverse feedback path for continuous knowledge evolution;

[0100] In the data processing unit, the digital twin DT enables the flow of data and the evolution of the model during the design process by constructing a virtual model that synchronously updates with the physical product; the knowledge graph DT can use the real-time operation data collected by sensors to dynamically correct the virtual model, thus accurately reflecting the state of the physical system;

[0101] Data output unit: The user can select visual outputs at different stages according to requirements.

[0102] The above are only the preferred embodiments of the present application. It should be noted that for those of ordinary skill in the art, without departing from the technical principle of the present application, several improvements and modifications can be made, and these improvements and modifications should also be regarded as the protection scope of the present application.

Claims

1. A reverse design method for electromechanical products integrating knowledge graph and digital twin, characterized in that: The following steps are involved: S1. Construct a digital twin model with multi-dimensional information association; The digital twin model is divided into three dimensions: information model, mechanism model and domain model. The metamodels corresponding to the three together constitute a complete digital twin model DTM; S2. Establish a digital twin model information management mechanism based on knowledge graph; In the digital twin model, the interaction between the information model IM, the mechanism model PM and the domain model FM determines the mapping method of the information flow; the knowledge graph helps to achieve information exchange in the product design, manufacturing and operation process by accessing, integrating and converting multi-dimensional information; S3. Establish an information-model mapping mechanism based on knowledge graph; Analyze multi-dimensional information data at different stages of the product life cycle, use knowledge graphs to uniformly manage multi-source heterogeneous information, and establish multiple semantic mapping relationships between information and models; S4. Reverse design optimization process integrating knowledge graph and digital twin; The knowledge graph is used for knowledge query and reasoning. It updates the digital twin model by mining hidden design knowledge and demand information through data association, forming a continuous feedback knowledge update loop and enhanced reverse optimization design. S41: Define the initial one-way design process as , It is an approximate parameter obtained by analyzing the design requirements or empirical data. As variables related to system conditions and status in the input information model IMI, Transmitted to PM through the knowledge graph mapping process; In PM, the simulation model is called to perform virtual analysis on the structure to obtain performance prediction information ,Will Input into FM to realize design parameters One-way optimization; S42: In the assumption When it is known a priori, the optimization algorithm can be used to solve make The optimal product design solution X* is obtained, because It cannot fully and accurately reflect the actual situation of the product and the design requirements, resulting in Deviations from the final design performance of the design solution; S43: Define the reverse design model as: ； Represents the actual response Y obtained through knowledge graph query reasoning IMI With model prediction The deviation between Indicates the deviation of the parameter The revised optimization function; The specific reverse process is: the actual response Y of the information model IMI IMI Feedback to the knowledge graph, through ontology reasoning and rule engine to mine relevant potential relationships and abnormal information, and continuously update , based on the actual system parameters ;Will As new design knowledge to replace the parameters in the original one-way mapping process ,Right now , thus forming a closed-loop process of reverse feedback of design decisions.

2. The electromechanical product reverse design method integrating knowledge graph and digital twin according to claim 1 is characterized in that: In step S1, the digital twin model expression is as follows: ； Information model IM refers to a logical data set formed by organizing and structuring the original data according to a certain information modeling framework and semantic rules; among them: IMI is the input of digital twin model simulation and mapping, IMO represents the virtual simulation prediction results and system response information obtained in the digital space, and IMDT is the information data generated by the digital twin during the mapping and feedback process; The mechanism model PM is a quantitative description of the physical behavior and internal mechanism of a product or system; The domain model FM is a collection of models built based on the different behavioral characteristics and engineering application requirements of equipment throughout its life cycle.

3. The electromechanical product reverse design method integrating knowledge graph and digital twin according to claim 1 is characterized in that: The digital model information management mechanism based on knowledge graph established in step S2 includes the following three modules: Data processing module: responsible for processing physical space data in different formats; The key technology module fills the instance information into the corresponding ontology structure; Knowledge ontology module: includes IM, PM, and FM multi-dimensional information ontologies, which are used to uniformly store monitoring data, design parameters, manufacturing status, and simulation results of models from the physical space.

4. The electromechanical product reverse design method integrating knowledge graph and digital twin according to claim 1 is characterized in that: The mapping mechanism in step S3 includes inheritance mapping: ； IM 1 O Indicates 1 Information Model IM 1 The actual input information contained in IM 2 I Indicates 2 Information Model IM 2 The model virtual simulation information contained in IM1O is represented as the attribute inheritance of the same entity in the knowledge graph, that is, the information output in IM1O directly corresponds to the information input in IM2I.

5. The electromechanical product reverse design method integrating knowledge graph and digital twin according to claim 1 is characterized in that: The mapping mechanism in step S3 includes aggregate mapping: ； IM i O Indicates i Information Model IM i The model virtual simulation information contained in the knowledge graph integrates the multi-entity information, that is, the data from multiple information sources are combined through aggregation relationships to form a new information model input.

6. The electromechanical product reverse design method integrating knowledge graph and digital twin according to claim 1 is characterized in that: The mapping mechanism in step S3 includes adding a mapping: ； Adding a mapping is represented in the knowledge graph as an attribute extension of the entity, that is, the output information cannot fully meet the needs of the target twin model, and additional information A needs to be supplemented; adding a mapping is represented by associating "optimized design results" with "user needs", and a complete input information model is generated through knowledge supplementation.

7. The electromechanical product reverse design method integrating knowledge graph and digital twin according to claim 1 is characterized in that: The mapping mechanism in step S3 includes extracting the mapping: ； Representation Extraction IM 1 O Specific data items in a i common k items and use them as information input for the digital twin model.

8. A reverse design system for electromechanical products integrating knowledge graph and digital twin, using the reverse design method for electromechanical products integrating knowledge graph and digital twin as described in any one of claims 1 to 7, characterized in that: It includes a data acquisition unit, a data processing unit and a data output unit; The data acquisition unit acquires the physical data and real-time operation data of the electromechanical products; The data processing unit combines the structured knowledge management capabilities of the knowledge graph KG with the dynamic update characteristics of the digital twin DT, so that the operation knowledge accumulated during the actual use of electromechanical products can be fed back to the design end in real time, forming a reverse feedback path for the continuous evolution of knowledge; Data output unit: Users can choose visual output at different stages according to their needs.

9. The electromechanical product reverse design system integrating knowledge graph and digital twin according to claim 8, characterized in that: The digital twin DT in the data processing unit builds a virtual model that is updated synchronously with the physical product, making the flow of data and the evolution of the model possible during the design process; the knowledge graph DT can use the real-time operation data collected by sensors to dynamically correct the virtual model, thereby accurately reflecting the state of the physical system.

Images