Design failure mode and influence analysis method and system based on knowledge graph and large model retrieval enhancement

Through the design failure mode and impact analysis method based on knowledge graphs and large models, the problem of insufficient reliance on personal experience, information islands and dynamic updates in the DFMEA process is solved, and dynamic management and efficient analysis are realized throughout the life cycle, which has improved new Reliability and safety of energy vehicle design and manufacturing.

CN118966002AActive Publication Date: 2024-11-15CHONGQING UNIV

Patent Information

Application Number
CN202411100111.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-12
Publication Date
2024-11-15
Estimated Expiration
2044-08-12

AI Technical Summary

Technical Problem

The existing DFMEA process relies on personal experience, has serious information silos, insufficient dynamic updates, and is difficult to adapt to the needs of complex design and manufacturing of new energy vehicles. The degree of intelligence and automation is not high, resulting in low efficiency and accuracy of failure mode analysis, which affects product reliability. Sex and safety.

Method used

Using design failure mode and impact analysis methods based on knowledge graph and large model retrieval, we form a full-cycle knowledge base through planning and preparation stages, structural analysis, failure analysis, risk analysis and optimization stages, combined with multidisciplinary teams and system integration, and use the full-cycle knowledge base. The large model performs in-depth analysis and information extraction, generates failure analysis results, and continuously optimizes.

Benefits of technology

It improves the objectivity and comprehensiveness of failure analysis, realizes dynamic management throughout the entire life cycle, improves the reliability and safety of product design and manufacturing processes, reduces human errors and omissions, and improves the efficiency of information retrieval and analysis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118966002A_ABST
    Figure CN118966002A_ABST
Patent Text Reader

Abstract

The invention discloses a design failure mode and influence analysis method based on knowledge graph and large model retrieval enhancement. The method comprises the following steps: step 1, a planning and preparation stage; 2, a structural analysis and function analysis stage; 3, a failure analysis stage: processing the input data by using a graph knowledge multiplexing component, retrieving related information from a complete-cycle knowledge base, and processing and constructing by using an industrial knowledge software system to obtain a knowledge graph; the input information is deeply analyzed through a large model retrieval enhancement method based on the knowledge graph, related information is extracted from the knowledge graph in combination with a large model prompt learning method, and a failure analysis result is generated; 4, a risk analysis and optimization stage: determining problems which need to be solved preferentially, and putting forward and implementing improvement measures; and 5, a result document and system integration stage. The invention further discloses a big model retrieval enhancement design failure mode and influence analysis system based on the knowledge graph.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of failure mode and effect analysis, and specifically provides a design failure mode and effect analysis method and system based on knowledge graph and large model retrieval enhancement. Background Art

[0002] DFMEA (Design Failure Mode and Effects Analysis) is a type of FMEA (Failure Mode and Effects Analysis) that focuses on failure prevention and risk management in the product design stage. It aims to discover and eliminate weaknesses in the design and ensure the reliability and safety of the product in actual use by systematically identifying, analyzing and evaluating potential failure modes and their effects in the design. By identifying and solving design problems early, DFMEA provides a solid guarantee for the successful development and application of products. In the design and manufacturing process of new energy vehicles, DFMEA is an important tool to ensure product reliability and safety. However, there are some common problems in the current DFMEA practice.

[0003] (1) The DFMEA process is highly dependent on personal experience. Traditional analysis mainly relies on the knowledge and experience of the expert team. This dependence causes the analysis results to be greatly affected by the professional quality and experience depth of the participants, which is prone to subjective bias and may miss key failure modes, thus affecting the reliability and safety of the product.

[0004] (2) The problem of information islands is serious. In the traditional DFMEA process, information sharing between different departments and teams is insufficient, and various design data and failure cases are scattered in their respective systems, making it difficult to form a unified knowledge base. This phenomenon of information islands makes it difficult to fully utilize existing experience and data during the analysis process, increases duplication of work and waste of resources, and reduces the efficiency and accuracy of failure mode identification.

[0005] (3) Insufficient dynamic updating and continuous optimization of DFMEA information. Traditional DFMEA analysis is often fixed after the design phase is completed, lacking dynamic association with feedback and improvement measures during actual use. As new energy vehicles continue to expose new problems and failure modes in actual use, the original DFMEA analysis results may be outdated and unable to reflect the current product status. This static analysis model limits the effectiveness of DFMEA throughout the product life cycle and is difficult to adapt to changing product needs and technological advances.

[0006] (4) The complexity of new energy vehicles increases the difficulty of DFMEA. New energy vehicles involve a variety of new technologies and new materials such as batteries, motors, and electronic control systems. Their design and manufacturing processes are more complex than those of traditional fuel vehicles. The interaction between each system and component is closer, and the analysis and prevention of failure modes become more challenging. Traditional DFMEA methods are difficult to fully cover these complex interactions, resulting in potential failure modes being overlooked.

[0007] (5) The intelligence and automation of DFMEA tools and methods are not high. Most of the current DFMEA tools are still at the stage of manual recording and analysis, lacking intelligent data processing and analysis methods. This not only increases the workload, but also easily leads to human errors and omissions. With the development of big data and artificial intelligence technology, DFMEA tools urgently need to be upgraded to improve the automation and intelligence of analysis, thereby improving the efficiency and accuracy of analysis. Summary of the invention

[0008] In view of this, the purpose of the present invention is to provide a design failure mode and effect analysis method and system based on knowledge graph and large model retrieval enhancement, which can accurately identify and predict possible failure modes, improve the speed and accuracy of analysis, reduce human errors and omissions, so as to continuously improve the reliability and safety of the design throughout the product life cycle.

[0009] In order to achieve the above object, the present invention provides the following technical solutions:

[0010] The present invention first proposes a design failure mode and effect analysis method based on knowledge graph and large model retrieval enhancement, comprising the following steps:

[0011] Step 1: Planning and preparation phase

[0012] Carry out planning and preparation, clarify analysis objectives, and form a multidisciplinary team;

[0013] Step 2: Structural and functional analysis phase

[0014] Conduct structural analysis of the product, identify the functions of each subsystem, assembly and component and their interrelationships, and fully understand the design intent of the product and the interaction of each part;

[0015] Step 3: Failure Analysis Phase

[0016] Input design schemes, design standards, two-dimensional models and existing failure case information, use graph knowledge reuse components to process input data and retrieve relevant information from the full-cycle knowledge base, and then process and construct a knowledge graph through the industrial knowledge software system; the large model retrieval enhancement method based on the knowledge graph deeply analyzes the input information, and combines the large model prompt learning method to extract relevant information from the knowledge graph to generate failure analysis results including failure impact, failure mode and failure cause;

[0017] Step 4: Risk Analysis and Optimization Phase

[0018] Evaluate the severity, frequency and detection difficulty of each failure mode, calculate the risk priority number, and determine the issues that need to be addressed first; propose and implement improvement measures including design improvements, process adjustments and additional detection methods to reduce or eliminate high-risk failure modes;

[0019] Step 5: Result documentation and system integration phase

[0020] The analysis results including failure modes, failure effects, failure causes, risk assessment and optimization measures are documented and stored in the FMEA knowledge base. By integrating with the data center, bill of materials BOM system and product lifecycle management PLM system, a full-cycle knowledge base is formed, and the full-cycle knowledge base is continuously updated and optimized throughout the product life cycle.

[0021] Furthermore, in step 1, the planning and preparation method steps are:

[0022] 11) Clarify the objectives and scope of FMEA analysis and ensure that the basic information of the project is complete;

[0023] 12) Establish a multidisciplinary team including design, manufacturing, quality and service to ensure the comprehensiveness and professionalism of FMEA analysis;

[0024] 13) Develop a detailed project plan to clarify the time schedule, resource allocation and responsible persons for each task to ensure that the FMEA analysis is carried out as planned.

[0025] Further, in step 2, the method of structural analysis is:

[0026] In the design failure mode and effect analysis, identify and define the product structure and clarify the interface design of each subsystem, component and part;

[0027] In process failure mode and effects analysis, critical steps in the manufacturing and assembly process are identified to ensure the stability of process inputs and outputs.

[0028] Further, in step 2, the method of functional analysis is:

[0029] In the design failure mode and effect analysis, define the functions and characteristics of the product to ensure that the design can meet the expected performance and reliability requirements;

[0030] In process failure mode and effect analysis, key functions in the process are identified to ensure that each step can achieve its intended function and avoid failures caused by process variation.

[0031] Further, in step three, the method steps of failure analysis are:

[0032] 31) Identify possible failure modes of products or processes;

[0033] 32) Evaluate the potential impact of each failure mode on the system, subsystem, component and user;

[0034] 33) Analyze potential causes that lead to failure modes.

[0035] Furthermore, in step 4, the risk analysis method steps are:

[0036] 41) Identify and develop preventive measures to reduce the probability of failure;

[0037] 42) Identify and implement detection measures to improve detection capabilities after failures occur;

[0038] 43) Score the severity S, frequency of occurrence O and detection difficulty D of each failure mode, and re-evaluate the risk priority number based on the implemented prevention and detection measures to ensure that the risks are effectively controlled.

[0039] Furthermore, in step 4, the risk optimization method steps are:

[0040] 44) Identify and record high-risk failure modes that require improvement;

[0041] 45) Propose specific optimization measures including design improvement, material replacement and process adjustment;

[0042] 46) Implement optimization measures and verify their effectiveness;

[0043] 47) Score and evaluate optimization measures to ensure they significantly reduce risk priority numbers.

[0044] Furthermore, in the step three, the big model retrieval enhancement method based on the knowledge graph is: starting from the design plan and standards, a problem combination representation is generated, and it is passed to the big model through Prompt for knowledge retrieval; the big model performs in-depth analysis of the prompts, extracts relevant knowledge from the knowledge graph, and generates failure analysis results.

[0045] Furthermore, in step 3, the large model prompt learning method is:

[0046] Input the question, and then provide a batch of examples from the analog pool and the supplementary pool to the large model; repeat this step until the input sequence length limit is reached;

[0047] Restate the query text and input the original triple sequence, and use the large model to re-rank the top candidate entities in the original triple sequence;

[0048] Parse the answer given by the large model into an ordered list and replace the first few entities in the original triple sequence as the final answer, thereby completing the knowledge reasoning task.

[0049] The present invention also proposes a large model retrieval enhanced design failure mode and effect analysis system based on knowledge graph, including a data acquisition system, a design failure mode and effect analysis system and a user interaction system;

[0050] The data acquisition system is used to acquire data and includes a data center, a bill of materials BOM system and a product lifecycle management PLM system;

[0051] After the design failure mode and effect analysis system obtains the failure analysis results by using the design failure mode and effect analysis method based on knowledge graph and large model retrieval enhancement as described above, it performs risk analysis and optimization on the failure analysis results, and finally documents and stores the analysis results in the FMEA knowledge base;

[0052] The user interaction system is used to display the analysis results to the user.

[0053] The beneficial effects of the present invention are:

[0054] The design failure mode and effect analysis method based on knowledge graph and large model retrieval enhancement of the present invention has the following technical effects:

[0055] (1) Improve the objectivity and comprehensiveness of failure analysis. By utilizing the deep analysis capabilities of knowledge graphs and large models, it can effectively integrate multiple information sources such as design plans, design standards, two-dimensional models, and failure cases to generate comprehensive and accurate failure analysis results, overcoming the problem that traditional FMEA relies heavily on personal experience and data islands, ensuring continuous optimization and updating of DFMEA information throughout the product life cycle, and improving the reliability and safety of product design and manufacturing processes.

[0056] (2) Realize dynamic management and application throughout the entire life cycle. The system integrates with the data center, bill of materials BOM system and product life cycle management PLM system to form a full-cycle knowledge base covering the entire product life cycle. FMEA information can be continuously updated and optimized during product design, manufacturing, use and maintenance. This full-cycle dynamic management method ensures that failure modes and improvement measures can reflect the current product status in real time, improving product reliability and safety.

[0057] (3) Improve the efficiency and accuracy of information retrieval and failure analysis. The large model retrieval enhancement method based on the knowledge graph significantly improves the efficiency of engineering design and problem solving through rich semantic understanding and fast information retrieval. Combined with the prompt learning method of the large model, the system can extract the most relevant information from the knowledge graph, generate failure analysis results, assess risks and propose optimization measures. This efficient and accurate information processing capability makes the failure analysis process faster and more reliable, improving the overall operation and maintenance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to make the purpose, technical solution and beneficial effects of the present invention clearer, the present invention provides the following drawings for illustration:

[0059] Figure 1 A flow chart of the design failure mode and effect analysis method based on knowledge graph and large model retrieval enhancement of the present invention;

[0060] Figure 2 Provide a technical roadmap for designing failure mode and effects analysis;

[0061] Figure 3 A seven-step flow chart for failure mode and effects analysis;

[0062] Figure 4 Flowchart of the enhanced method for large model retrieval;

[0063] Figure 5 Flowchart for cue learning of large models;

[0064] Figure 6 Flowchart of the software-based approach for industrial knowledge;

[0065] Figure 7 A flowchart for constructing a hierarchical multimodal industrial knowledge ontology system;

[0066] Figure 8 It is a structural diagram of the hierarchical ontology system;

[0067] Fig. 9 Schematic diagram of the industrial knowledge mining framework for modal feature-natural language description generation;

[0068] Fig.10 Schematic diagram for cross-modal industrial knowledge fusion and industrial knowledge graph formation throughout the product life cycle;

[0069] Fig.11 This is the schematic diagram of the knowledge graph-based large model retrieval enhanced design failure mode and effect analysis system of the present invention. DETAILED DESCRIPTION

[0070] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it, but the embodiments are not intended to limit the present invention.

[0071] like Figure 1-3 As shown, the design failure mode and effect analysis method based on knowledge graph and large model retrieval enhancement in this embodiment includes the following steps.

[0072] Step 1: Planning and preparation phase

[0073] Carry out planning and preparation, clarify analysis objectives, and form a multidisciplinary team.

[0074] In the initial stage of DFMEA analysis, detailed planning and preparation are crucial. Specifically, in this embodiment, the planning and preparation method steps are as follows:

[0075] 11) Clarify the objectives and scope of FMEA analysis and ensure that the basic information of the project is complete;

[0076] 12) Establish a multidisciplinary team including design, manufacturing, quality and service to ensure the comprehensiveness and professionalism of FMEA analysis;

[0077] 13) Develop a detailed project plan to clarify the time schedule, resource allocation and responsible persons for each task to ensure that the FMEA analysis is carried out as planned.

[0078] Step 2: Structural and functional analysis phase

[0079] Conduct structural analysis of the product, identify the functions of each subsystem, assembly and component and their interrelationships, and fully understand the design intent of the product and the interaction of its parts.

[0080] The purpose of the structural analysis phase is to identify the various components of the product and their interrelationships, laying the foundation for subsequent failure analysis. Specifically, the method of structural analysis is: in the design failure mode and effect analysis, identify and define the product structure, clarify the interface design of each subsystem, component and part; in the process failure mode and effect analysis, identify the key steps in the manufacturing and assembly process to ensure the stability of process input and output. This can help to fully understand the structure and function of the product, so as to conduct failure analysis more effectively.

[0081] The purpose of functional analysis is to identify the functions and requirements of a product or process and ensure that each function is fully considered in subsequent steps. Specifically, the method of functional analysis is: in the design failure mode and effect analysis, define the functions and characteristics of the product to ensure that the design can meet the expected performance and reliability requirements; in the process failure mode and effect analysis, identify the key functions in the process to ensure that each step can achieve its expected function and avoid failures caused by process variation.

[0082] Step 3: Failure Analysis Phase

[0083] Input design plans, design standards, two-dimensional models and existing failure case information, use graph knowledge reuse components to process the input data and retrieve relevant information from the full-cycle knowledge base, and then process and construct the knowledge graph through the industrial knowledge software system; the large model retrieval enhancement method based on the knowledge graph deeply analyzes the input information, and combines the large model prompt learning method to extract relevant information from the knowledge graph to generate failure analysis results including failure impact, failure mode and failure cause.

[0084] Failure analysis is the core step of FMEA, which provides a basis for subsequent risk assessment and optimization by identifying potential failure modes, failure effects and failure causes. In this embodiment, the method steps of failure analysis are:

[0085] 31) Identify possible failure modes of products or processes, such as fracture, wear, corrosion, etc.;

[0086] 32) Evaluate the potential impact of each failure mode on the system, subsystem, component and user;

[0087] 33) Analyze potential causes of failure modes, such as design defects, material problems, improper manufacturing processes, etc.

[0088] The failure analysis step helps to fully understand the potential failure risks and their root causes.

[0089] Step 4: Risk Analysis and Optimization Phase

[0090] Evaluate the severity, frequency of occurrence and difficulty of detection of each failure mode, calculate the risk priority number, and determine the issues that need to be addressed first; propose and implement improvement measures including design improvements, process adjustments and increased detection methods to reduce or eliminate high-risk failure modes.

[0091] In the risk analysis phase, by evaluating the severity, frequency of occurrence and difficulty of detection of each failure mode, the risk priority number (RPN) is calculated and the issues that need to be addressed first are determined. Specifically, in this embodiment, the steps of the risk analysis method are as follows:

[0092] 41) Identify and develop preventive measures to reduce the probability of failure;

[0093] 42) Identify and implement detection measures to improve detection capabilities after failures occur;

[0094] 43) Score the severity S, frequency of occurrence O and detection difficulty D of each failure mode, and re-evaluate the risk priority number based on the implemented prevention and detection measures to ensure that the risks are effectively controlled.

[0095] The purpose of the optimization phase is to propose and implement improvement measures to reduce or eliminate high-risk failure modes. Specifically, the risk optimization method steps are:

[0096] 44) Identify and record high-risk failure modes that require improvement;

[0097] 45) Propose specific optimization measures including design improvement, material replacement and process adjustment;

[0098] 46) Implement optimization measures and verify their effectiveness;

[0099] 47) Score and evaluate optimization measures to ensure they significantly reduce risk priority numbers.

[0100] The optimization phase helps to continuously improve the reliability and safety of the product or process.

[0101] Step 5: Result documentation and system integration phase

[0102] The analysis results including failure modes, failure effects, failure causes, risk assessment and optimization measures are documented and stored in the FMEA knowledge base. By integrating with the data center, bill of materials BOM system and product lifecycle management PLM system, a full-cycle knowledge base is formed, and the full-cycle knowledge base is continuously updated and optimized throughout the product life cycle.

[0103] The purpose of result documentation is to document all the results and conclusions of FMEA analysis and store them in the FMEA knowledge base. By integrating with the data center, bill of materials (BOM) system and product lifecycle management (PLM) system, comprehensive information sharing and utilization can be achieved. Record the detailed information of FMEA analysis, including failure mode, failure effect, failure cause, risk assessment, optimization measures, etc. Develop a control plan for the product or process to ensure that each link is effectively controlled. Incorporate the results of FMEA analysis into the knowledge base to form a full-cycle knowledge base to ensure its continuous updating and optimization throughout the product life cycle.

[0104] Regarding the failure analysis stage, the large model retrieval enhancement method based on knowledge graph, the large model prompt learning method and the industrial knowledge software method are explained below.

[0105] (1) Large model retrieval enhancement method based on knowledge graph

[0106] The large model retrieval enhancement based on the knowledge graph is an intelligent knowledge retrieval method that combines a large-scale pre-trained language model and knowledge graph technology. The knowledge graph is a structured knowledge base that represents knowledge units and their relationships in the form of nodes and edges. The large model has powerful natural language processing and understanding capabilities, and can learn and extract knowledge from large amounts of data. By combining the knowledge graph with the large model, enhancements in rich semantic understanding, fast information retrieval, dynamic knowledge expansion, and deep knowledge association can be achieved. The large model retrieval enhancement method based on the knowledge graph achieves efficient knowledge retrieval and failure analysis by combining the powerful natural language processing capabilities of the large-scale pre-trained language model and the structured knowledge base of the knowledge graph. Specifically, in this embodiment, the large model retrieval enhancement method based on the knowledge graph is: starting from the design plan and standards, a problem combination representation is generated, and it is passed to the large model through Prompt for knowledge retrieval; the large model extracts relevant knowledge from the knowledge graph through in-depth analysis of the prompts, and generates failure analysis results, including failure impacts, modes, and causes. This method can quickly and accurately provide rich semantic understanding and information retrieval, improve the efficiency and reliability of engineering design and problem solving, such as Figure 4 shown.

[0107] (2) Large model prompts learning method

[0108] Hint learning is a contextual learning strategy designed for knowledge graph completion tasks. It significantly improves the performance of large models (LLM) on knowledge reasoning tasks by encoding parts of the knowledge graph as examples. In this process, knowledge hints use analogy pools (Da) and supplementary pools (Ds) to build examples for each query (h, r, ?), thereby providing richer and more relevant context information, such as Figure 5 shown.

[0109] The analogy pool Da contains triplets with the same relationship as the query, which help LLM better understand the semantics of the query through analogy. In order to ensure the diversity of examples and allow LLM to learn from various analogy examples, the triplets in the analogy pool Da are selected through a sorting strategy that promotes diversity. Specifically, a zero counter is set for each entity, a triple in Da is randomly selected as an example, and the counter of its related entity is increased by 1. Subsequently, the triple with the smallest counter value of its related entity is iteratively selected as an example, and its counter value is increased accordingly. This process is repeated until all triplets in Da are used up, and the final list of examples is recorded as La.

[0110] The supplementary pool Ds provides supplementary information about the query head entity h, focusing on selecting examples relevant to the query. Specifically, all triples in Ds are ranked by the BM25 score, which is used to evaluate the textual relevance between each example and the query. The sorted list is denoted as Ls, which contains all triples in Ds. Queries with specific relations or head entities use shared analogies or supplementary pools. To prevent duplicate calculations, these example pools are created and sorted during the data preprocessing stage. During reasoning, the corresponding example pool is used based on the query.

[0111] In practice, a unified prompt template is used to convert queries and examples into plain text with the same format, and multiple rounds of interaction are used to guide the large model to re-rank. In this process, the large model summarizes natural text descriptions from given examples using the original descriptions, generates easy-to-understand prompt templates, and achieves text self-alignment. At this point, the large model processes the questions, ranks candidate answers by rationality, and checks feedback to ensure that its task understanding is accurate.

[0112] Specifically, in this embodiment, the big model prompts the learning method as follows: input a question (corresponding to the query text), and then provide a batch of examples from the analogy pool and the supplementary pool to the big model; repeat this step until the input sequence length limit is reached; restate the query text, and input the original triple sequence, and use the big model to re-rank the top candidate entities in the original triple sequence; parse the answer given by the big model into an ordered list, and replace the first few entities in the original triple sequence as the final answer, thereby completing the knowledge reasoning task.

[0113] This large-model-based hint learning approach greatly enhances the performance of large models in complex knowledge reasoning tasks by making full use of analogies and supplementary information in knowledge graphs.

[0114] (3) Industrial knowledge software method

[0115] The industrial knowledge software system uses industrial knowledge software methods to process data. Specifically, Figure 6 As shown, the method of industrial knowledge softwareization includes the following steps.

[0116] S1: Obtain the sources and needs of multimodal industrial data throughout the product life cycle, and perform cluster analysis on multimodal industrial data.

[0117] Specifically, in this embodiment, the method steps for clustering analysis of multimodal industrial data are as follows:

[0118] S11) Analyze the sources of multimodal industrial data, knowledge carriers and application requirements, perform data cleaning, relationship definition, combination induction and integration processing on multimodal industrial knowledge sources, build a full-cycle multimodal industrial database, and realize abnormal data cleaning and multi-source heterogeneous data integration of multimodal industrial knowledge sources.

[0119] S12) Based on the multimodal industrial data types and the adapted similarity metrics, combined with the full-cycle multimodal industrial knowledge software requirements, a bottom-up agglomerative multimodal clustering algorithm is selected.

[0120] S13) Initialize the multimodal industrial data, regard each data point as an independent cluster, and globally measure the distance or similarity matrix between all clusters.

[0121] S14) judging whether the distance or similarity between adjacent clusters meets the inter-cluster merging condition: if so, executing step 15); if not, the inter-cluster merging is terminated, a clustering hierarchy is constructed, and executing step 16).

[0122] In this embodiment, the inter-cluster merging condition is less than or equal to a preset distance threshold or similarity threshold. In this embodiment, the distance is used to judge whether the adjacent clusters meet the inter-cluster merging condition, and the distance includes the nearest neighbor distance (single chain method), the farthest neighbor distance (full chain method) and the average distance (average chain method).

[0123] S15) Select two clusters with the smallest distance or the smallest similarity to merge, and update the distance or similarity matrix between clusters to reflect the relationship between the newly formed cluster and other clusters; and execute step 14) repeatedly.

[0124] S16) Using a dendrogram to represent the hierarchical clustering results of full-cycle multimodal industrial data, it is used to enhance the understanding of the gradual aggregation process of the data and the hierarchical structure of the clusters.

[0125] S2: Based on the clustering results of multimodal industrial data, the existing ontologies and standards are reused and mapped to build a hierarchical multimodal industrial knowledge ontology system.

[0126] In this embodiment, the product life cycle multimodal industrial knowledge ontology system is based on the hierarchical clustering results. The specific ontology system construction process is as follows: Figure 7 As shown. The ontology system construction method of this embodiment is an improved seven-step method, which is an improvement based on the Stanford seven-step method. Specifically, in this embodiment, the method steps for constructing a hierarchical multimodal industrial knowledge ontology system are:

[0127] S21) It is clear that the ontology domain is the industrial domain, and the purpose of ontology application is to provide top-level guidance for the mining and softwareization of industrial knowledge.

[0128] S22) Check whether there are reusable concepts, mainly involving existing ontologies and standards: if there are reusable ontologies, modify the reusable ontology; for reusable standards, map the required content to the standard ontology based on the needs of industrial knowledge software.

[0129] S23) Domain experts evaluate the reusable ontologies and standard ontologies based on the evaluation criteria, and introduce the reusable ontologies and standard ontologies that meet the requirements into the reusable ontology library. For ontologies that do not meet the requirements, they are revised or mapped again until they meet the requirements or are eliminated.

[0130] S24) Match the concepts in the reused ontology library with the full-cycle multimodal industrial data clustering results. For the clustering results and related concepts without reused ontology, determine the important terms of the industrial knowledge ontology system with the guidance of domain experts.

[0131] S25) According to the hierarchical clustering result, a hierarchical structure of the ontology class is defined, and the ontology hierarchy is evaluated.

[0132] S26) Determine the ontology attributes and their properties, and perform detailed definition and facet processing on the attributes.

[0133] S27) Build a bridging ontology to integrate ontologies of different levels, modes, and types into a multimodal industrial knowledge ontology system for the entire product life cycle.

[0134] like Figure 8 As shown, in this embodiment, the multimodal industrial knowledge ontology system of the product's entire life cycle is a hierarchical ontology system, which is divided into three layers, among which: the top layer includes the broadest and most abstract industrial concepts, such as "productivity", "automation", "sustainable development", etc., involving the core concepts and universal principles of the entire industrial field; the second layer is close to the actual industrial scene, but still maintains a certain degree of abstraction, including specific production processes, industrial machine types, production efficiency and other concepts; the bottom layer is aimed at specific industrial application scenarios, including the operating details of specific machines, specific maintenance guidelines, troubleshooting procedures, etc.

[0135] S28) Create an instance according to the defined ontology and attributes.

[0136] S3: Under the guidance of the multimodal industrial knowledge ontology system, multimodal industrial data is converted into textual modality using text as a modal bridge; multimodal industrial data knowledge mining is realized using textual knowledge mining methods to form triple clusters of industrial knowledge in each modality.

[0137] like Fig. 9 As shown, in this embodiment, the method steps of using the text knowledge mining method to perform multimodal industrial data knowledge mining are as follows:

[0138] S31) In view of the problem that industrial data of the entire product life cycle has multiple presentation modes, types, and carriers, and knowledge mining methods of different modal data are difficult to standardize, explore the natural language description method of multimodal industrial data, and establish an industrial knowledge mining framework for modal feature-natural language description consistency generation. Specifically, the industrial knowledge mining framework for modal feature-natural language description consistency generation constructed in this embodiment is mainly aimed at the five common modalities in industrial sites, namely text, image, graphic, signal, and formula, but the idea of ​​the mining framework can be extended to other modal data.

[0139] S32) using the industrial knowledge mining framework generated by modal feature-natural language description consistency to convert non-text modal data into text form or graph form, and realizing multimodal knowledge mining through text extraction method, including:

[0140] For text modality: First, the PL-Marker strategy is used to encode text sentences or paragraphs, and then Albert is used for embedding representation. Finally, a hypergraph is used to model the embedded representation, and a hypergraph neural network is constructed to extract text modality knowledge and form a text modality triple group.

[0141] Note: There are various methods for text modality extraction. This embodiment is only an example. In this framework, the text modality knowledge extraction method is the most basic method and is applied to other modalities.

[0142] For image modality: select several multi-image description models, perform image description tasks on the same image, obtain multiple image description texts, embed and represent the description texts and images, perform feature recognition, and sort the description text quality. The top-k description texts are combined and prompted into the large language model to generate a fused image description. Use text modality knowledge extraction methods to extract image modality industrial knowledge and form image modality triple groups.

[0143] For graphic modality: first convert all 3D models into standard formats such as OBJ or STEP, then introduce the PCL library to perform point cloud processing on the 3D model to obtain the 3D point cloud of the model; then use 3D object detectors such as Pointnet++ to obtain point cloud related features, and generate point cloud description text based on multi-head cross attention; use text modality knowledge extraction method to realize graphic modality industrial knowledge extraction and form graphic modality triple group.

[0144] For signal modality: first, store the signal data in standard databases such as csv, then call time-frequency domain statistical methods and signal processing methods such as Fourier transform and wavelet transform to process the signal, and extract the typical time-frequency domain features of the signal; under the guidance of prior knowledge such as sensors, construct signal-text association rules; use text modality knowledge extraction methods to realize signal modality industrial knowledge extraction and form signal modality triple groups.

[0145] Regarding expression modality: according to the different forms of expressions, it is divided into unstructured expression data and semi-structured expression data; among them, unstructured mainly refers to data in the form of pictures, and semi-structured refers to data in the form of expressions such as latex and XML. Specifically, for semi-structured expression data, the discretized information is directly extracted and a graph structure is formed; for unstructured expression data, the expression in the picture is first identified through OCR, then discretized, and the scene graph of discrete elements is constructed with human participation, and finally an expression modality triple group is formed.

[0146] Note: All text knowledge extraction is carried out under the guidance of the ontology system, and the parts that require human participation are also operated in accordance with the system specified by the ontology.

[0147] S4: Globally encode the triplet clusters of industrial knowledge in each modality, and perform modal fusion and cross-modal alignment to achieve cross-modal industrial knowledge fusion and form a multimodal industrial knowledge graph for the entire product life cycle.

[0148] After the multimodal industrial data is processed by the industrial knowledge mining framework generated by multimodal features and natural language description, each modality forms its own modal triple group. In order to better realize the complementarity of each modality's industrial knowledge, cross-modal industrial knowledge fusion is required. Fig.10As shown. In this embodiment, the method for forming a multimodal industrial knowledge graph for the entire life cycle of a product is as follows: according to the association relationship of the modal triple group, the modal original data features are introduced, and the modal triple group graph features such as the graph topology information, relationship information and attribute information of each triple cluster are combined and globally encoded, and weights are assigned to each part of the features through dynamic cross-modal weighting, and then modal fusion and cross-modal alignment operations are performed to achieve cross-modal knowledge fusion and form a multimodal industrial knowledge graph for the entire life cycle of the product. The multimodal industrial knowledge graph for the entire life cycle of a product takes the URI number as the core node, and loads text attribute descriptions (i.e., each modal triple cluster information), modal attribute descriptions (i.e., the number of modalities involved under the node and related information), standardized data attributes (i.e., the standardized data that can represent the node, and non-text data can be represented by URL mounting) and feature attributes (i.e., abstract features extracted by various algorithm models in the mining framework).

[0149] S5: Using the multimodal industrial knowledge graph of the entire product life cycle as the foundation for knowledge reuse, it supports the personalized configuration and development of industrial software for ubiquitous deployment of multi-scenario intelligent business, and realizes the software-based standard process of industrial knowledge acquisition, mining, and reuse.

[0150] like Fig.11 As shown, this embodiment also proposes a large model retrieval-enhanced design failure mode and effect analysis system based on knowledge graph, including a data acquisition system, a design failure mode and effect analysis system and a user interaction system. Specifically, the data acquisition system is used to acquire data and includes a data center, a bill of materials BOM system and a product lifecycle management PLM system. After the design failure mode and effect analysis system obtains the failure analysis results by using the design failure mode and effect analysis method enhanced by knowledge graph and large model retrieval as described in this embodiment, it performs risk analysis and optimization on the failure analysis results, and finally documents the analysis results and stores them in the FMEA knowledge base. The user interaction system is used to display the analysis results to the user.

[0151] The above-described embodiments are only preferred embodiments for fully illustrating the present invention, and the protection scope of the present invention is not limited thereto. Equivalent substitutions or changes made by those skilled in the art based on the present invention are within the protection scope of the present invention. The protection scope of the present invention shall be subject to the claims.

Claims

1. A design failure mode and effect analysis method based on knowledge graph and large model retrieval enhancement, characterized by: The steps include: Step 1: Planning and preparation phase Carry out planning and preparation, clarify analysis objectives, and form a multidisciplinary team; Step 2: Structural and functional analysis phase Conduct structural analysis of the product, identify the functions of each subsystem, assembly and component and their interrelationships, and fully understand the design intent of the product and the interaction of each part; Step 3: Failure Analysis Phase Input design schemes, design standards, two-dimensional models and existing failure case information, use graph knowledge reuse components to process the input data and retrieve relevant information from the full-cycle knowledge base, and then process and construct the knowledge graph through the industrial knowledge software system; The large model retrieval enhancement method based on the knowledge graph deeply analyzes the input information, and extracts relevant information from the knowledge graph in combination with the large model prompt learning method to generate failure analysis results including failure effects, failure modes and failure causes; Step 4: Risk Analysis and Optimization Phase Assess the severity, frequency and detection difficulty of each failure mode, calculate the risk priority number, and determine the issues that need to be addressed first; Propose and implement improvement measures including design improvement, process adjustment and additional testing methods to reduce or eliminate high-risk failure modes; Step 5: Results documentation and system integration phase The analysis results including failure modes, failure effects, failure causes, risk assessment and optimization measures are documented and stored in the FMEA knowledge base. By integrating with the data center, bill of materials BOM system and product lifecycle management PLM system, a full-cycle knowledge base is formed, and the full-cycle knowledge base is continuously updated and optimized throughout the product life cycle.

2. According to claim 1, the design failure mode and effect analysis method based on knowledge graph and large model retrieval enhancement is characterized by: In step 1, the planning and preparation steps are as follows: 11) Clarify the objectives and scope of FMEA analysis and ensure that the basic information of the project is complete; 12) Establish a multidisciplinary team including design, manufacturing, quality and service to ensure the comprehensiveness and professionalism of FMEA analysis; 13) Develop a detailed project plan to clarify the time schedule, resource allocation and responsible persons for each task to ensure that the FMEA analysis is carried out as planned.

3. The design failure mode and effect analysis method based on knowledge graph and large model retrieval enhancement according to claim 1, characterized in that: In the step 2, the method of structural analysis is: In the design failure mode and effect analysis, identify and define the product structure and clarify the interface design of each subsystem, component and part; In process failure mode and effects analysis, critical steps in the manufacturing and assembly process are identified to ensure the stability of process inputs and outputs.

4. The design failure mode and effect analysis method based on knowledge graph and large model retrieval enhancement according to claim 3 is characterized by: In the step 2, the method of functional analysis is: In the design failure mode and effect analysis, define the functions and characteristics of the product to ensure that the design can meet the expected performance and reliability requirements; In process failure mode and effect analysis, key functions in the process are identified to ensure that each step can achieve its intended function and avoid failures caused by process variation.

5. According to claim 1, the design failure mode and effect analysis method based on knowledge graph and large model retrieval enhancement is characterized by: In step 3, the method steps of failure analysis are: 31) Identify possible failure modes of products or processes; 32) Evaluate the potential impact of each failure mode on the system, subsystem, component and user; 33) Analyze potential causes that lead to failure modes.

6. The design failure mode and effect analysis method based on knowledge graph and large model retrieval enhancement according to claim 1 is characterized by: In step 4, the risk analysis method steps are: 41) Identify and develop preventive measures to reduce the probability of failure; 42) Identify and implement detection measures to improve detection capabilities after failures occur; 43) Score the severity S, frequency of occurrence O and detection difficulty D of each failure mode, and re-evaluate the risk priority number based on the implemented prevention and detection measures to ensure that the risks are effectively controlled.

7. The design failure mode and effect analysis method based on knowledge graph and large model retrieval enhancement according to claim 6 is characterized by: In step 4, the risk optimization method steps are: 44) Identify and record high-risk failure modes that require improvement; 45) Propose specific optimization measures including design improvement, material replacement and process adjustment; 46) Implement optimization measures and verify their effectiveness; 47) Score and evaluate optimization measures to ensure they significantly reduce risk priority numbers.

8. The design failure mode and effect analysis method based on knowledge graph and large model retrieval enhancement according to claim 1 is characterized by: In the step 3, the large model retrieval enhancement method based on the knowledge graph is: starting from the design plan and standards, generating a combination representation of the question, and passing it to the large model through Prompt for knowledge retrieval; The large model conducts in-depth analysis of the prompts, extracts relevant knowledge from the knowledge graph, and generates failure analysis results.

9. The design failure mode and effect analysis method based on knowledge graph and large model retrieval enhancement according to claim 1, characterized in that: In step 3, the large model prompts the learning method as follows: Input the question, and then provide a batch of examples from the analog pool and the supplementary pool to the large model; repeat this step until the input sequence length limit is reached; Restate the query text and input the original triple sequence, and use the large model to re-rank the top candidate entities in the original triple sequence; Parse the answer given by the large model into an ordered list and replace the first few entities in the original triple sequence as the final answer, thereby completing the knowledge reasoning task.

10. A large model retrieval enhanced design failure mode and effect analysis system based on knowledge graph, characterized by: Including data acquisition system, design failure mode and effect analysis system and user interaction system; The data acquisition system is used to acquire data and includes a data center, a bill of materials BOM system and a product lifecycle management PLM system; The design failure mode and effect analysis system obtains failure analysis results by using the design failure mode and effect analysis method based on knowledge graph and large model retrieval enhancement as described in any one of claims 1 to 9, performs risk analysis and optimization on the failure analysis results, and finally documents and stores the analysis results in the FMEA knowledge base; The user interaction system is used to display the analysis results to the user.

Citation Information

Patent Citations

  • Failure model effectiveness analysis knowledge management system and method

    CN101697218A

  • Fault diagnosis method based on knowledge graph technology

    CN113360679A

  • Bridge management and cultivation question-answering method based on cooperation of large model and knowledge graph

    CN118410145A

  • Automated data exploration and validation

    US20180203857A1

Cited By

  • Tumor knowledge base construction system and method based on large model and cue word optimization

    CN119168040A

  • Aviation airborne software supply chain security risk detection system and method

    CN119862584A

  • A security risk detection system and method for airborne software supply chain

    CN119862584B

  • Failure propagation link-oriented intelligent FMECA risk analysis method

    CN122334059A

  • An intelligent fmeca risk analysis method for failure propagation link

    CN122334059B