Knowledge Graph Fault Root Cause Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional product fault root cause analysis in manufacturing relies heavily on expert experience and data from the production side, which is insufficient in identifying comprehensive fault causes due to the complexity of fault nodes and generation paths.
Innovation Solution
A method and device for product fault root cause analysis using knowledge graphs that acquire and integrate entities, relationships, and attributes from multi-source heterogeneous data, including design and production data, to construct a comprehensive knowledge graph for inferential analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If knowledge graphs are built based only on production side data, then the construction process is simple, but the fault root cause analysis is incomplete
Solution Approach 1:
The patent merges production side data (structured) with design side data (semi-structured and unstructured) to construct a comprehensive knowledge graph. This combination allows the system to maintain relatively simple construction processes while achieving complete fault root cause analysis by integrating multiple data sources that complement each other.
Solution Approach 2:
The knowledge graph is designed to handle multiple types of data (structured, semi-structured, and unstructured) from different sources (production and design). This multi-functional capability enables the system to process diverse data formats uniformly, achieving both construction simplicity and analysis completeness.
2Ease of operation
If manual expert experience methods are used for fault analysis, then the analysis process is simple, but the analysis depth and efficiency are insufficient
Solution Approach 1:
The patent replaces manual expert experience-based analysis with an automated knowledge graph system. The system automatically extracts entities, relationships, and attributes from multi-source data, constructs the knowledge graph, and performs fault root cause analysis without manual intervention, thereby dramatically improving efficiency while maintaining ease of operation through automated workflows.
Solution Approach 2:
The knowledge graph system performs self-service by automatically acquiring data from multiple sources, extracting relevant information, constructing the graph structure, and conducting fault analysis without requiring continuous expert intervention. This automation maintains operational simplicity while achieving high productivity.
3Loss of information
If knowledge graphs integrate multi-source heterogeneous data, then the fault analysis comprehensiveness is improved, but the data processing complexity increases
Solution Approach 1:
The patent segments the complex data processing task into distinct stages: data acquisition from multiple sources, information extraction from semi-structured and unstructured data, knowledge graph construction, and fault analysis. This segmentation manages complexity by breaking down the overall process into manageable, modular steps while achieving comprehensive fault analysis.
Solution Approach 2:
The knowledge graph serves as an intermediary structure that integrates multi-source heterogeneous data. By using the knowledge graph as a mediating layer, the system can process diverse data formats (structured, semi-structured, unstructured) from different sources without direct complex interactions between them, thereby improving comprehensiveness while managing processing complexity.
Data Source
AI summary
A method for product fault root cause analysis based on knowledge graphs includes (i) acquiring product-associated design data, wherein the design data comprises semi-structured data and/or unstructured data, (ii) acquiring product-associated production data, wherein the production data comprises structured data, (iii) performing information extraction on the design data to acquire structured design data, (iv) performing a knowledge fusion of knowledge generated separately based on the production data and the structured design data to construct a target knowledge graph, and (v) and performing product fault root cause analysis tasks based on the target knowledge graph.