Knowledge Graph Decision Support for Machinery Fault Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern machinery control systems face challenges in situational awareness and decision-making due to anomalous circumstances, requiring advanced diagnostic and prognostic tools to improve operational efficiency and accuracy.
Innovation Solution
A knowledge graph-based decision support system that extracts entities and relations from various data sources, constructs a knowledge graph, predicts missing links, and performs diagnostic and prognostic analysis using machine learning and data analytics to enhance situational awareness and support decision-making in machinery control operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If advanced machinery control systems with state-of-the-art sensors are deployed to monitor vital components, then measurement precision and reliability are improved, but device complexity increases and difficulty of detecting and measuring anomalous circumstances worsens
Solution Approach 1:
The patent introduces a knowledge graph as an intermediary layer between sensor data and decision-making processes. The knowledge graph stores pre-defined relationships, diagnostic rules, and domain knowledge that mediate the complex interaction between multiple sensor inputs and anomaly detection, making the system more interpretable and easier to diagnose without reducing measurement precision
Solution Approach 2:
The system performs self-diagnosis by automatically querying the knowledge graph with current sensor observations to identify anomalies and their causes. The knowledge graph enables the system to self-service diagnostic tasks by matching observed symptoms with pre-stored knowledge patterns, reducing the complexity of anomaly detection without requiring additional external diagnostic tools
2Reliability
If more sensors and automated monitoring functions are added to improve situational awareness, then reliability is improved, but device complexity and loss of information increase
Solution Approach 1:
The patent merges multiple data sources including sensor observations, maintenance records, operational parameters, and external knowledge into a unified knowledge graph structure. This consolidation integrates disparate information streams into a single coherent system, improving reliability through comprehensive data fusion while managing complexity through unified data representation rather than separate processing systems
Solution Approach 2:
The knowledge graph serves multiple functions simultaneously: it stores domain knowledge, performs diagnostic reasoning, generates maintenance recommendations, and supports decision-making. This multi-functionality allows a single knowledge graph component to replace what would otherwise require multiple separate systems, improving reliability through comprehensive coverage while reducing overall device complexity
3Measurement precision
If comprehensive data collection from multiple information sources is performed to improve diagnostic accuracy, then measurement precision is improved, but loss of time for data processing increases
Solution Approach 1:
The system performs preliminary actions by pre-populating the knowledge graph with domain knowledge, diagnostic rules, and relationships before actual diagnostic tasks. When anomalies occur, the system queries this pre-prepared knowledge structure rather than processing raw data from scratch, significantly reducing processing time while maintaining high diagnostic accuracy through the use of pre-validated knowledge patterns
Data Source
AI summary
A decision support method for machinery control includes extracting entities and relations from information sources, and creating subject-predicate-object (SPO) triples. Each SPO triple includes a subject entity and an object entity, and a relation between the subject entity and the object entity. The method further includes constructing a knowledge graph (KG) based on the SPO triples. The KG includes a plurality of nodes corresponding to the entities, and a plurality of links corresponding to the relations between the entities. The method also includes predicting missing links between the nodes and adding the predicted links to the KG, and performing diagnostic and prognostic analysis using the KG, including analyzing plain text description of MCS situations to obtain relevant information concerning key components from the KG, recognizing sensor observations and component conditions to diagnose situations of other related components, and providing prognostics by analyzing the present trending/symptom in the MCS operating process.