Fault Tree Synthesis from Knowledge Graphs

2025-08-29

AI Summary

In complex equipment fault diagnosis, domain expertise is difficult to formalize, and manual fault tree construction is inefficient. Method: This paper proposes a knowledge graph–based approach for automated fault tree synthesis. It introduces a lightweight, semantically rich knowledge graph representation that enables semi-automatic extraction of failure logic relationships from unstructured documents (e.g., maintenance manuals) and structured/functional models. Leveraging hierarchical modeling and semantic reasoning, the method generates fault trees in a fully structured manner—without requiring historical fault data, relying solely on engineering knowledge. Contribution/Results: The synthesized fault trees are inherently interpretable and accurately capture system-level failure propagation paths. Experimental validation on the Lycoming O-320 aircraft engine demonstrates substantial improvements in diagnostic modeling efficiency and engineering applicability.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Reasoning under Uncertainty: Graphical Models
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

A truly effective diagnostic system provides system engineers with valuable insights into the behavior of their machines, leveraging a rich body of (often tacit) expertise. Much of this expertise typically resides in written documentation or troubleshooting manuals, which are frequently imprecise or vaguely specified. Therefore, methods for formalizing this knowledge, such as through the use of knowledge graphs, are of particular interest. However, ensuring that the extracted knowledge (ideally in a semi-automatic way) encapsulates sufficient semantic depth for system-level diagnostics is a challenging task. In this paper, we propose a minimal format for knowledge graphs that is semantically rich enough to facilitate the synthesis of meaningful fault trees. Fault trees offer an intuitive and efficient means for systematic failure analysis, enabling engineers to assess all potential failure modes in a structured, hierarchical manner. The methodology is applied to the Lycoming O-320 engine, showing that meaningful fault trees can be synthesized from only structural and functional knowledge of the system, defined by the proposed conceptual model.

Problem

• Formalizing imprecise diagnostic knowledge from documentation
• Ensuring semantic depth for system-level fault analysis
• Synthesizing fault trees from structural and functional knowledge

Innovation

• Knowledge graph format for fault trees
• Synthesizing fault trees from system knowledge
• Structural and functional knowledge conceptual model