Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.00129 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909760875397120 |
|---|---|
| author | Ntagengerwa, Manzi Aimé Caltais, Georgiana Stoelinga, Mariëlle |
| author_facet | Ntagengerwa, Manzi Aimé Caltais, Georgiana Stoelinga, Mariëlle |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_00129 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fault Tree Synthesis from Knowledge Graphs Ntagengerwa, Manzi Aimé Caltais, Georgiana Stoelinga, Mariëlle Other Computer Science 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. |
| title | Fault Tree Synthesis from Knowledge Graphs |
| topic | Other Computer Science |
| url | https://arxiv.org/abs/2509.00129 |