2026-09-28T11:51:12Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:27833 2026-09-28T06:35:13Z ddc:004 open_access

Uncertainty-Aware Fault Diagnosis of Unknown Faults Using Ensemble-Based NODE Residuals (Extended Abstract) Jung, Daniel Westny, Theodor Data-driven diagnosis model-based diagnosis structural methods neural ordinary differential equations ensemble models This extended abstract presents an uncertainty-aware approach to data-driven fault diagnosis using ensembles of neural ordinary differential equations (NODE). The proposed method leverages physical insights in the design of NODE models for residual generation and employs bootstrap ensembles to quantify prediction uncertainty and adapt detection thresholds. The adaptive thresholds enable robust detection and isolation of faults in scenarios with limited training data and reduces the risk of false alarms due to out-of-distribution data. The methodology is validated on real-world data from the LiU-ICE benchmark, providing insights into how training data quality and residual design impact uncertainty-aware fault diagnosis. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Daniel Jung and Theodor Westny 2026 Is Part Of OASIcs, Volume 148, 37th International Conference on Principles of Diagnosis and Resilient Systems (DX 2026) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/OASIcs.DX.2026.19 urn:nbn:de:0030-drops-278334 https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2026.19 eng https://creativecommons.org/licenses/by/4.0/legalcode