2026-08-07T20:31:57Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:22107 2024-11-26T15:16:36Z ddc:004 open_access

Property Learning-Based Fault Detection for Liquid Propellant Rocket Engine Control Systems Urgolo, Andrea Pill, Ingo Waxenegger-Wilfing, Günther Freiberger, Manuel Machine learning Runtime verification Property learning Monitoring Fault detection Diagnosis Genetic programming Explainable AI Accommodating the dynamic and uncertain operational environments that are typical for aerospace applications, our work focuses on robust fault detection and accurate diagnosis in the context of Liquid Propellant Rocket Engines. To this end, we employ techniques based on learning temporal properties which are then dynamically adapted and refined based on observed behavior. Leveraging the capabilities of genetic programming, our methodology evolves and optimizes temporal properties that are validated through formal methods in order to ensure precise, interpretable real-time fault monitoring and diagnosis. Our integrated strategy enables us to enhance resilience, safety and reliability when operating rocket engines - due to the proactive detection and systematic analysis of operational deviations before they would escalate into critical failures. We demonstrate the effectiveness of our method via a rigorous evaluation across varied simulated fault conditions, in order to showcase its potential to significantly mitigate the fault-related risks in aerospace systems. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Andrea Urgolo and Ingo Pill and Günther Waxenegger-Wilfing and Manuel Freiberger 2024 Is Part Of OASIcs, Volume 125, 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/OASIcs.DX.2024.15 urn:nbn:de:0030-drops-221074 https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.15 eng https://creativecommons.org/licenses/by/4.0/legalcode