Safety-critical electronic systems must meet high requirements for reliability and availability. Predictive maintenance strategies help avoiding unforeseen failures and ensuring high reliability over the entire lifetime. Data-driven methods allow simultaneous condition monitoring of decentralized systems with numerous units.
This requires the detection of failure precursors in historical data sets and their evaluation regarding the systems condition. This project aims at identifying types of failure precursors relevant for condition monitoring of electronic systems and making those precursors detectable by integrating expert knowledge and hardware tests into machine learning algorithms.
The project is a cooperation with the European Organization for Nuclear Research (CERN).
This project is sponsored by the Wolfgang Gentner Programme of the German Federal Ministry of Education and Research (grant no. 13E18CHA).
Publications
- Waldhauser, Felix ; Boukabache, Hamza ; Perrin, Daniel ; Dazer, Martin: Wavelet-based Noise Extraction for Anomaly Detection Applied to Safety-Critical Electronics at CERN. In: Proceedings of the 32nd European Safety and Reliability Conference (ESREL 2022), 2022. — ISBN 978-981-18-5183-4 — IMA-ZUV 401 (peer-review)
- Waldhauser, Felix ; Dazer, Martin ; Bertsche, Bernd: Strahlenschutz am CERN: Wie können Ausfälle hochsensibler elektronischer Systeme aus der Ferne sicher vorhergesagt werden? In: WiGeP-News Dezember 2022. (2022), Nr. 2, S. 18–19 — IMA-ZUV 407
Contact
Felix Waldhauser
M. Sc.PhD Student