Skip to Main content Skip to Navigation
New interface
Conference papers

Explainable Deep Learning for Fault Prognostics in Complex Systems: A Particle Accelerator Use-Case

Lukas Felsberger 1, 2 Andrea Apollonio 3 Thomas Cartier-Michaud 3 Andreas Müller 4 Benjamin Todd 3 Dieter Kranzlmüller 1 
1 MNM-Team - Munich Network Management Team
TUM - Technische Universität Munchen - Université Technique de Munich [Munich, Allemagne], LMU - Ludwig-Maximilians-Universität München
Abstract : Sophisticated infrastructures often exhibit misbehaviour and failures resulting from complex interactions of their constituent subsystems. Such infrastructures use alarms, event and fault information, which is recorded to help diagnose and repair failure conditions by operations experts. This data can be analysed using explainable artificial intelligence to attempt to reveal precursors and eventual root causes. The proposed method is first applied to synthetic data in order to prove functionality. With synthetic data the framework makes extremely precise predictions and root causes can be identified correctly. Subsequently, the method is applied to real data from a complex particle accelerator system. In the real data setting, deep learning models produce accurate predictive models from less than ten error examples when precursors are captured. The approach described herein is a potentially valuable tool for operations experts to identify precursors in complex infrastructures.
Complete list of metadata

https://hal.inria.fr/hal-03414728
Contributor : Hal Ifip Connect in order to contact the contributor
Submitted on : Thursday, November 4, 2021 - 3:57:14 PM
Last modification on : Thursday, October 13, 2022 - 5:22:09 PM
Long-term archiving on: : Saturday, February 5, 2022 - 7:07:47 PM

File

 Restricted access
To satisfy the distribution rights of the publisher, the document is embargoed until : 2023-01-01

Please log in to resquest access to the document

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Lukas Felsberger, Andrea Apollonio, Thomas Cartier-Michaud, Andreas Müller, Benjamin Todd, et al.. Explainable Deep Learning for Fault Prognostics in Complex Systems: A Particle Accelerator Use-Case. 4th International Cross-Domain Conference for Machine Learning and Knowledge Extraction (CD-MAKE), Aug 2020, Dublin, Ireland. pp.139-158, ⟨10.1007/978-3-030-57321-8_8⟩. ⟨hal-03414728⟩

Share

Metrics

Record views

18