Explaining Deep Neural Networks for Bearing Fault Detection with Vibration Concepts

Decker, Thomas; Lebacher, Michael und Tresp, Volker (2023): Explaining Deep Neural Networks for Bearing Fault Detection with Vibration Concepts. 2023 IEEE 21st International Conference on Industrial Informatics (INDIN), Lemgo, Germany, 18-20 July 2023. Jasperneite, Jürgen (Hrsg.): In: 2023 IEEE 21st International Conference on Industrial Informatics : INDIN 2023 : 17-20 July 2023, Lemgo, Germany, [Piscataway, NJ]: IEEE.

Abstract

Concept-based explanation methods, such as Concept Activation Vectors, are potent means to quantify how abstract or high-level characteristics of input data influence the predictions of complex deep neural networks. However, applying them to industrial prediction problems is challenging as it is not immediately clear how to define and access appropriate concepts for individual use cases and specific data types. In this work, we investigate how to leverage established concept-based explanation techniques in the context of bearing fault detection with deep neural networks trained on vibration signals. Since bearings are prevalent in almost every rotating equipment, ensuring the reliability of intransparent fault detection models is crucial to prevent costly repairs and downtimes of industrial machinery. Our evaluations demonstrate that explaining opaque models in terms of vibration concepts enables human-comprehensible and intuitive insights about their inner workings, but the underlying assumptions need to be carefully validated first.

• Dokumententyp: Konferenzbeitrag (Paper)
• Fakultät: Mathematik, Informatik und Statistik > Statistik > Lehrstühle/Arbeitsgruppen > Lehrstuhl für Statistik und ihre Anwendungen in Wirtschafts- und Sozialwissenschaften ; Mathematik, Informatik und Statistik > Informatik
• Themengebiete: 000 Informatik, Informationswissenschaft, allgemeine Werke > 004 Informatik
• ISBN: 978-1-6654-9313-0 ; 978-1-6654-9314-7
• Ort: [Piscataway, NJ]
• Sprache: Englisch