Skip to main content Skip to main navigation


A Neuro-Symbolic Approach for Anomaly Detection and Complex Fault Diagnosis Exemplified in the Automotive Domain

Tim Bohne; Anne-Kathrin Patricia Windler; Martin Atzmueller
In: Brent Venable; Daniel Garijo; Brian Jalaian (Hrsg.). Proceedings of the 12th Knowledge Capture Conference 2023. International Conference on Knowledge Capture (K-Cap-2023), December 5-7, Pensacola, FL, USA, Pages 35-43, K-CAP '23, Vol. 12, ISBN 979-8-4007-0141-2, Association for Computing Machinery, New York, NY, USA, 12/2023.


This paper presents an iterative, hybrid neuro-symbolic approach for anomaly detection and complex fault diagnosis, enabling knowledge-based (symbolic) methods to complement (neural) machine learning methods and vice versa. We demonstrate an instantiation of this novel diagnosis system with applicability in a practically relevant real-world context, specifically the automotive domain. Explainability is indispensable for diagnosis and arises naturally in the system through the specific interplay of neural and symbolic methods. The presented architecture can be considered as a blueprint which is generally transferable to various diagnostic problems and domains.


Weitere Links