Grünhagen, ArneArneGrünhagenEichler, AnnikaAnnikaEichlerTropmann-Frick, MarinaMarinaTropmann-FrickFey, GörschwinGörschwinFey2025-11-142025-11-142025-03-17Frontiers in artificial intelligence and applications 399: 128-144 (2025)978-1-6436-8572-4https://hdl.handle.net/11420/58657The early and automatic detection of faulty behavior is essential for maintaining the reliability of a cyber-physical system. In this paper we describe a fault localization approach for such a highly complex distributed system, the optical synchronization system of the European X-ray free-electron laser. Using a dependency graph, we model the relationships between the components and the influences of environmental effects. After we first resolve linear long-term dependencies between dependent components with a correlation analysis, we then use an unsupervised fault detection pipeline consisting of statistical feature extraction and unsupervised anomaly detection to accurately identify anomalies and localize their origins in the system.enhttps://creativecommons.org/licenses/by-nc/4.0/Data MiningFault AnalysisDependency GraphCyber-Physical SystemTechnology::629: Other Branches::629.8: Control and Feedback Control SystemsBook Parthttps://doi.org/10.15480/882.1613610.3233/faia24157710.15480/882.16136Book Chapter