Towards Predictive Maintenance for the Optical Synchronisation System at the European XFEL

Supervisors: Dr. Annika Eichler (DESY), Prof. Marina Tropmann-Frick (HAW), Prof. Görschwin Fey (TUHH)

The European XFEL is the largest currently operated linear particle accelerator in the world. It provides measurements requiring timing with an error margin in the femto-second range for most subsystems within the facility. For this purpose, an optical synchronisation system is installed at the European XFEL to stabilize critical RF stations and the experimental lasers in time. Up to now, the data corresponding to the optical synchronization system was only accessible online without any possibility to access histories. With this no root cause analysis of occurring failures was possible nor failure statistics. Currently, a data acquisition system is built to support efficient storage for a part of available sensor data.
The main goal of the project is the development of a predictive maintenance module for the optical synchronization system installed at the accelerator. This module should provide a system monitoring and a predictive component  allowing to detect critical events and conditions with anomaly potential. The module should support handling of the huge amount of dynamic data, provide efficient storage and compression techniques for long-term data storage and retrieval. Additionally, the interactive visualization and analytic techniques should be developed to provide deep insights into the system.