Predictive Maintenance for the Optical Synchronization System of the European XFEL: A Systematic Literature Survey

Abstract

The optical synchronization system of the European X-ray Free Electron Laser is a networked cyber-physical system producing a large amount of data. To maximize the availability of the optical synchronization system, we are developing a predictive maintenance module that can evaluate and predict the condition of the system. In this paper, we report on state-of-the-art predictive maintenance methods by systematically reviewing publications in this field. Guided by three research questions addressing the type of cyber-physical systems, feature extraction methods, and data analytical approaches to evaluate the current health status or to predict future system behavior, we identified 144 publications of high quality contributing to research in this area. Our result is that especially neural networks are used for many predictive maintenance tasks. This review serves as a starting point for a detailed and systematic evaluation of the different methods applied to the optical synchronization system.