Data-driven Anomaly Detection for Railway Propulsion Control Systems

The popularity of railway transportation has been on the rise over the past decades, as it has provided safe, reliable, and highly available service. One of the main challenges this domain has been facing is reducing the costs of preventive maintenance and improving operational efficiency. In this paper, we aim at enabling the monitoring and analysis of collected signal data from a train propulsion system. The main idea is to monitor and analyze collected signal data gathered during the regular operation of the propulsion control unit or data recorded during the regular train tests in the real-time simulator. To do so, we have implemented a solution to enable train signal data collection and its storage for further analysis purposes. In our analysis, we focus on identifying signal anomalies and predicting potential failures using MathWorks tools. Two machine learning techniques, unsupervised and supervised learning, are implemented. Additionally, in this paper, we have investigated ways of how data can be efficiently managed.