This project is funded by and executed in collaboration with Strukton Rail
The presently applied railway maintenance strategies are mainly based on past experience and periodic inspections. However, the inspections do not effectively prevent unexpected failures of the network, especially since variations in usage of the track and environmental conditions make degradation rates rather unpredictable. As a result, many maintenance activities are performed in a reactive way, which yields network unavailability and relatively high maintenance costs.
The research in this project aims to make the transition from reactive maintenance to (pro-active) predictive maintenance by developing and utilizing a range of continuous monitoring systems and continuously improving Failure Mode, Effects (and Criticality) Analyses (FME(C)As) and Root Cause Analyses (RCAs). This will significantly reduce the uncertainty on the actual condition of the network elements, thus reducing the number of unexpected failures and extending the preventive maintenance intervals in case of less severe usage of the track.
The research is subdivided in three main topics:
- Capturing and preliminary processing of the data,
- Data analytics for diagnosis and prognosis,
- Data integration and analytics for maintenance planning and optimization.
These topics are addressed by executing two PhD projects (Meghoe and Wu) and a number of additional (PDEng and Postdoc) projects (Seraj).