Monitoring of Railpad Long-term Condition in Turnouts Using Extreme Value Distributions

The railpad is a key element in railway infrastructures that plays an essential role in the train-track dynamics. Presence of worn or defective railpads along railway track may lead to large wheel/rail interaction forces, and a high rate of deterioration for track components. Despite the importance of railpad, the track infrastructure managers use no inspection tool for monitoring in-service railpads over time. In this paper, a novel data-driven monitoring tool for long-term performance analysis of in-service railpads is developed based on train-induced vibration data collected by a track-side measurement system. The monitoring tool consists of a method for track resonance frequencies estimation, a temperature-frequency model for describing railpad behavior with respect to ambient temperature, and a generalized likelihood ratio test based on the generalized extreme value distribution for detecting changes in the railpad status over time. To evaluate the performance of the proposed monitoring system, the status of railpads at four different locations along a railway turnout is monitored over a period of 18 months. It is shown that the monitoring system can successfully detect changes in railpad properties over the considered period.