Development and operation of a system for diagnosing the condition of regional railways tracks

Abstract

Monitoring the condition of railway tracks effectively increases the safety of regional railways. A system that uses a compact on-board sensing device was previously developed for monitoring the track condition of regional railways. However, this system does not consider the running speed of the vehicle. In this study, we propose two new methods for diagnosing the condition of tracks considering the travelling speed of the vehicle: one based on the Mahalanobis distance and the other that uses Gaussian process regression. After conducting a test study to verify the effectiveness of the proposed methods, the results showed that both approaches can provide an accurate diagnosis when considering the influence of speed.

Keywords

• railway
• track
• condition monitoring
• car-body acceleration
• gaussian process regression