Vibration-based damage detection of rail fastener using fully convolutional networks

Abstract

The rail fastener plays an important role in supporting the rail and isolating the train-track system vibrations. Its damage detection is therefore an inevitable part in railway maintenance to ensure the system performance. Recently, deep learning techniques are widely applied to structural health monitoring, including damage detection of the rail fastener based on visions. However, the vision-based detection is mainly limited to visible damages. To address this limitation, this work presents a vibration-based detection method by introducing the fully convolutional network (FCN) to identify invisible damages of fasteners. Firstly, three damage categories are defined and five damage degrees are equivalently represented by modifying the stiffness and damping coefficients of target fasteners. Then, a vehicle-track vertically coupled dynamics model with variable vehicle speeds is established to obtain axle box accelerations (ABAs) under excitations of fastener damage and track irregularity. Finally, a fastener damage detection network is designed based on the FCN architecture to predict damage degrees by inputting the ABA, the track irregularity and the vehicle speed simultaneously. The detection performance is estimated and the network robustness to noise is analysed. The results show that the proposed method is capable of achieving accurate, real-time and robust identification of the fastener damage.