A CNN-Based Structure for Performance Degradation Estimation of High-Speed Train Lateral Damper

Abstract

This paper addresses the problem of performance degradation estimation of high-speed train lateral damper based on SDS-CNN. The proposed SDS-CNN consists of two types convolution modules, i.e., DA-Module and FE-Module, where the DA-Module is used to adjust data dimension and map original vibration signals into high dimensional space, while the FE-Module is employed to extract features of different frequencies from different scales adaptively. Experimental results on CRH380A high speed train vibration signals validate the superiority of the proposed structure over FCN, MCNN, Time-CNN, ResNet, ResNext, Xception, and EfficientNet, with the minimum MAE (0.46) and minimum RMSE (0.63).

Keywords

• High-speed train
• lateral damper
• performance degradation
• vibration signal
• deep learning
• convolution neural network