Fault diagnosis of railway point machines based on wavelet transform and artificial immune algorithm

Abstract

Aiming at the current problems of high failure rate and low diagnostic efficiency of railway point machines (RPMs) in the railway industry, a short-time method of fault diagnosis is proposed. Considering the effect of noise on power signals in the data acquisition process of the railway centralized signaling monitoring (CSM) system, this study utilizes wavelet threshold denoising to eliminate interference. The results show that the accuracy of fault diagnosis can be improved by 4.4% after denoising the power signals. Then in order to attain a lighter weight and shorten the running time of the diagnosis model, Mallat wavelet decomposition and artificial immune algorithm are applied to RPM fault diagnosis. Finally, voluminous experiments using veritable power signals collected from CSM are introduced, which show that combining these methods can procure higher precision of RPMs and curtail fault diagnosis time. This substantiates the validity and feasibility of the presented approach.