Fault Diagnosis of Switch Machine Based on Hierarchical Dispersion Entropy and SSA-SVM

The switch machine (SM) is a critical piece of equipment in the railway signal system. Its function is to realize the conversion of the turnout position, which is of great meaning to ensure the operation of the train. It has been in a bad environment for a long time, which aggravates the occurrence of SM faults. However, the current signal of the SM could be more robust, and the difficulty of feature extraction leads to the low accuracy of SM fault diagnosis. In this paper, a fault diagnosis method of SM based on hierarchical dispersion entropy (HDE) and sparrow search algorithm-support vector machine (SSA-SVM) is proposed. Firstly, combining the analytic hierarchy process and the dispersion entropy, the HDE is proposed to obtain the current feature information. Secondly, the SSA is used to optimize the parameters of SVM to improve the performance of SVM. Using the optimized SVM as the fault classification method of the SM, the fault diagnosis results of the SM is acquired. In order to confirm the superiority of the suggested approach, the experiment is ultimately conducted using real data that was gathered in the field and compared with the current approaches. The experimental findings demonstrate the high fault diagnostic accuracy of the suggested approach, which can offer theoretical backing for the SM fault diagnosis.