Research on Fault Diagnosis of Traction Motor Based on Group Decision Making

Abstract

In the fault diagnosis of traction motor, it is difficult to make a accurate and complete decision for the single fault diagnosis method. To handle this problem, a method of fault diagnosis for traction motor is proposed based on group decisionmaking in this paper. Firstly, the weights of the characteristic data are determined by intuitionistic fuzzy entropy, intuitionistic fuzzy cross entropy and foreground theory, according to traffic flow parameters the fault feature data. Secondly, fuzzy theory, neural network and support vector machine are used to diagnose the fault of the switch control circuit respectively. And then the three methods are considered as decision experts with the group decision theory. Through the simulation study, the prediction results of different diagnosis methods are given. The results show that the proposed method can accurately identify the fault type of the traction motor. This method is better than the single method to improve the accuracy of fault diagnosis, and has a good application prospect.