Composite Fault Diagnosis of Rotor Broken Bar and Air Gap Eccentricity Based on Park Vector Module and Decision Tree Algorithm

Abstract

Taking the traction motor of CRH2 high-speed train as the research object, this paper proposes a composite fault diagnosis method based on park vector module for the composite fault of rotor broken bar and air gap eccentricity. Firstly, the current noise is reduced with the improved empirical mode decomposition method; and the three phase stator current is converted to park vector using the extension park vector method, to effectively avoid the case in which the composite fault features are submerged by the fundamental frequency characteristics; Secondly, the park vector module of stator current is transformed by fast Fourier transform, and compound fault features are extracted in frequency domain. Finally, the fault feature is put into the decision tree classifier to estimate the fault degree. The data of CRH2 semi-physical simulation platform are used to verify the validity of this method.