Compound Fault Diagnosis of Stator Interturn Short Circuit and Air Gap Eccentricity Based on Random Forest and XGBoost

Taking the traction motor of CRH2 high-speed train as research object, this paper proposes a diagnosis method based on random forest and XGBoost for compound fault resulting from stator interturn short circuit air gap eccentricity. First, U-phase V-phase currents are used signal then Savitzky–Golay filtering is noise deduction signal. Second, wavelet packet decomposition to extract composite features high-dimensional optimized by principal component analysis (PCA) method. Finally, combined detect faults. Using experimental data semiphysical simulation platform, different modes completed, high accuracy achieved, which verifies validity