Fault Diagnosis of Induction Motor Stator Winding Open Circuit Based on Wavelet Transformation and Bayesian Classification

Aiming at the problem that the traditional single-phase winding open-circuit fault diagnosis method of induction motor has low positioning accuracy, this paper proposes a motor fault diagnosis method based on wavelet transform energy analysis and Bayesian classification. Firstly, wavelet analysis is carried out on the three-phase stator current signal. The signal of each frequency band is reconstructed by using wavelet packet decomposition coefficients. Secondly, the wavelet reconstruction coefficient root mean square method is used to calculate the energy eigenvalues of different frequency bands. The energy eigenvalues are selected as the basis for fault judgment. Finally, the Bayesian classification is used to complete the fault classification under the two states of standard and open winding. The above method is simulated and verified on the MATLAB/Simulink platform. Simulation results show that the fault diagnosis method has high effectiveness and accuracy.