Ma, J.; Liu, X.; Hu, J.; Fei, J.; Zhao, G.; Zhu, Z. Stator ITSC Fault Diagnosis of EMU Asynchronous Traction Motor Based on apFFT Time-Shift Phase Difference Spectrum Correction and SVM. Energies2023, 16, 5612.
Ma, J.; Liu, X.; Hu, J.; Fei, J.; Zhao, G.; Zhu, Z. Stator ITSC Fault Diagnosis of EMU Asynchronous Traction Motor Based on apFFT Time-Shift Phase Difference Spectrum Correction and SVM. Energies 2023, 16, 5612.
Ma, J.; Liu, X.; Hu, J.; Fei, J.; Zhao, G.; Zhu, Z. Stator ITSC Fault Diagnosis of EMU Asynchronous Traction Motor Based on apFFT Time-Shift Phase Difference Spectrum Correction and SVM. Energies2023, 16, 5612.
Ma, J.; Liu, X.; Hu, J.; Fei, J.; Zhao, G.; Zhu, Z. Stator ITSC Fault Diagnosis of EMU Asynchronous Traction Motor Based on apFFT Time-Shift Phase Difference Spectrum Correction and SVM. Energies 2023, 16, 5612.
Abstract
Abstract: The EMU(electric multiple units) traction motors are powered by converters. The PWM(pulse width modulation) voltage increases the voltage stress borne by the motor insulation system, making the ITSC(inter-turn short-circuit) fault more prominent. An index based on short-circuit thermal power was proposed in the article to evaluate the non-metallic ITSC faults degree. The apFFT(all phase FFT) time-shift phase difference correction with double Hanning-windows is used to calculate the fundamental frequency of the traction motor's ZSVC（zero se-quence voltage component）, the fundamental amplitudes of ZSVC and three-phase current. The five parameters are used as fault features to train the SVM (support vector machine)fault diagnosis model. The SVM hyper-parameters C and g are optimized by K-CV (K fold cross-validation) and grid search methods. The experimental verification was carried out by the EMU electric traction simulation experimental platform. According to the non-metallic degree index proposed in this article, the experimental samples were divided into three categories, normal, incipient and serious fault samples. The ITSC fault diagnosis accuracy was 100% on the training data set and 93.33 % on the test data set. There was no misclassification between normal and serious ITSC fault samples.
Engineering, Electrical and Electronic Engineering
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
