Study on Faulty Phase Selection Based on the Wavelet Power Spectrum Entropy and LIBSVM

Fault phase selection is studied in this paper based on the wavelet power spectrum entropy and LIBSVM for transmission line. First, MATLAB is used to simulate five fault types and obtain a variety of fault voltage waveforms. Second, the simulation waveform is transformed to extract the energy spectrum entropy which is pretreatment to greatly reduce the number of data dimensions and effectively optimize the input data of LIBSVM. Finally, LIBSVM is used to select fault phase, experimental results show that the method is very effective.