Transmission Line Fault Classification Based on Higher-Order Spectrum and ResNet

The accurate classification of transmission line faults has been a key issue in the development of smart grids. At present, fault classification is based on recurrent neural network (RNN) for temporal signals, and the development of RNN is not so mature compared with convolutional neural network (CNN). Therefore, this paper proposes a transmission line fault classification algorithm based on higher-order spectral analysis and CNN, aiming at converting the time-series signals into images and using CNN for fault classification. After establishing the fault model on Matlab/Simulink, the current signals of different faults are obtained. After processing the current signals to extract their zero-mode currents, the fault image signals are obtained using higher-order spectral analysis as the input to the CNN. Simulation results show that the proposed method can accurately identify faults with high accuracy when faults occur in transmission lines, thus reducing the economic losses caused by faults.