Single-ended fault location and early warning method of transmission line based on back propagation neural network

Abstract

Abstract For power transmission systems, accurate and reliable fault location methods can ensure rapid recovery of faulty lines and improve power supply reliability. In order to solve the problems of the structural complexity of the transmission system and the difficulty of line fault location, a single-ended fault location and early warning method of transmission line based on back propagation neural network is proposed. First, the fault line selection is performed quickly when the fault occurs. Then, the voltage fault components collected at the measuring point when the fault occurs are decomposed and reconstructed by wavelet packet to obtain the wavelet packet energy, which is used as the input sample to train through the nonlinear fitting ability of back propagation. With the help of backpropagation neural network, arbitrary complex functions can be processed, and the learning results can be accurately used for new knowledge, and circuit faults can be diagnosed conveniently and quickly. Finally, the corresponding fault distance can be output by substituting the wavelet packet energy reflecting the fault location. The simulation results show that the method has strong resistance to transition resistance and high positioning accuracy.