Diagnosis of Power Cable Fault Types Based on PSO-BP algorithm

Aiming at the problems of complex fault types in power cables and low accuracy of traditional diagnostic methods, a fault diagnosis method based on wavelet packet energy entropy feature extraction and particle swarm optimization BP neural network (PSO-BP) is proposed. Firstly, the energy entropy characteristics of the cable voltage signal are extracted by using the wavelet packet decomposition technology to construct a complete three-phase feature vector. Secondly, the particle swarm optimization algorithm is adopted to optimize the initial weights and thresholds of the BP neural network to improve the convergence speed and diagnostic accuracy of the model. Finally, the effectiveness of the constructed model in multi-type fault identification was verified through simulation experiments. The results show that this method is superior to the traditional methods in terms of feature extraction, training efficiency and recognition accuracy, and has good promotion and application value.