Primary Equipment Fault Diagnosis Strategy for Box Substation Based on PSO-BP Neural Network

摘要

Box type substations are widely used in industrial, commercial and urban transmission and distributed system, which play an important role in power systems, and has considerable meaning in box type substation's fault diagnosis. Through the study of the box type substation's internal structure, working principle and the analysis of fault and fault characteristics. A fault diagnosis network model based on PSO-BP neural network is proposed to integrate the system data. To avoid the drawbacks of BP neural network algorithm learning and make the model have a good convergence and adaptability, the optimization of BP neural network is carried out by using the optimal characteristics of PSO. The simulation model results that the network has a good recognition effect, and it's very promising in the fault prediction of box type substation.