Research on fault diagnosis of high-voltage circuit breaker based on the improved BP neural network

High-voltage circuit breaker is the most important control and protection equipment. Doing fault diagnosis to high-voltage is very important to realize the power system stable and reliable running. The improved BP neural network momentum gradient descent algorithm was used in high-voltage fault diagnosis comparing with traditional BP neural network in this paper. The simulation indicated that this algorithm makes the fault diagnosis more accurate and functional through adjusting the learning rate and weights.