BP neural network has been applied in transformer fault diagnosis,but it still has shortcomings,such as slow convergence speed,and easy falling into local minimum.So to solve the above problems,this paper uses principal component anal-ysis to optimize the BP neural network diagnosis model,to improve the diagnosis accuracy.Principal component analysis(PCA)is used to reduce the dimension of network learning samples.The neural network structure is simplified and the shortage of the neural network is improved.Finally,based on this model,the transformer fault is analyzed and compared with other transformer diagnosis methods.The results show that the principal component-BP neural network discriminant model has higher accuracy and reliability.
维普
万方数据
