Fault Diagnosis of Power Transformers Based on Membrane Computing Optimizing Neural Network

Abstract

Presently, dissolved gas content analysis and fault diagnosis are the important segments of power transformer. As to the problem of the back propagation algorithm of neural network commonly used lies in the optimization procedure getting easily stacked into the minimal value locally and strict requirement on the initial value, a fault diagnostic method is presented, based on the membrane computing optimizing back propagation neural network. Throughout the process, compromise is satisfactorily reached among the network complexity, the convergence and the generalization ability. The results of diagnosis test show that the algorithm proposed has high classification accuracy, which proves its robustness and effectiveness.