Grounding Grids Fault Diagnosis Based on PCA-BP Neural Network

In order to solve the problem of needing to build accurate mathematical model in grounding grids fault diagnosis ,a new method for applying to the study of grounding grids fault diagnosis,which was based on BP neural network and improved by PCA theory，was introduced.The PCA(Principal component analysis)method was incorporated into the network,which not only solved the linear correlation of the input, but also simplified the network structure and reduced the parameters of neural net input. It realized optimum compression of fault sample data and enhanced classification speed and precision. The experimental results demonstrated that the method could decrease the number of the network input nerve cells effectively, and enhanced study efficiency and diagnosis accuracy. The way had very good fault distinguishing ability and vast prospect.