Research of Fault Diagnosis Distinguishing Technology Based on PCA-Neural Network

A new method of fault diagnosis distinguishing based on PCA-neural network is raised. Use PCA theory to extract the main element from the fault sample data, realize optimum compressed of fault sample data, simplify structure of neural network classify in fault diagnosis, enhance classify speed and precision. The results of power electronic circuit experiment show that the way can decrease the number of the network input nerve cells effectively, enhance studying efficiency and diagnosis accuracy. The way has very good fault distinguishing ability and vast prospect.