Analog Circuit Fault Diagnosis Using Multi-wavelet Transform and SVM

A new method for diagnosing analog circuit faults using multi-wavelet transform and support vector machine (SVM) is presented. The response signals of the analog circuit are preprocessed using multi-wavelet transform and the optimal fault feature with better classification capacity are obtained using energy normalization. Then, the features are inputted into the ensemble SVM to identify different fault cases. Simulation results indicate that this method can effectively enhance the analog fault diagnostic accuracy.