Based on Compact Type of Wavelet Neural Network Tolerance Analog Circuit Fault Diagnosis

Based on the classical wavelet neural network, this paper put forward a sort of improved multiple-input multiple-output compact type of wavelet neural network, adopted adaptive learning rate and additional momentum BP algorithm to carry out training, studied its tolerance analog circuit fault diagnosis applications. Simulation results displayed that the compact type of wavelet neural network learning is fast, it can be effective diagnosed and located to tolerance analog circuit fault.