Analog Circuit Fault Diagnosis Based on Wavelet Transform and Improved Fuzzy Support Vector Machine

Abstract

To improve the accuracy of analog circuit fault diagnosis, the method of combination wavelet transform and improved fuzzy support vector machine(FSVM) is presented in this paper based on the characteristics of wavelet transform and FSVM. The optimum eigenvector is proposed based on extracting wavelet power spectrum of the signal of analog circuit, whilst the membership function of FSVM is improved. Then the proposed approach is applied to diagnose the analog circuit fault, the experimental results show that the diagnosis accuracy of analog circuit fault is improved by proposed algorithm, and the algorithm is a feasible method for analog circuit fault.