Nonlinear Analog Circuit Fault Diagnosis Based on MF-DFA Method
Jingyuan Tang, Yibing Shi, Zhang We, Longfu Zhou · Journal of Computer-Aided Design & Computer Graphics · 2010
Abstract — This paper presents a fault diagnosis method for nonlinear analog circuit based on multifractal detrended fluctuation analysis (MFDFA) method. The MFDFA method is applied to analysis fault signal and extracts the multifractal features from the raw signal. The selected features are given to SVM classifier for further classification. The data required to develop the classifier are generated by simulating various faults using Pspice software. The simulation results show that the proposed method provides a robust and accurate method for nonlinear circuit fault diagnosis.