Analog circuit soft fault diagnosis based on LSSVM optimized by improved PSO

In order to diagnose the tolerance analog circuit soft fault, fault diagnosis model combining multi-swarm cooperative chaos particle swarm optimization (MCCPSO) algorithm with the least square support vector machine (LSSVM) was proposed. The acquisition signal was preprocessed by wavelet analysis. And the feature information as the sample was input LSSVM for classification decision. MCCPSO was used for optimizing structure parameters of LSSVM. The simulation result shows that the proposed model has high diagnosis accuracy, and it can be applied to tolerance analog circuit fault diagnosis.