Intelligent Fault Diagnosis Method in Controlled Rectifier Based on Support Vector Machines

Abstract

Rectifier units is widely used in electrochemical and the metallurgical industry,stability and reliability are required.This paper studied the fault classification and diagnosis method of the bridge 6-pulse waveform controlled rectifier circuit based on Support Vector Machines.All the faults in thyristors were analyzed, the fault classification method according to the rectifier aberrant voltage waveforms was put forward,fault voltage waveforms were summarized.By keeping the relations between faults and waveforms in a support vector machines model, the support vector machines model could be trained to detect faults and realize automation of fault diagnosis. Three-phase bridge rectifier circuit fault was presented as an example, coupled with the results of a certain power electronic circuit experiment, indicates that the method can accurately diagnose and locate fault for controlled rectifier circuits.