Open circuit fault diagnosis for the power electronic converter stages using ANFIS algorithm

Abstract

This paper demonstrates a fault detection and location for the open circuit (O.C) faults in the all power electronic converter stages including; the three-phase rectifier, the dc-dc converter, and finally the single-phase inverter. The proposed fault diagnosis is based on the adaptive neuro-fuzzy inference system (ANFIS) algorithm. The inputs to the ANFIS unit are the voltage and the current measurements of the power converter stages after they undergo several signal processing operations so that they could efficiently reflect the fault occurrence and behavior. The output of the ANFIS unit is utilized as an index in order to identify the O.C fault in the power converter. Then, it locates the fault within the three different stages of the converter.