Fuzzy Detection and Diagnosis of Fault Modes in a Voltage-Fed PWM Inverter Induction Motor

This paper describes a fuzzy-based method of fault detection and diagnosis in a PWM inverter feeding an induction motor. The proposed fuzzy approach is a sensor-based technique using the mains current measurement to detect intermittent loss of firing pulses in the inverter switches. A localization domain made with seven patterns is built with the stator Concordia current vector. One is dedicated to the healthy domain and the last six to each inverter switch. The fuzzy fault detector is designed on the basis of stator current analysis. Simulated experimental results on 1.5-kW induction motor drives show the feasibility of the proposed approach