Fault detection and isolation on a PWM inverter by knowledge-based model

Abstract

This paper presents an approach based on knowledge models to detect and isolate faults in a pulsewidth modulation inverter supplying a synchronous machine. These faults do not affect the system protection. A diagnosis system which uses only the input variables of the drive is presented. It is based on the analysis of the current-vector trajectory and of the instantaneous frequency in faulty mode. These two methods have been successfully applied to an experimental system.