Neural Fault Diagnosis and Inverter Reconfiguration for a Neural Direct Torque Control of Induction Motor Drive

Abstract

At the present time, electrical drives generally associate inverter and induction machine. Therefore, these two elements must be taken into account in order to provide a relevant diagnosis of these electrical systems. So it is important to detect early different defects that can occur in these systems in order to find ways to allow us to monitor the operation and preventive action to avoid frequent breakdowns. The aim of this work is to study the feasibility of fault detection and diagnosis in a three-phase inverter feeding an induction motor. We present the simulation results of a neural network direct torque control of induction motor with a fault diagnosis and reconfiguration system using an artificial intelligence technique. we gave a detailed description of one or multiple inverter switching faults with a simple method for extraction of characteristics to study the feasibility of detection and diagnosis of these defects, and at the same time trying to made a reconfiguration of the inverter to surround faults when they occurs.