Diagnostic de la MAS triphasée par la méthode des réseaux de neurones artificiels

Abstract

This end-of-study project aims to diagnose faults in three-phase asynchronous machines. Firstly, we will develop the state model of the healthy machine, which will be simulated using Matlab/Simulink software. Then, we will study the machine in the presence of two specific faults, namely coil-to-coil short circuits and supply imbalance. Finally, the last part of this work will focus on detecting these faults using artificial neural network methods. For this purpose, the architecture of this Artificial Neural Network (ANN) is determined using the trial-and-error method. The data for training and testing are collected using the simulation model.