Diagnostic d’un défaut rotorique dans les moteurs asynchrones triphasés à cage par RNA

Abstract

In this work, we have modeled and simulated the asynchronous machine for the diagnosis of the rotor bar breakage fault. This diagnosis is based on two techniques. The first is the application of signal processing which is an efficient solution to the problem of fault diagnosis. The second is based on a neural network, which is one of the best tools for automatic fault diagnosis. This technique allows to diagnose and determine the number of broken bars despite the change of the load.