Diagnosis and Classification of broken bars fault using DWT and Artificial Neural Network without slip estimation

Abstract

Many methods of the diagnosis of broken rotor bar fault in induction machine are developed every day and shown its reliability for the detection of BRB fault. Nevertheless, despite its existing reliable fault detection. The slip estimation procedure is always presented. To overcome this obstruction a new approach based on Discrete Wavelet Transform and Artificial Neural Network is proposed in the aim to make the broken rotor bar fault diagnosis load independent. The results obtained from the proposed method showed the optimal and efficient performance of the method in detecting the broken rotor bar fault in induction motor under various conditions.