Induction motor broken rotor bar faults diagnosis using ANFIS-based DWT

This paper proposes a new method for diagnosis Broken Rotor Bar (BRB) faults in three phase squirrel-cage induction motors. The proposed method is based on the stator current signature analysis using Discrete Wavelet Transform (DWT) and Adaptive Neural Fuzzy Inference System (ANFIS) artificial intelligence approach. The DWT technique plays an important role for signal feature extraction. The abnormal transient signals can be applied to recognize the BRB faults by DWT. The DWT is considered to identify fault features accurately. The dataset is established by feature vectors are applied as input pattern in the training and identification process. Furthermore, the ANFIS is proposed to classify and identify the BRB fault. The fault diagnosis is verified experimentally on 1.5 Hp three phase induction motor under different fault conditions and different load conditions. The experiment results demonstrate that this technique is valid and effective for the BRB faults diagnosis.

Automated summary

This paper proposes a new method for diagnosing BRB faults in three phase squirrel-cage induction motors using DWT and ANFIS. The experimental results show that this technique is valid and effective for BRB fault diagnosis.