Diagnostic Modelling for Induction Motor Faults via ANFIS Algorithm and DWT-Based Feature Extraction

This paper proposes an Adaptive Neural Fuzzy Inference System (ANFIS) model for diagnosis of combined Inter Turn Short Circuit (ITSC) and Broken Rotor Bar (BRB) faults in a Squirrel Cage Induction Motor (SC-IM). The signal the stator current is obtained from really healthy faulty SC-IM. Experimental tests have been set up using 1.5 Hp/380 V three-phase SC-IM with different ITSC BRB under loading conditions. Before entering model, Discrete Wavelet Transform (DWT) pre-processes signal. DWT generates data sets order to evaluate proposed technique. ANFIS based on used successfully diagnose most relevant very effectively. In addition, method has compared auto-regressive finding that achieves higher efficiency than previous one. classifies entirely states high accuracy.