ANN-Based Pattern Recognition for Induction Motor Broken Rotor Bar Monitoring under Supply Frequency Regulation

The requisite of direct-on-line (DOL) starting for various applications in underground mines subjects the rotor bars heavy-duty squirrel cage induction motors (SCIMs) to severe stresses, resulting sustained fault bars, unlike where mostly reduced voltage is preferred. Furthermore, SCIMs working are also affected by unforeseen frequency fluctuations. Hence, paper proposes a discrete wavelet transform (DWT)-based broken bar detection scheme using stator current analysis SCIM when subjected regulation (±4% 50 Hz supply) steady-state, as prevalent mines. In this regard, level-seven detailed coefficient obtained DWT-based multi-resolution corresponding healthy compared with that faulty extract necessary features identify fault. Further implementation proposed done artificial neural network (ANN)-based pattern recognition techniques, wherein both feed-forward backdrops and cascaded forward backdrop type ANNs have been used pinpointing based on feature extraction results from DWT. developed analysed MATLAB/Simulink 5.5 kW, 415 V, SCIM, which further validated LabVIEW-based real-time implementation.