Broken rotor bar fault detection of 3-phase induction motor using online adaptive continuous wavelet transform and fuzzy logic

This paper presents an online adaptive wavelet and fuzzy logic based accurate broken rotor bar fault detection of the 3-phase squirrel cage induction motor (IM). The winding function is applied for obtainment of stator current and speed signals at different fault and load conditions. To detect the amplitudes and frequency components corresponding to different fault and load conditions, these signals are analyzed through the adaptive continuous wavelet transform (CWT). The coefficients of CWT are adapted online based on the harmonic amplitude which is the output of CWT. The amplitudes and frequencies from CWT are used to train a fuzzy logic controller (FLC) in simulation. The adaptive CWT and trained FLC are then applied to detect the fault condition of the motor in both simulation and real-time. The experimental results show that the proposed method of fault detection based on adaptive CWT and FLC detects the motor fault conditions with high precision. The method is a potential candidate to detect the squirrel cage IM fault, especially for the large size industrial motors.