Rational-Dilation Wavelet Transform Based Torque Estimation from Acoustic Signals for Fault Diagnosis in a Three-Phase Induction Motor

Condition monitoring of electric drives play a significant role for a safe working environment. Induction motors are widely used in industries and any fault in it leads to interruption in the process or complete shutdown of the equipment. In this paper, acoustic-based fault detection in a three-phase induction motor is done by estimating the torque from the acoustic signals released by the machine. The fault detection is possible as acoustic emission is different for faults such as single phasing, bearing cage damage, and broken rotor bars. The acoustic signals are processed using rational-dilation wavelet transform (RADWT) technique to extract the fault features and thereby diagnose the fault type. The torque estimation is done using multiple regression method by extracting the energy possessed in the processed acoustic signal and the faults are diagnosed precisely. An experimental setup comprising of a three-phase induction motor with brake drum loading is used to validate this approach. The RADWT has adjustable frequency resolution in comparison with other wavelet methods. When high Q-factor filters are employed in the RADWT, better representation of different faults are obtained in the decomposed sub-bands. In addition, characteristic frequencies of different faults are calculated analytically and validated by observing the frequencies in the FFT spectrum of acoustic fault signals.