Electrical Fault Detection in Three-Phase Induction Motor Based on Acoustics

This study presents the methodology for detecting single phasing fault of three-phase induction motors in steady-state operation based on acoustic sound signal analysis. In the proposed methodology, the signal analysis based on the Root Mean Square (RMS) parameter is used as a comparison between a healthy and a faulty motor in the time-domain. Whereas for the frequency-domain, the Fast Fourier Transform (FFT) with the Average power parameter is used. The hypothesis test is used to prove the statistical significance of the difference between the calculated parameters of the faulty and healthy three-phase induction motors. To illustrate the functionality of the proposed technique many tests have been carried out on a real machine. The results show that integrating motor sound with the traditional control system can increase the protection and reliability of three-phase induction motors.