Vibration-signature-based inter-turn short circuit identification in a three-phase induction motor using multiple hidden layer back propagation neural networks

Inter-turn short circuits in stator windings area fairly common fault in induction motors. Early detection of this type of fault will greatly assist in sustaining production processes in manufacture. This paper proposes a method to detect inter-turn short circuits in stator windings at an early stage. The proposed method consists of four steps: (1) preprocessing by decomposing the signal into detail and approximation signals using a wavelet transform, (2) converting the first detail signal into a frequency-based signal using fast Fourier transform, (3) calculating the values of statistical features for the signal in time and frequency domains and (4) identifying faults using a back propagation neural network (BPNN). Using BPNN architecture with 3 hidden layers and 75 neurons per layer, the identified recognition rate was96.67% with a mean square error of 1.39×10-5. The validity of the proposed method is excellent based on a receiver operating characteristic analysis, with a precision level of 94.66%.