Identification of PQ disturbances and degree of loading in induction motor using neuro-wavelets

This paper presents a methodology for the simultaneous detection of the load and percentage of PQ disturbance if any in the supply to the induction motor. Stator current signature analysis is used for monitoring the variations in the supply as well as in the load. Wavelet transform is applied to the stator current for the extraction of the signature indicating the variations in the load and in the supply. A feedforward neural network is trained and tested using these wavelet coefficients as input. The output of the neural network classifies the health of the supply, percentage of PQ disturbance if any and the percentage of load at which the machine is running. The entire simulation is carried out using MATLAB. The proposed network has performance efficiency of 95.2%.