Skip to Main Content
This paper presents a novel technique for power quality disturbance classification. Wavelet transform (WT) has been used to extract some useful features of the power system disturbance signal and discrete harmony search with modified differential mutation operator (DHS_MD) have been used for feature dimension reduction in order to achieve high classification accuracy. Next, a probabilistic neural network (PNN) has been trained using the optimal feature set selected by DHS_MD for automatic PQ disturbance classification. Considering ten types of PQ disturbances, simulations have been carried out which show that the combination of feature extraction by WT followed by feature reduction using DHS_MD increases the testing accuracy of PNN while classifying PQ signals.