Detection and Classification of Multiple PQ Event Using MWT and k-NN Classifier

The research work looks into the use of signal processing techniques for power quality event classification. We propose an algorithm for classifying power quality events that uses multi-wavelet transform as a feature extraction technique and a k-Nearest Neighbor classifier for classification. The proposed work is divided into two sections: feature extraction and classification. Using the multi-wavelet transform, features are extracted with greater accuracy and with a new set of features in the feature extraction section. The k-Nearest Neighbor technique was used in the classification section. A classifier's operation is determined by its features. The performance of the classifier is influenced by the number of features used, but if the number of features used is large, the classifier's efficiency increases slightly, resulting in precise classification.