The Feature Selection based Power Quality Event Classification using Wavelet Transform and Logistic Model Tree

This paper presents a new power quality event classification technique using wavelet transform and logistic model tree. The proposed method uses the samples of three cycle duration of three line voltage of power quality events. The features of these samples are obtained by using the wavelet transform and a few different feature extraction techniques. The sequential forward selection method based a feature selection process is done to ensure good classification accuracy by selecting 20 better features from all 90 features generated from the wavelet transform coefficients. The obtained features are used to train a single logistic model tree. The feasibility of the proposed algorithm has been tested using real life power quality events. The result indicates that the feature selection based proposed method reliably classifies all types of power quality events with high accuracy. Streszczenie. W artykule zaproponowano nową metodę oceny jakości energii wykorzystującą transformatę falkową i logistyczny model drzewa. W metodzie analizuje się trzy cykle w trzech liniach napięcia. Możliwa jest klasyfikacja 90 zdarzeń i wybranie 20 typowych cech. (Selekcja cech bazująca na klasyfikacji jakości energii z wykorzystaniem transformaty falkowej i modelu drzewa)