An approach for classification of power quality disturbances based on Hilbert Huang Transform and Relevance Vector Machine

This paper presents a new approach for power quality disturbances classification using Hilbert Huang Transform (HHT) and Relevance Vector Machine (RVM). A disturbed power signal is first analyzed in terms of intrinsic mode functions (IMFs) by Empirical mode decomposition (EMD). Considering the first three IMFs, the Hilbert transform is then applied to them to obtain HHT outcomes, namely instantaneous amplitude and phase, which are exploited to form the feature vector. The feature vector thus obtained when fed to a RVM classifier is found to effectively classify various classes of power quality disturbances. Simulation results through training and testing show that the proposed method using RVM classifier is superior in performance in comparison to the methods using k nearest neighbour (k-NN) or Support Vector Machine (SVM) as a classifier.