Comparison of Empirical Mode Decomposition and Wavelet Based Classification of Power Quality Events

Abstract

This paper presents a novel method of power quality events classification like sag, swell, harmonics, flicker, notch etc based on Empirical Mode Decomposition (EMD) with Hilbert Transform (HT). EMD decomposes the disturbance signal into different mono component and symmetric component signals by sifting process. These mono component signals are called Intrinsic Mode Functions (IMFs) i.e. they are composed of single frequency or narrow band of frequencies. The magnitude plot of the Hilbert transform of the first IMF can correctly detect the disturbance. The characteristic features of the first three IMFs of each disturbance are used as inputs to Probabilistic Neural Network (PNN) for identification of the disturbances. A comparison is made with wavelet transform. Simulation results show that EMD method effectively classifies the power quality disturbances.