Automatic Power Quality Disturbances Detection and Recognition Using Empirical Wavelet Transform and Random Forest Method

In this paper, empirical Wavelet transform (EWT), Hilbert transform (HT) and random forest (RF) are integrated to reorganized the signal as well as simulation of power quality disturbances (PQDs) in a real time. EWT is a method used to figure out series of amplitude modulated frequency modulated (AM-FM) signals for different given signal, known as detail and approximate coefficients. Hilbert transform (HT) is used to extract the productive features from the detail and approximation coefficients. The terms standard deviation of magnitude, Hilbert energy array, Shannon entropy and crest factor are extracted from the Hilbert array and train to classifier random forest. RF is a quintet learning technique used for classification and regression purposes. The algorithm commences with the selection of many bootstrap samples from the data. Furthermore, the proposed less computational complex and superior classification accuracy based EWTHT-RF method is implemented in the digital signal processor (DSP) based platform to validate the feasibility of the proposed method.