Published Paper Details:

In this paper, Maximal overlap discrete Wavelet Transform (MODWT) has been implemented along with the traditional discrete wavelet transform (DWT) for the detection and localization of different types of power quality (PQ) disturbance signals. Each of the signal has been decomposed up to fourth level with both the MODWT and DWT. The co-efficients of both MODWT and DWT decomposition have been further used for classification. The selected features have been extracted from the detail coefficient of the variants of WT and then given as inputs to the data mining classifiers for characterization of the signals. Moreover, a comparative assessment of the PQ signal has been carried out with different classifiers such as Decision Tree (DT) and Random Forest (RF) have been implemented along with aforementioned detection techniques. The ensemble decision tree named RF has been used for the classification of large number of data set. Various single as well as combined power quality disturbance signals have been simulated in noisy and noise free environment in order to demonstrate the efficiency of the proposed techniques. Moreover, in order to represent in realistic environment, these techniques have been tested with tree phase signals captured from transmission line panels.