INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
Detection and classification of Real Time Power Quality Disturbance Signals with HMMs incorporating with SGWT Features
Authors Name:
S. Upadhyaya
Unique Id:
IJSDR1805112
Published In:
Volume 3 Issue 6, June-2018
Abstract:
In this paper, Second generation Wavelet Transform (SGWT) has been implemented along with the traditional discrete Wavelet Transform (DWT) for localization of different types of power quality (PQ) disturbance signals. Selected features have been extracted from the detail coefficient of the variants of WT and then fed as inputs to the classifiers in order to characterize the signals. Moreover, a comparative assessment of the PQ signal carried out with Multilayer perceptron (MLP) and Hidden Markov Models (HMMs). For localisation of power quality disturbances, the signals have been analysed upto four decomposition levels whereas for classification the signals are decomposed for seven decomposition levels. In order to represent in realistic environment, these proposed techniques are tested with the signals captured from transmission line panels. Further, to aid these PQ disturbance detection, different types of real time fault signals are also characterized with these aforementioned approaches.
Keywords:
-
Cite Article:
"Detection and classification of Real Time Power Quality Disturbance Signals with HMMs incorporating with SGWT Features", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.3, Issue 6, page no.730 - 742, June-2018, Available :http://www.ijsdr.org/papers/IJSDR1805112.pdf
Downloads:
000337070
Publication Details:
Published Paper ID: IJSDR1805112
Registration ID:180267
Published In: Volume 3 Issue 6, June-2018
DOI (Digital Object Identifier):
Page No: 730 - 742
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn