Automatic identification of power quality events using a machine learning approach

Fuente: Redalyc
Saved in:
Bibliographic Details
Main Author: A. F. Valencia-Duque
Format: Artículo científico
Language:en
Published: Universidad Tecnológica de Pereira 2019
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1876449588019200000
author A. F. Valencia-Duque
author_facet A. F. Valencia-Duque
contents Automatic identification of power quality events using a machine learning approach A. F. Valencia-Duque A. M. Álvarez Meza A. A. Orozco-Gutiérrez Ingeniería time frequency power quality domain features Machine learning In nowadays, Power Quality (PQ) events have been studied because they represent an essential aspect for the industries concerning the efficiency and the useful life of the elements connected to electrical systems. If the disturbances related to PQ events are classified (identified) fast and with reliable accuracy, the costs and losses generated would be reduced. In this paper, we present a machine learning-based approach to identify PQ events. Our proposal comprises the following stages: we employ a feature representation space based on time and frequency parameters. Besides, we include a supervised relevance analysis technique, called Relieff, to highlight the discriminant capability of the considered features. Then, we evaluate the success of classifying PQ events with different classifiers by adding different levels of noise under a cross-validation scheme. For concrete testing, a synthetic database based on the IEEE 1159 standard is generated, considering 3000 signals and ten classes (300 samples per class). Remarkably, obtained results show a suitable classification performance holding straightforward classifiers, e.g., quadratic and k-NN, in comparison to those state-of-the-art methodologies. 2019 artículo científico 0122-1701 https://www.redalyc.org/articulo.oa?id=84961237006 https://www.redalyc.org/journal/849/84961237006/ https://www.redalyc.org/journal/849/84961237006/html/ https://www.redalyc.org/journal/849/84961237006/84961237006.epub https://www.redalyc.org/journal/849/84961237006/movil en http://www.redalyc.org/revista.oa?id=849 Scientia Et Technica application/pdf Universidad Tecnológica de Pereira Scientia Et Technica (Colombia) Num.2 Vol.24
format Artículo científico
id redalyc_84961237006
institution Redalyc
language en
publishDate 2019
publisher Universidad Tecnológica de Pereira
spellingShingle Automatic identification of power quality events using a machine learning approach
A. F. Valencia-Duque
Ingeniería
time
frequency
power quality
domain features
Machine learning
Automatic identification of power quality events using a machine learning approach A. F. Valencia-Duque A. M. Álvarez Meza A. A. Orozco-Gutiérrez Ingeniería time frequency power quality domain features Machine learning In nowadays, Power Quality (PQ) events have been studied because they represent an essential aspect for the industries concerning the efficiency and the useful life of the elements connected to electrical systems. If the disturbances related to PQ events are classified (identified) fast and with reliable accuracy, the costs and losses generated would be reduced. In this paper, we present a machine learning-based approach to identify PQ events. Our proposal comprises the following stages: we employ a feature representation space based on time and frequency parameters. Besides, we include a supervised relevance analysis technique, called Relieff, to highlight the discriminant capability of the considered features. Then, we evaluate the success of classifying PQ events with different classifiers by adding different levels of noise under a cross-validation scheme. For concrete testing, a synthetic database based on the IEEE 1159 standard is generated, considering 3000 signals and ten classes (300 samples per class). Remarkably, obtained results show a suitable classification performance holding straightforward classifiers, e.g., quadratic and k-NN, in comparison to those state-of-the-art methodologies. 2019 artículo científico 0122-1701 https://www.redalyc.org/articulo.oa?id=84961237006 https://www.redalyc.org/journal/849/84961237006/ https://www.redalyc.org/journal/849/84961237006/html/ https://www.redalyc.org/journal/849/84961237006/84961237006.epub https://www.redalyc.org/journal/849/84961237006/movil en http://www.redalyc.org/revista.oa?id=849 Scientia Et Technica application/pdf Universidad Tecnológica de Pereira Scientia Et Technica (Colombia) Num.2 Vol.24
title Automatic identification of power quality events using a machine learning approach
topic Ingeniería
time
frequency
power quality
domain features
Machine learning
url https://www.redalyc.org/articulo.oa?id=84961237006
https://www.redalyc.org/journal/849/84961237006/
https://www.redalyc.org/journal/849/84961237006/html/
https://www.redalyc.org/journal/849/84961237006/84961237006.epub
https://www.redalyc.org/journal/849/84961237006/movil