Multi-Label Classification for Power Quality Disturbances by Integrated Deep Learning

The traditional power quality disturbances classification methods include three stages, i.e., feature extraction, feature selection, classifier training. These methods suffer from low accuracy and a limited improvement margin. Since deep learning can greatly improve the accuracy of classification, a...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xiangui Xiao, Kaicheng Li
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Power quality disturbances deep learning CNN ResNet multi-label learning Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/d8775a8e800140b0b425564cadf68c0b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d8775a8e800140b0b425564cadf68c0b
record_format	dspace
spelling	oai:doaj.org-article:d8775a8e800140b0b425564cadf68c0b2021-11-20T00:02:47ZMulti-Label Classification for Power Quality Disturbances by Integrated Deep Learning2169-353610.1109/ACCESS.2021.3124511https://doaj.org/article/d8775a8e800140b0b425564cadf68c0b2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9597531/https://doaj.org/toc/2169-3536The traditional power quality disturbances classification methods include three stages, i.e., feature extraction, feature selection, classifier training. These methods suffer from low accuracy and a limited improvement margin. Since deep learning can greatly improve the accuracy of classification, a new classification method was designed in this paper by combining three types of deep learning frameworks, including CNN-GRU, ResNet-GRU, and Inception-GRU. The proposed method omits the two steps of feature extraction and feature selection, achieving “end-to-end” PQDs identification. To improve the performance on real signals, “pre-training and re-training” is applied. Then, a voting method was employed to vote the prediction labels by different algorithms, which further improves the accuracy of classification. Simulation experiments show that for the classification of compound PQDs, the proposed method performs better than the triple-stage methods and single deep learning classification method. Finally, real signals from Power source are test by the twice-trained model, and the five metrics are better than the old methods.Xiangui XiaoKaicheng LiIEEEarticlePower quality disturbancesdeep learningCNNResNetmulti-label learningElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 152250-152260 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Power quality disturbances deep learning CNN ResNet multi-label learning Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Power quality disturbances deep learning CNN ResNet multi-label learning Electrical engineering. Electronics. Nuclear engineering TK1-9971 Xiangui Xiao Kaicheng Li Multi-Label Classification for Power Quality Disturbances by Integrated Deep Learning
description	The traditional power quality disturbances classification methods include three stages, i.e., feature extraction, feature selection, classifier training. These methods suffer from low accuracy and a limited improvement margin. Since deep learning can greatly improve the accuracy of classification, a new classification method was designed in this paper by combining three types of deep learning frameworks, including CNN-GRU, ResNet-GRU, and Inception-GRU. The proposed method omits the two steps of feature extraction and feature selection, achieving “end-to-end” PQDs identification. To improve the performance on real signals, “pre-training and re-training” is applied. Then, a voting method was employed to vote the prediction labels by different algorithms, which further improves the accuracy of classification. Simulation experiments show that for the classification of compound PQDs, the proposed method performs better than the triple-stage methods and single deep learning classification method. Finally, real signals from Power source are test by the twice-trained model, and the five metrics are better than the old methods.
format	article
author	Xiangui Xiao Kaicheng Li
author_facet	Xiangui Xiao Kaicheng Li
author_sort	Xiangui Xiao
title	Multi-Label Classification for Power Quality Disturbances by Integrated Deep Learning
title_short	Multi-Label Classification for Power Quality Disturbances by Integrated Deep Learning
title_full	Multi-Label Classification for Power Quality Disturbances by Integrated Deep Learning
title_fullStr	Multi-Label Classification for Power Quality Disturbances by Integrated Deep Learning
title_full_unstemmed	Multi-Label Classification for Power Quality Disturbances by Integrated Deep Learning
title_sort	multi-label classification for power quality disturbances by integrated deep learning
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/d8775a8e800140b0b425564cadf68c0b
work_keys_str_mv	AT xianguixiao multilabelclassificationforpowerqualitydisturbancesbyintegrateddeeplearning AT kaichengli multilabelclassificationforpowerqualitydisturbancesbyintegrateddeeplearning
_version_	1718419867096317952

Multi-Label Classification for Power Quality Disturbances by Integrated Deep Learning

Ejemplares similares