Fault Line Selection Method Based on Transfer Learning Depthwise Separable Convolutional Neural Network

With the continuous development of artificial intelligence technology, the value of massive power data has been widely considered. Aiming at the problem of single-phase-to-ground fault line selection in resonant grounding system, a fault line selection method based on transfer learning depthwise sep...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Haixia Zhang, Wenao Cheng
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi Limited 2021
Materias:	Computer engineering. Computer hardware TK7885-7895
Acceso en línea:	https://doaj.org/article/c1a75984fd57445f89696b6f9a57053f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c1a75984fd57445f89696b6f9a57053f
record_format	dspace
spelling	oai:doaj.org-article:c1a75984fd57445f89696b6f9a57053f2021-11-22T01:11:19ZFault Line Selection Method Based on Transfer Learning Depthwise Separable Convolutional Neural Network2090-015510.1155/2021/9979634https://doaj.org/article/c1a75984fd57445f89696b6f9a57053f2021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/9979634https://doaj.org/toc/2090-0155With the continuous development of artificial intelligence technology, the value of massive power data has been widely considered. Aiming at the problem of single-phase-to-ground fault line selection in resonant grounding system, a fault line selection method based on transfer learning depthwise separable convolutional neural network (DSCNN) is proposed. The proposed method uses two pixel-level image fusions to transform the three-phase current of each feeder into the RGB color image, which is used as the input of DSCNN. After DSCNN self-feature extraction, the fault line selection is completed. With the consideration that not all of power distribution systems can obtain a large amount of data in practical applications, the transfer learning strategy is adopted to transplant the trained line selection model. The smaller number of DSCNN parameters increases the portability of the model. The test results show that not only does the proposed method extracts obvious features, but also the line selection accuracy can reach 99.76%. It also has good adaptability under different sampling frequencies, different noise environments, and different distribution network topologies; the line selection accuracy can reach more than 97.43%.Haixia ZhangWenao ChengHindawi LimitedarticleComputer engineering. Computer hardwareTK7885-7895ENJournal of Electrical and Computer Engineering, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer engineering. Computer hardware TK7885-7895
spellingShingle	Computer engineering. Computer hardware TK7885-7895 Haixia Zhang Wenao Cheng Fault Line Selection Method Based on Transfer Learning Depthwise Separable Convolutional Neural Network
description	With the continuous development of artificial intelligence technology, the value of massive power data has been widely considered. Aiming at the problem of single-phase-to-ground fault line selection in resonant grounding system, a fault line selection method based on transfer learning depthwise separable convolutional neural network (DSCNN) is proposed. The proposed method uses two pixel-level image fusions to transform the three-phase current of each feeder into the RGB color image, which is used as the input of DSCNN. After DSCNN self-feature extraction, the fault line selection is completed. With the consideration that not all of power distribution systems can obtain a large amount of data in practical applications, the transfer learning strategy is adopted to transplant the trained line selection model. The smaller number of DSCNN parameters increases the portability of the model. The test results show that not only does the proposed method extracts obvious features, but also the line selection accuracy can reach 99.76%. It also has good adaptability under different sampling frequencies, different noise environments, and different distribution network topologies; the line selection accuracy can reach more than 97.43%.
format	article
author	Haixia Zhang Wenao Cheng
author_facet	Haixia Zhang Wenao Cheng
author_sort	Haixia Zhang
title	Fault Line Selection Method Based on Transfer Learning Depthwise Separable Convolutional Neural Network
title_short	Fault Line Selection Method Based on Transfer Learning Depthwise Separable Convolutional Neural Network
title_full	Fault Line Selection Method Based on Transfer Learning Depthwise Separable Convolutional Neural Network
title_fullStr	Fault Line Selection Method Based on Transfer Learning Depthwise Separable Convolutional Neural Network
title_full_unstemmed	Fault Line Selection Method Based on Transfer Learning Depthwise Separable Convolutional Neural Network
title_sort	fault line selection method based on transfer learning depthwise separable convolutional neural network
publisher	Hindawi Limited
publishDate	2021
url	https://doaj.org/article/c1a75984fd57445f89696b6f9a57053f
work_keys_str_mv	AT haixiazhang faultlineselectionmethodbasedontransferlearningdepthwiseseparableconvolutionalneuralnetwork AT wenaocheng faultlineselectionmethodbasedontransferlearningdepthwiseseparableconvolutionalneuralnetwork
_version_	1718418305161625600

Fault Line Selection Method Based on Transfer Learning Depthwise Separable Convolutional Neural Network

Ejemplares similares