Automatic Detection of Display Defects for Smart Meters based on Deep Learning

The smart meter is an essential part of an intelligent grid system. Defects in the LCD screen the smart meters affect their use. Therefore, detection of LCD screen defects of smart meters is of great significance for management and use of smart electricity meters. At present, detection methods are m...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ye Chen, Zhihu Hong, Yaohua Liao, Mengmeng Zhu, Tong Han, Quan Shen
Formato:	article
Lenguaje:	EN
Publicado:	University of Zagreb Faculty of Electrical Engineering and Computing 2020
Materias:	smart meter display defects YOLOv5 ResNet34 Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/ffbbbba24bae4cbc8dd47eaf4896e96d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ffbbbba24bae4cbc8dd47eaf4896e96d
record_format	dspace
spelling	oai:doaj.org-article:ffbbbba24bae4cbc8dd47eaf4896e96d2021-12-02T18:10:33ZAutomatic Detection of Display Defects for Smart Meters based on Deep Learning1330-11361846-3908https://doaj.org/article/ffbbbba24bae4cbc8dd47eaf4896e96d2020-01-01T00:00:00Zhttps://hrcak.srce.hr/file/384991https://doaj.org/toc/1330-1136https://doaj.org/toc/1846-3908The smart meter is an essential part of an intelligent grid system. Defects in the LCD screen the smart meters affect their use. Therefore, detection of LCD screen defects of smart meters is of great significance for management and use of smart electricity meters. At present, detection methods are mainly realized by manual detection and automatic detection based on machine vision. However, performance of these two methods is not satisfactory. The fault detection task of a smart meter LCD screen can be divided into two parts: smart meter LCD localization and LCD fault detection. Therefore, this paper proposes a twostage system based on deep learning, which combines YOLOv5 with ResNet34. YOLOv5 is used for smart meter LCD localization and the classification network based on ResNet34 for LCD fault detection. We have constructed an LCD screen localization dataset and an LCD screen defect detection dataset to train and test our model. As a result, our model achieves a defect detection accuracy of 98.9% on the dataset proposed in this paper and can accurately detect the common defects of an LCD screen.Ye ChenZhihu HongYaohua LiaoMengmeng ZhuTong HanQuan ShenUniversity of Zagreb Faculty of Electrical Engineering and Computingarticlesmart meterdisplay defectsYOLOv5ResNet34Electronic computers. Computer scienceQA75.5-76.95ENJournal of Computing and Information Technology, Vol 28, Iss 4, Pp 241-254 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	smart meter display defects YOLOv5 ResNet34 Electronic computers. Computer science QA75.5-76.95
spellingShingle	smart meter display defects YOLOv5 ResNet34 Electronic computers. Computer science QA75.5-76.95 Ye Chen Zhihu Hong Yaohua Liao Mengmeng Zhu Tong Han Quan Shen Automatic Detection of Display Defects for Smart Meters based on Deep Learning
description	The smart meter is an essential part of an intelligent grid system. Defects in the LCD screen the smart meters affect their use. Therefore, detection of LCD screen defects of smart meters is of great significance for management and use of smart electricity meters. At present, detection methods are mainly realized by manual detection and automatic detection based on machine vision. However, performance of these two methods is not satisfactory. The fault detection task of a smart meter LCD screen can be divided into two parts: smart meter LCD localization and LCD fault detection. Therefore, this paper proposes a twostage system based on deep learning, which combines YOLOv5 with ResNet34. YOLOv5 is used for smart meter LCD localization and the classification network based on ResNet34 for LCD fault detection. We have constructed an LCD screen localization dataset and an LCD screen defect detection dataset to train and test our model. As a result, our model achieves a defect detection accuracy of 98.9% on the dataset proposed in this paper and can accurately detect the common defects of an LCD screen.
format	article
author	Ye Chen Zhihu Hong Yaohua Liao Mengmeng Zhu Tong Han Quan Shen
author_facet	Ye Chen Zhihu Hong Yaohua Liao Mengmeng Zhu Tong Han Quan Shen
author_sort	Ye Chen
title	Automatic Detection of Display Defects for Smart Meters based on Deep Learning
title_short	Automatic Detection of Display Defects for Smart Meters based on Deep Learning
title_full	Automatic Detection of Display Defects for Smart Meters based on Deep Learning
title_fullStr	Automatic Detection of Display Defects for Smart Meters based on Deep Learning
title_full_unstemmed	Automatic Detection of Display Defects for Smart Meters based on Deep Learning
title_sort	automatic detection of display defects for smart meters based on deep learning
publisher	University of Zagreb Faculty of Electrical Engineering and Computing
publishDate	2020
url	https://doaj.org/article/ffbbbba24bae4cbc8dd47eaf4896e96d
work_keys_str_mv	AT yechen automaticdetectionofdisplaydefectsforsmartmetersbasedondeeplearning AT zhihuhong automaticdetectionofdisplaydefectsforsmartmetersbasedondeeplearning AT yaohualiao automaticdetectionofdisplaydefectsforsmartmetersbasedondeeplearning AT mengmengzhu automaticdetectionofdisplaydefectsforsmartmetersbasedondeeplearning AT tonghan automaticdetectionofdisplaydefectsforsmartmetersbasedondeeplearning AT quanshen automaticdetectionofdisplaydefectsforsmartmetersbasedondeeplearning
_version_	1718378610046271488

Automatic Detection of Display Defects for Smart Meters based on Deep Learning

Ejemplares similares