Defect detection of photovoltaic modules based on convolutional neural network

Mingjian Sun; Shengmiao Lv; Xue Zhao; Ruya Li; Wenhan Zhang; Xiao Zhang

doi:10.1007/978-3-319-73564-1_13

Defect detection of photovoltaic modules based on convolutional neural network

Mingjian Sun^*
, Shengmiao Lv
, Xue Zhao
, Ruya Li
, Wenhan Zhang
, Xiao Zhang

^*Corresponding author for this work

Harbin Institute of Technology Weihai

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

30 Scopus citations

Abstract

Deep learning is employed to detect defects in photovoltaic (PV) modules in the thesis. Firstly, the thesis introduces related concepts of cracks. Then a convolutional neural network with seven layers is constructed to classify the defective battery panels. Finally, the accuracy of the validation set is 98.35%. Besides, the thesis introduces a method in which a single battery cell can be extracted from the Electro Luminescence (EL) image of the PV module. This method is very suitable for automatic inspection of photovoltaic power plants.

Original language	English
Title of host publication	Machine Learning and Intelligent Communications - Second International Conference, MLICOM 2017, Proceedings
Editors	Xuemai Gu, Gongliang Liu, Bo Li
Publisher	Springer Verlag
Pages	122-132
Number of pages	11
ISBN (Print)	9783319735634
DOIs	https://doi.org/10.1007/978-3-319-73564-1_13
State	Published - 2018
Externally published	Yes
Event	2nd International Conference on Machine Learning and Intelligent Communications, MLICOM 2017 - Weihai, China Duration: 5 Aug 2017 → 6 Aug 2017

Publication series

Name	Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
Volume	226 LNICST
ISSN (Print)	1867-8211

Conference

Conference	2nd International Conference on Machine Learning and Intelligent Communications, MLICOM 2017
Country/Territory	China
City	Weihai
Period	5/08/17 → 6/08/17

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Convolutional neural network
Deep learning
Defect detection
PV module cracks

Access to Document

10.1007/978-3-319-73564-1_13

Cite this

Sun, M., Lv, S., Zhao, X., Li, R., Zhang, W., & Zhang, X. (2018). Defect detection of photovoltaic modules based on convolutional neural network. In X. Gu, G. Liu, & B. Li (Eds.), Machine Learning and Intelligent Communications - Second International Conference, MLICOM 2017, Proceedings (pp. 122-132). (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 226 LNICST). Springer Verlag. https://doi.org/10.1007/978-3-319-73564-1_13

Sun, Mingjian ; Lv, Shengmiao ; Zhao, Xue et al. / Defect detection of photovoltaic modules based on convolutional neural network. Machine Learning and Intelligent Communications - Second International Conference, MLICOM 2017, Proceedings. editor / Xuemai Gu ; Gongliang Liu ; Bo Li. Springer Verlag, 2018. pp. 122-132 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST).

@inproceedings{b5301a42e8b748878ab48181af0cdad8,

title = "Defect detection of photovoltaic modules based on convolutional neural network",

abstract = "Deep learning is employed to detect defects in photovoltaic (PV) modules in the thesis. Firstly, the thesis introduces related concepts of cracks. Then a convolutional neural network with seven layers is constructed to classify the defective battery panels. Finally, the accuracy of the validation set is 98.35\%. Besides, the thesis introduces a method in which a single battery cell can be extracted from the Electro Luminescence (EL) image of the PV module. This method is very suitable for automatic inspection of photovoltaic power plants.",

keywords = "Convolutional neural network, Deep learning, Defect detection, PV module cracks",

author = "Mingjian Sun and Shengmiao Lv and Xue Zhao and Ruya Li and Wenhan Zhang and Xiao Zhang",

note = "Publisher Copyright: {\textcopyright} ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2018.; 2nd International Conference on Machine Learning and Intelligent Communications, MLICOM 2017 ; Conference date: 05-08-2017 Through 06-08-2017",

year = "2018",

doi = "10.1007/978-3-319-73564-1\_13",

language = "英语",

isbn = "9783319735634",

series = "Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST",

publisher = "Springer Verlag",

pages = "122--132",

editor = "Xuemai Gu and Gongliang Liu and Bo Li",

booktitle = "Machine Learning and Intelligent Communications - Second International Conference, MLICOM 2017, Proceedings",

address = "德国",

}

Sun, M, Lv, S, Zhao, X, Li, R, Zhang, W & Zhang, X 2018, Defect detection of photovoltaic modules based on convolutional neural network. in X Gu, G Liu & B Li (eds), Machine Learning and Intelligent Communications - Second International Conference, MLICOM 2017, Proceedings. Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST, vol. 226 LNICST, Springer Verlag, pp. 122-132, 2nd International Conference on Machine Learning and Intelligent Communications, MLICOM 2017, Weihai, China, 5/08/17. https://doi.org/10.1007/978-3-319-73564-1_13

Defect detection of photovoltaic modules based on convolutional neural network. / Sun, Mingjian; Lv, Shengmiao; Zhao, Xue et al.
Machine Learning and Intelligent Communications - Second International Conference, MLICOM 2017, Proceedings. ed. / Xuemai Gu; Gongliang Liu; Bo Li. Springer Verlag, 2018. p. 122-132 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 226 LNICST).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Defect detection of photovoltaic modules based on convolutional neural network

AU - Sun, Mingjian

AU - Lv, Shengmiao

AU - Zhao, Xue

AU - Li, Ruya

AU - Zhang, Wenhan

AU - Zhang, Xiao

N1 - Publisher Copyright: © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2018.

PY - 2018

Y1 - 2018

N2 - Deep learning is employed to detect defects in photovoltaic (PV) modules in the thesis. Firstly, the thesis introduces related concepts of cracks. Then a convolutional neural network with seven layers is constructed to classify the defective battery panels. Finally, the accuracy of the validation set is 98.35%. Besides, the thesis introduces a method in which a single battery cell can be extracted from the Electro Luminescence (EL) image of the PV module. This method is very suitable for automatic inspection of photovoltaic power plants.

AB - Deep learning is employed to detect defects in photovoltaic (PV) modules in the thesis. Firstly, the thesis introduces related concepts of cracks. Then a convolutional neural network with seven layers is constructed to classify the defective battery panels. Finally, the accuracy of the validation set is 98.35%. Besides, the thesis introduces a method in which a single battery cell can be extracted from the Electro Luminescence (EL) image of the PV module. This method is very suitable for automatic inspection of photovoltaic power plants.

KW - Convolutional neural network

KW - Deep learning

KW - Defect detection

KW - PV module cracks

UR - https://www.scopus.com/pages/publications/85045202009

U2 - 10.1007/978-3-319-73564-1_13

DO - 10.1007/978-3-319-73564-1_13

M3 - 会议稿件

AN - SCOPUS:85045202009

SN - 9783319735634

T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST

SP - 122

EP - 132

BT - Machine Learning and Intelligent Communications - Second International Conference, MLICOM 2017, Proceedings

A2 - Gu, Xuemai

A2 - Liu, Gongliang

A2 - Li, Bo

PB - Springer Verlag

T2 - 2nd International Conference on Machine Learning and Intelligent Communications, MLICOM 2017

Y2 - 5 August 2017 through 6 August 2017

ER -

Sun M, Lv S, Zhao X, Li R, Zhang W, Zhang X. Defect detection of photovoltaic modules based on convolutional neural network. In Gu X, Liu G, Li B, editors, Machine Learning and Intelligent Communications - Second International Conference, MLICOM 2017, Proceedings. Springer Verlag. 2018. p. 122-132. (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST). doi: 10.1007/978-3-319-73564-1_13

Defect detection of photovoltaic modules based on convolutional neural network

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this