Defect Detection of Photovoltaic Modules Based on Convolutional Neural Network

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

Machine Learning and Intelligent Communications. Second International Conference, MLICOM 2017, Weihai, China, August 5-6, 2017, Proceedings, Part I

Research Article

Defect Detection of Photovoltaic Modules Based on Convolutional Neural Network

Download

599 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.1007/978-3-319-73564-1_13,
    author={Mingjian Sun and Shengmiao Lv and Xue Zhao and Ruya Li and Wenhan Zhang and Xiao Zhang},
    title={Defect Detection of Photovoltaic Modules Based on Convolutional Neural Network},
    proceedings={Machine Learning and Intelligent Communications. Second International Conference, MLICOM 2017, Weihai, China, August 5-6, 2017, Proceedings, Part I},
    proceedings_a={MLICOM},
    year={2018},
    month={2},
    keywords={Convolutional Neural Network PV module cracks Defect detection Deep learning},
    doi={10.1007/978-3-319-73564-1_13}
}

Mingjian Sun
Shengmiao Lv
Xue Zhao
Ruya Li
Wenhan Zhang
Xiao Zhang
Year: 2018
Defect Detection of Photovoltaic Modules Based on Convolutional Neural Network
MLICOM
Springer
DOI: 10.1007/978-3-319-73564-1_13

Mingjian Sun¹^,*, Shengmiao Lv¹, Xue Zhao¹, Ruya Li¹, Wenhan Zhang¹, Xiao Zhang¹

1: Harbin Institute of Technology at Weihai

*Contact email: sunmingjian@hit.edu.cn

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 PV module cracks Defect detection Deep learning

Published: 2018-02-09
Appears in: SpringerLink

: http://dx.doi.org/10.1007/978-3-319-73564-1_13