Staff View: A Multi-Layer Deep Learning System for Fault Detection Solar Cell Electroluminescence Images

A Multi-Layer Deep Learning System for Fault Detection Solar Cell Electroluminescence Images

An automatic solar defect detection with a classification system was proposed using deep learning. This paper focuses on solar defects in photovoltaic systems identified through electroluminescence (EL) images. Convolutional Neural Networks (CNNS), Artificial Neural Networks (ANN), Support Vector Ma...

Full description

Saved in:

Bibliographic Details
Main Authors:	Almashhadani R., Hock G.C., Hani Nordin F., Abdulrazzak H.N., Ali Abbas Z.
Other Authors:	57223341022
Format:	Conference paper
Published:	IEEE Computer Society 2025
Subjects:	Convolutional neural networks Deep neural networks Multilayer neural networks Classification system Convolutional neural network Defect detection Electroluminescence images Faults detection Multi-layers Neural-networks Photovoltaic systems Photovoltaics VGG16 Support vector machines
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.uniten.dspace-36852
record_format	dspace
spelling	my.uniten.dspace-368522025-03-03T15:45:12Z A Multi-Layer Deep Learning System for Fault Detection Solar Cell Electroluminescence Images Almashhadani R. Hock G.C. Hani Nordin F. Abdulrazzak H.N. Ali Abbas Z. 57223341022 16021614500 59558916700 57210449807 59558170700 Convolutional neural networks Deep neural networks Multilayer neural networks Classification system Convolutional neural network Defect detection Electroluminescence images Faults detection Multi-layers Neural-networks Photovoltaic systems Photovoltaics VGG16 Support vector machines An automatic solar defect detection with a classification system was proposed using deep learning. This paper focuses on solar defects in photovoltaic systems identified through electroluminescence (EL) images. Convolutional Neural Networks (CNNS), Artificial Neural Networks (ANN), Support Vector Machine (SVM), and a pre-trained VGG16 network for feature extraction were compared in this paper. They adopted two classification strategies: binary classification (defective or non-defective) and multi-class classification the class names are 0%, 33%, 67%, and 100% (here % represents the percentage of defectiveness), which represents the defect likelihood. The effectiveness of the model was evaluated using various metrics, including the recall, precision, accuracy, and F1-score for two and four classes and obtained on, supported by confusion matrices. VGG-16 model outperformed other models and achieved an accuracy of 89% for 2-classes and 93% for 4-classes. ? 2024 IEEE. Final 2025-03-03T07:45:12Z 2025-03-03T07:45:12Z 2024 Conference paper 10.1109/ICAST61769.2024.10856497 2-s2.0-85217832164 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85217832164&doi=10.1109%2fICAST61769.2024.10856497&partnerID=40&md5=a74fa60fa8a616a1b076433d2e906c9c https://irepository.uniten.edu.my/handle/123456789/36852 IEEE Computer Society Scopus
institution	Universiti Tenaga Nasional
building	UNITEN Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Tenaga Nasional
content_source	UNITEN Institutional Repository
url_provider	http://dspace.uniten.edu.my/
topic	Convolutional neural networks Deep neural networks Multilayer neural networks Classification system Convolutional neural network Defect detection Electroluminescence images Faults detection Multi-layers Neural-networks Photovoltaic systems Photovoltaics VGG16 Support vector machines
spellingShingle	Convolutional neural networks Deep neural networks Multilayer neural networks Classification system Convolutional neural network Defect detection Electroluminescence images Faults detection Multi-layers Neural-networks Photovoltaic systems Photovoltaics VGG16 Support vector machines Almashhadani R. Hock G.C. Hani Nordin F. Abdulrazzak H.N. Ali Abbas Z. A Multi-Layer Deep Learning System for Fault Detection Solar Cell Electroluminescence Images
description	An automatic solar defect detection with a classification system was proposed using deep learning. This paper focuses on solar defects in photovoltaic systems identified through electroluminescence (EL) images. Convolutional Neural Networks (CNNS), Artificial Neural Networks (ANN), Support Vector Machine (SVM), and a pre-trained VGG16 network for feature extraction were compared in this paper. They adopted two classification strategies: binary classification (defective or non-defective) and multi-class classification the class names are 0%, 33%, 67%, and 100% (here % represents the percentage of defectiveness), which represents the defect likelihood. The effectiveness of the model was evaluated using various metrics, including the recall, precision, accuracy, and F1-score for two and four classes and obtained on, supported by confusion matrices. VGG-16 model outperformed other models and achieved an accuracy of 89% for 2-classes and 93% for 4-classes. ? 2024 IEEE.
author2	57223341022
author_facet	57223341022 Almashhadani R. Hock G.C. Hani Nordin F. Abdulrazzak H.N. Ali Abbas Z.
format	Conference paper
author	Almashhadani R. Hock G.C. Hani Nordin F. Abdulrazzak H.N. Ali Abbas Z.
author_sort	Almashhadani R.
title	A Multi-Layer Deep Learning System for Fault Detection Solar Cell Electroluminescence Images
title_short	A Multi-Layer Deep Learning System for Fault Detection Solar Cell Electroluminescence Images
title_full	A Multi-Layer Deep Learning System for Fault Detection Solar Cell Electroluminescence Images
title_fullStr	A Multi-Layer Deep Learning System for Fault Detection Solar Cell Electroluminescence Images
title_full_unstemmed	A Multi-Layer Deep Learning System for Fault Detection Solar Cell Electroluminescence Images
title_sort	multi-layer deep learning system for fault detection solar cell electroluminescence images
publisher	IEEE Computer Society
publishDate	2025
_version_	1825816196266590208
score	13.244413

A Multi-Layer Deep Learning System for Fault Detection Solar Cell Electroluminescence Images

Similar Items