Publication:
Electroluminescence Images for Solar Cell Fault Detection Using Deep Learning for Binary and Multiclass Classification

Simple item page
dc.citedby2
dc.contributor.authorAlmashhadani R.A.I.en_US
dc.contributor.authorHock G.C.en_US
dc.contributor.authorNordin F.H.B.en_US
dc.contributor.authorAbdulrazzak H.N.en_US
dc.contributor.authorid57223341022en_US
dc.contributor.authorid16021614500en_US
dc.contributor.authorid25930510500en_US
dc.contributor.authorid57210449807en_US
dc.date.accessioned2025-03-03T07:43:33Z
dc.date.available2025-03-03T07:43:33Z
dc.date.issued2024
dc.description.abstractIn this study, an automatic solar defect detection and classification system using deep learning was proposed. This study focuses on solar faults in photovoltaic systems identified through Electroluminescence (EL) images by employing a deep learning framework that utilizes both traditional Convolutional Neural Networks (CNNs) and a pre-trained VGG16 and VGG-19 network for feature extraction. This approach was designed to enhance the accuracy and efficiency of solar defect classification. The framework is structured into three main phases: image preprocessing, feature extraction using CNNs, Histogram of Oriented Gradients (HOG) and Artificial Neural Networks (ANN), and classification through a Deep Neural Network (DNN). During preprocessing, images are scaled down to uniform dimensions to ensure consistent learning. They adopted two classification strategies: binary classification (defective or non-defective) and multiclass classification; the class names are 0%, 33%, 67%, and 100% (here, % represents the percentage of defectiveness), which represents the defect likelihood. To refine the model?s performance, a data augmentation technique has been utilized on the dataset. The effectiveness of the model was evaluated using various metrics, including the precision, recall, F1-score, and accuracy for two and four classes and obtained on, supported by confusion matrices. VGG-19 model outperformed other models and achieved precision, recall, F1-score and accuracy of 90% each for two classes respectively and similarly 94% for four classes. This study compares two classification methods to assess the ability of the deep learning framework to detect and classify solar defect images automatically. ? 2024 Seventh Sense Research Group. All rights reserved.en_US
dc.description.natureFinalen_US
dc.identifier.doi10.14445/23488379/IJEEE-V11I5P114
dc.identifier.epage160
dc.identifier.issue5-May
dc.identifier.scopus2-s2.0-85195444937
dc.identifier.spage150
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85195444937&doi=10.14445%2f23488379%2fIJEEE-V11I5P114&partnerID=40&md5=173dd2329f3f0e036eb0de55cb8c85f0
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/36635
dc.identifier.volume11
dc.pagecount10
dc.publisherSeventh Sense Research Groupen_US
dc.relation.ispartofAll Open Access; Hybrid Gold Open Access
dc.sourceScopus
dc.sourcetitleSSRG International Journal of Electrical and Electronics Engineering
dc.titleElectroluminescence Images for Solar Cell Fault Detection Using Deep Learning for Binary and Multiclass Classificationen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS