Deep learning in defects detection of PV modules: A review
Identifying defects in photovoltaic (PV) modules is essential for ensuring optimal performance and prolonging their operational lifespan. Traditional manual inspection methods are time-consuming, labor-intensive, and subject to human error, necessitating the development of automated, efficient detec...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Solar Energy Advances |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667113125000038 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206911643942912 |
|---|---|
| author | Katleho Masita Ali Hasan Thokozani Shongwe Hasan Abu Hilal |
| author_facet | Katleho Masita Ali Hasan Thokozani Shongwe Hasan Abu Hilal |
| author_sort | Katleho Masita |
| collection | DOAJ |
| description | Identifying defects in photovoltaic (PV) modules is essential for ensuring optimal performance and prolonging their operational lifespan. Traditional manual inspection methods are time-consuming, labor-intensive, and subject to human error, necessitating the development of automated, efficient detection techniques. With the increasing scale of PV power plants, there is a pressing need for automated, accurate, and efficient defect detection methods. This review explores the application of deep learning (DL) methods, particularly convolutional neural networks (CNNs), in the identification and classification of PV module defects. Var- ious imaging techniques, including electroluminescence (EL), thermal, and visible spectrum imaging, are discussed for their roles in data acquisition. The importance of preprocessing steps such as image normalization, registration, and segmentation is emphasized to enhance detection accuracy. The review highlights the effectiveness of DL models like MobileNet, VGG-16, and YOLO, and techniques such as transfer learning and data augmentation in improving model performance. Despite achieving high accuracy, challenges such as the need for large datasets and model generalization across different PV modules and environmental conditions remain. The integration of DL with aerial inspection technologies and advance- ments in image processing holds promise for further enhancing the reliability and efficiency of solar energy systems. |
| format | Article |
| id | doaj-art-ea680747d2fa4af2b88a85068fc0ad3f |
| institution | Kabale University |
| issn | 2667-1131 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Solar Energy Advances |
| spelling | doaj-art-ea680747d2fa4af2b88a85068fc0ad3f2025-02-07T04:48:30ZengElsevierSolar Energy Advances2667-11312025-01-015100090Deep learning in defects detection of PV modules: A reviewKatleho Masita0Ali Hasan1Thokozani Shongwe2Hasan Abu Hilal3Electrical and Electronic Engineering Science Department, University of Johannesburg, Johannesburg, South Africa; Corresponding author.Electrical and Electronic Engineering Science Department, University of Johannesburg, Johannesburg, South AfricaElectrical and Electronic Engineering Science Department, University of Johannesburg, Johannesburg, South AfricaElectrical and Electronic Engineering Department, Eastern Mediterranean University, North Cyprus, 99628, Famagusta, CyprusIdentifying defects in photovoltaic (PV) modules is essential for ensuring optimal performance and prolonging their operational lifespan. Traditional manual inspection methods are time-consuming, labor-intensive, and subject to human error, necessitating the development of automated, efficient detection techniques. With the increasing scale of PV power plants, there is a pressing need for automated, accurate, and efficient defect detection methods. This review explores the application of deep learning (DL) methods, particularly convolutional neural networks (CNNs), in the identification and classification of PV module defects. Var- ious imaging techniques, including electroluminescence (EL), thermal, and visible spectrum imaging, are discussed for their roles in data acquisition. The importance of preprocessing steps such as image normalization, registration, and segmentation is emphasized to enhance detection accuracy. The review highlights the effectiveness of DL models like MobileNet, VGG-16, and YOLO, and techniques such as transfer learning and data augmentation in improving model performance. Despite achieving high accuracy, challenges such as the need for large datasets and model generalization across different PV modules and environmental conditions remain. The integration of DL with aerial inspection technologies and advance- ments in image processing holds promise for further enhancing the reliability and efficiency of solar energy systems.http://www.sciencedirect.com/science/article/pii/S2667113125000038PV moduleSolarDroneDeep learningDefects detection |
| spellingShingle | Katleho Masita Ali Hasan Thokozani Shongwe Hasan Abu Hilal Deep learning in defects detection of PV modules: A review Solar Energy Advances PV module Solar Drone Deep learning Defects detection |
| title | Deep learning in defects detection of PV modules: A review |
| title_full | Deep learning in defects detection of PV modules: A review |
| title_fullStr | Deep learning in defects detection of PV modules: A review |
| title_full_unstemmed | Deep learning in defects detection of PV modules: A review |
| title_short | Deep learning in defects detection of PV modules: A review |
| title_sort | deep learning in defects detection of pv modules a review |
| topic | PV module Solar Drone Deep learning Defects detection |
| url | http://www.sciencedirect.com/science/article/pii/S2667113125000038 |
| work_keys_str_mv | AT katlehomasita deeplearningindefectsdetectionofpvmodulesareview AT alihasan deeplearningindefectsdetectionofpvmodulesareview AT thokozanishongwe deeplearningindefectsdetectionofpvmodulesareview AT hasanabuhilal deeplearningindefectsdetectionofpvmodulesareview |