Photovoltaic Panel Defect Detection System
Journal of Applied Science, Engineering, Technology and Management · 30.05.2026 · 4 (1) · 13-18
DOI: 10.61779/jasetm.v4i1.3 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Applied Science, Engineering, Technology and Management, online erschienen am 30.05.2026. Verfasst von Safwa Samad und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Detecting defects in photovoltaic (PV) panels is important for maintaining their performance, especially in large-scale solar farms where manual inspection is time-consuming and inefficient. This work presents a simple and practical deep learning solution that makes this process easier and more accessible by using images captured through UAVs (drones), enabling efficient monitoring of large areas. A customized YOLOv8m-based model is designed to automatically detect and classify defects, even with a relatively small dataset of around 700–800 images across five categories. To handle the lack of data, class-based GAN augmentation is used to increase data variety and improve balance between classes. The model is further improved with additions like a C2f-PSA module for better attention and a custom Multi-Scale Feature Fusion (MCFF) block to help detect small and hard-to-spot defects. While these improvements enhance the model’s ability to learn features, they also make it more sensitive to dataset size and design choices, sometimes affecting accuracy. To make the system useful in real-world situations, a user-friendly web application and dashboard are developed using Streamlit, allowing users to upload images, see detected defects with their severity levels, and easily understand the results. The system also enables users to generate and download detailed reports with annotated images, making it a complete and practical solution for efficient PV panel monitoring and maintenance in large solar installations.
Zitieren
APA
Samad, S., Anjali, N. B., Hashim, O. A. M., Nidheesh, A., & Mohyiddeen, M. (2026). Photovoltaic Panel Defect Detection System. Journal of Applied Science, Engineering, Technology and Management, 4(1), 13-18. https://doi.org/10.61779/jasetm.v4i1.3
Vancouver
Samad S, Anjali NB, Hashim OAM, Nidheesh A, Mohyiddeen M. Photovoltaic Panel Defect Detection System. Journal of Applied Science, Engineering, Technology and Management. 2026;4(1):13-18. doi:10.61779/jasetm.v4i1.3
BibTeX
@article{Samad2026,
author = {Samad, Safwa and Anjali, N B and Hashim, O A Mohammed and Nidheesh, Adwaith and Mohyiddeen, Muneebah},
title = {Photovoltaic Panel Defect Detection System},
journal = {Journal of Applied Science, Engineering, Technology and Management},
year = {2026},
volume = {4},
number = {1},
pages = {13--18},
doi = {10.61779/jasetm.v4i1.3}
}
EUVIMED