Photovoltaic Panel Defect Detection System
DOI:
https://doi.org/10.61779/jasetm.v4i1.3Keywords:
Photovoltaic Defect Detection, YOLOv8, GAN, PSA, MCFF, Deep Learning, Object DetectionAbstract
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.
References
W. Yin, L. Shen, M. Li, Q. Sun, and X. Li, “PV-YOLO: Lightweight YOLO for Photovoltaic Panel Fault Detection,” IEEE Access, vol. 11, pp. 10966–10974, 2023, doi: 10.1109/ACCESS.2023.3240894.
D. Lang and Z. Lv, “A PV cell defect detector combined with trans- former and attention mechanism,” Scientific Reports, vol. 14, no. 20671, pp. 1–14, 2024, doi: 10.1038/s41598-024-72019-5.
T. Sun, H. Xing, S. Cao, Y. Zhang, S. Fan, and P. Liu, “A novel detection method for hot spots of photovoltaic (PV) panels using improved anchors and prediction heads of YOLOv5 network,” Energy Reports, vol. 8, pp. 1219–1229, 2022, doi: 10.1016/j.egyr.2022.08.130.
H. Rao, Q. Li, L. Chen, S. Jin, Y. Lu, and Z. Li, “Defect Diagnosis of Photovoltaic Module Visible Light Images Under Imbalanced Sam- ple Conditions,” IEEE Access, vol. 13, pp. 99112–99120, 2025, doi: 10.1109/ACCESS.2025.3574334.
M. Zhang and L. Yin, “Solar Cell Surface Defect Detection Based on Improved YOLO v5,” IEEE Access, vol. 10, pp. 80804–80814, 2022, doi: 10.1109/ACCESS.2022.3195901.
X. Zhang, R. Yao, B. Jing, X. Jiao, and M. Ren, “Study on PV defect detection based on CWE-YOLOv8,” IEEE Access, vol. 13, pp. 74647–74657, 2025, doi: 10.1109/ACCESS.2025.3561044.
W. Pan, X. Sun, Y. Wang, Y. Cao, Y. Lang, and Y. Qian, “Enhanced photovoltaic panel defect detection via adaptive complementary fusion in YOLO-ACF,” Scientific Reports, vol. 14, no. 26425, pp. 1–13, 2024, doi: 10.1038/s41598-024-75772-9.
X. Xu, M. Liu, Y. Nie, K. Wang, and W. Xu, “Photovoltaic module fault detection technology based on remote sensing technology and Deeplabv3+ model,” IEEE Access, vol. 12, pp. 195472–195481, 2024, doi: 10.1109/ACCESS.2024.3515165.
C. Liang, S. Jiang, J. Yang, W. Hu, Y. Liu, P. Zhu, G. He, and C. Shi, “A distributed photovoltaic operation and maintenance cloud platform for PV aerial inspections with sparse industrial data,” IEEE Access, vol. 13, pp. 69677–69688, 2025, doi: 10.1109/ACCESS.2025.3561234.
L. S. Pinho, T. D. Sousa, C. D. Pereira, and A. M. Pinto, “Anomaly detection for PV modules using multi-modal data fusion in aerial inspections,” IEEE Access, vol. 13, pp. 88762–88775, 2025, doi: 10.1109/AC- CESS.2025.3570815.
Y. Jia, G. Chen, and L. Zhao, “Defect detection of photovoltaic modules based on improved VarifocalNet,” Scientific Reports, vol. 14, no. 15170, pp. 1–13, 2024, doi: 10.1038/s41598-024-66234-3.
J. S. J. C. Amorim, A. F. S. Neto, R. S. Chaves, A. R. L. Zachi, J. A. Gouveˆa, F. A. A. Andrade, and M. F. Pinto, “Collaborative inspection of solar panel farms using YOLOv5-based computer vision and UGV–UAV integration,” Journal of Intelligent Robotic Systems, vol. 111, no. 66, pp. 1–19, 2025, doi: 10.1007/s10846-025-02265-w.
E. Lodhi, X. Liu, G. Xiong, M. A. Khan, Z. Lodhi, T. Nawaz, A. Dilawar, S. Tarkoma, and F. Wang, “SmartPV-AIoT: An AIoT-integrated framework for fault diagnosis and remote monitoring in photovoltaic systems,” Energy Conversion and Management: X, vol. 27, no. 101117, pp. 1–23, 2025, doi: 10.1016/j.ecmx.2025.101117.
Y. Chen, M. Shan, W. Zhou, B. Ma, and X. Mei, “RT-DETR-Pro: An enhanced RT-DETR model for visual detection of photovoltaic module defects,” IEEE Access, vol. 13, pp. 116473–116480, 2025, doi: 10.1109/ACCESS.2025.3585151.
M. M. Rizwan, A. M. A. Khan, M. B. Sultan, and L. Ahmad, “Advancements in photovoltaic module defect detection using deep learning and infrared thermography,” Heliyon, vol. 11, no. 3, pp. e160346, 2025, doi: 10.1016/j.heliyon.2025.e160346.
P. R. Sonawane, S. Bhandari, R. B. Patil, and S. Al-Dahidi, “Comparative analysis of methods used to solve class imbalance problem in dataset for CNN-based fault diagnosis of solar photovoltaic panels,” Int. J. Thermofluids, vol. 28, p. 101303, 2025.
L. Zhang, X. Wu, Z. Liu, P. Yu, and M. Yang, “ESD-YOLOv8: An Efficient Solar Cell Fault Detection Model Based on YOLOv8,” IEEE Access, vol. 12, pp. 138801–138814, 2024, doi: 10.1109/AC- CESS.2024.3466209.
F. M. A. Mazen, R. A. A. Seoud, and Y. O. Shaker, “Deep Learning for Automatic Defect Detection in PV Modules Using Electrolumines- cence Images,” IEEE Access, vol. 11, pp. 57783–57793, 2023, doi: 10.1109/ACCESS.2023.3284043.
Y. Yang, J. Zhang, X. Shu, L. Pan, and M. Zhang, “A Lightweight Transformer Model for Defect Detection in Electroluminescence Images of Photovoltaic Cells,” IEEE Access, vol. 12, pp. 194922–194930, 2024, doi: 10.1109/ACCESS.2024.3520239..
D. P. Winston, M. S. Murugan, R. M. Elavarasan, R. Pugazhendhi, O. J. Singh, and E. Hossain, “Solar PV’s Micro Crack and Hotspots Detection Technique Using NN and SVM,” IEEE Access, vol. 9, pp. 127259–127269, 2021, doi: 10.1109/ACCESS.2021.3111904
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Safwa Samad, Anjali N.B., Mohammed Hashim O.A., Adwaith Nidheesh, Muneebah Mohyiddeen
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after the acceptance, with an acknowledgement of its initial publication in this journal, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
