This study briefly introduces an intelligent detection algorithm for foreign objects on solar panel surfaces, as well as an intelligent cleaning robot. In the intelligent detection algorithm, the improved Retinex algorithm was used to improve low-light images, and the You Only Look Once version 5 (YOLOv5) algorithm was used to detect foreign objects on the surface. Simulation experiments were performed. The improved Retinex algorithm was compared with the traditional Retinex and histogram equalization methods. The YOLOv5 algorithm was compared with the faster region-based convolutional neural network (R-CNN) and YOLOv4 algorithms. The surface foreign object cleaning ability of the developed intelligent robot was compared with the robot that did not use the same algorithm. The results showed that the improved Retinex algorithm could increase image brightness while preserving color. The edge strength, information entropy, and locally orderless error of the improved images were 79.8±1.6, 7.5±0.7, and 813.6±2.6, respectively. The YOLOv5 algorithm could identify and locate foreign objects more accurately, with a precision of 0.987, a recall rate of 0.985, and an F-value of 0.986. It was also discovered that the intelligent robot using the proposed surface foreign object detection algorithm cleaned foreign objects on the surface of photovoltaic panels faster and better. The time consumed in one round of cleaning was 6.2±0.1 min, and the residual foreign object on the surface was 0.7%±0.1%.

1. [1] X. Bai, R. Wang, Y. Pi, and W. Zhang, “DMFR-YOLO: An infrared small hotspot detection algorithm based on double multi-scale feature fusion,” Meas. Sci. Technol., Vol.36, No.1, pp. 1-12, 2025. https://doi.org/10.1088/1361-6501/ad8e77
2. [2] J. Zhu, D. Zhou, R. Lu, X. Liu, and D. Wan, “C2DEM-YOLO: Improved YOLOv8 for defect detection of photovoltaic cell modules in electroluminescence image,” Nondestruct. Test. Eva., Vol.40, No.1, pp. 309-331, 2025. https://doi.org/10.1080/10589759.2024.2319263
3. [3] J. Zhang, W. Yang, Y. Chen, M. Ding, H. Huang, B. Wang, K. Gao, S. Chen, and R. Du, “Fast object detection of anomaly photovoltaic (PV) cells using deep neural networks,” Appl. Energ., Vol.372, No.C, pp. 1-12, 2024. https://doi.org/10.1016/j.apenergy.2024.123759
4. [4] Y. Su, F. Tao, J. Jin, and C. Zhang, “Automated overheated region object detection of photovoltaic module with thermography image,” IEEE J. Photovolt., Vol.11, No.2, pp. 535-544, 2021. https://doi.org/10.1109/JPHOTOV.2020.3045680
5. [5] T. Han, M. Bao, T. He, R. Zhang, X. Feng, and Y. Huang, “LW-PV DETR: Lightweight model for photovoltaic panel surface defect detection,” Eng. Res. Express, Vol.7, No.1, Article No.015357, 2025. https://doi.org/10.1088/2631-8695/adb4be
6. [6] F. Xu and Z. Wu, “Federated contrastive self-supervised pre-training for photovoltaic panels defect detection,” Proc. 4th Int. Conf. on Image Processing and Intelligent Control (IPIC 2024), Article No.132502Z, 2024. https://doi.org/10.1117/12.3038604
7. [7] H. Chen, Y. Zhang, Y. Zhang, X. Yan, X. Zhang, and K. Zou, “Defect detection of photovoltaic panels to suppress endogenous shift phenomenon,” IEEE Trans. Semiconduct. Manufacturing, Vol.38, No.1, pp. 83-95, 2025. https://doi.org/10.1109/TSM.2024.3510358
8. [8] J. Luo, G. Wang, Y. Lei, D. Wang, and H. Zhang, “YOLOv8n-PP: A lightweight pose recognition algorithm for photovoltaic array cleaning robot,” J. Real-Time Image Pr., Vol.22, Article No.136, 2025. https://doi.org/10.1007/s11554-025-01713-y
9. [9] F. Saeed, S. Aldera, A. A. Al-Shamma’a, and H. M. H. Farh, “Rapid adaptation in photovoltaic defect detection: Integrating CLIP with YOLOv8n for efficient learning,” Energy Rep., Vol.12, pp. 5383-5395, 2024. https://doi.org/10.1016/j.egyr.2024.11.033
10. [10] G. Yang, J. Zhang, H. Li, and C. Bai, “Research on defect detection of photovoltaic cells based on improved mask R-CNN-attention model,” Proc. 4th Int. Conf. on Automation Control, Algorithm, and Intelligent Bionics (ICAIB 2024), Article No.132593M, 2024. https://doi.org/10.1117/12.3039405
11. [11] L. Zhou, X. Sun, and Y. Liu, “Application of interpretability method based on FN-v8 in defect detection of photovoltaic panels,” Proc. 3rd Int. Conf. on Electronics, Electrical and Information Engineering (ICEEIE 2023), Article No.129220N, 2023. https://doi.org/10.1117/12.3008834
12. [12] X. Jiang, W. X. Chen, H. T. Nie, and Z. C. Hao, “Real-time ship target detection based on aerial remote sensing images,” Opt. Precis. Eng., Vol.28, No.10, pp. 2360-2369, 2020. https://doi.org/10.37188/OPE.20202810.2360
13. [13] F. Gao, T. Huang, J. Sun, J. Wang, A. Hussain, and E. Yang, “A new algorithm of SAR image target recognition based on improved deep convolutional neural network,” Cogn. Comput., Vol.11, pp. 809-824, 2019. https://doi.org/10.1007/s12559-018-9563-z
14. [14] S. Kim, “Infrared variation reduction by simultaneous background suppression and target contrast enhancement for deep convolutional neural network-based automatic target recognition,” Opt. Eng., Vol.56, No.6, Article No.063108, 2017. https://doi.org/10.1117/1.OE.56.6.063108
15. [15] J. Pei, Y. Huang, Z. Sun, Y. Zhang, J. Yang, and T. S. Yeo, “Multiview synthetic aperture radar automatic target recognition optimization: Modeling and implementation,” IEEE Trans. Geosci. Remote, Vol.11, pp. 6425-6439, 2018. https://doi.org/10.1109/TGRS.2018.2838593