Dust Erosion-Aware Detection of End-of-Life Photovoltaic Modules Using an Edge-Deployable Improved YOLOv8 with Coordinate Attention and Frequency-Domain Fusion
Source abstract
Abstract
The industrial dismantling and recycling of end-of-life photovoltaic (PV) modules require robust visual inspection under dust contamination, inter-class similarity, and constrained edge-computing conditions. This study proposes an end-to-end framework that detects key module components (junction box, backsheet label, aluminum frame, and shadow region) and estimates the aluminum frame gap height for dismantling control. The primary novelty is a dust erosion-aware detection and metrology framework that couples frequency-enhanced visual perception with shadow-guided geometric measurement, while lightweight deployment modules serve as supporting engineering components. Specifically, DWT/FFT-based enhancement with CLAHE is used to improve degraded features, and YOLOv8 is strengthened by GSConv and Coordinate Attention in the backbone and neck; transfer learning, INT8 quantization-aware training, and CMFH-based compact rechecking are further introduced for practical deployment. Experiments show that the proposed method improves mAP@0.5 by 5.08 percentage points over baseline YOLOv8 while increasing speed from 45 to 52 FPS. For geometric metrology, the method achieves 93.0% accuracy with a mean error of 0.45 mm. The results demonstrate an accurate, robust, and edge-deployable solution for the automated inspection and recycling of end-of-life PV modules under dusty conditions.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Photovoltaic System Optimization Techniques · Photovoltaic Systems and Sustainability · Industrial Vision Systems and Defect Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Mechatronic Engineering, School of Mechanical Engineering, Inner Mongolia University of Technology, Hohhot 010051, China
Mechanical Design, School of Mechanical Engineering, Inner Mongolia University of Technology, Hohhot 010051, China
Funding
Key Technology Research on Green Disassembly Line for Decommissioned Photovoltaic Modules
References (37)
Show source-provided references
1. Heath, G., Wade, A., Komoto, K., Lee, J.S., Zhang, J., Ravikumar, D., and Sinha, P. (2018). End-of-Life Management of Photovoltaic Panels: Trends in PV Module Recycling Technologies, IEA Photovoltaic Power Systems Programme (IEA-PVPS). Report No. IEA-PVPS T12-10:2018.
2. Global Status of Recycling Waste Solar Panels: A Review10.1016/j.wasman.2018.01.036 ↗
3. Weckend, S., Wade, A., and Heath, G.A. (2016). End-of-Life Management: Solar Photovoltaic Panels, International Renewable Energy Agency (IRENA) and IEA Photovoltaic Power Systems Programme (IEA-PVPS). Report No. T12-06:2016.10.2172/1561525 ↗
4. UAV Aerial Small-Target Detection Based on Improved YOLO v8n
5. Object Detection in Low-Illumination Environments Based on Improved YOLO11
6. Luo, Y., Han, Y., and Huang, H. (2026). Small-Target Defect Detection of Power Transmission Lines Based on STDD-YOLO. Electron. Meas. Technol., (In Chinese).
7. Yu, C., Lai, H., Tang, J., and Gao, G. (2025). DBA-YOLO: Dual-Backbone Lightweight UAV Small-Target Detection Algorithm. Comput. Eng. Appl., (In Chinese).
8. Sugarcane Leaf Disease Recognition Based on Improved YOLO v8n
9. Apple Leaf Disease Detection Based on Improved YOLO v8
10. Lightweight Tomato Leaf Disease Detection Based on Improved YOLO v8n
11. Rice Pest Detection for Insecticidal Lamp Based on Improved YOLO v10n
12. Chemical Thinning Apple Inflorescence Status Detection Based on ESW-YOLO
13. Binocular-Vision Automatic Cup Mounting for Dairy Cow Teat Localization Based on Improved YOLO v8n
14. Worker PPE Detection in Cement Aggregate Workshop Based on ODEM–YOLO
15. Zhou, T., Luo, Y., Zhang, F., and Liu, X. (2025). Abnormal Shredded-Tobacco State Detection Based on YOLO11. Comput. Integr. Manuf. Syst., (In Chinese).
16. Zhang, S., and Wang, B. (2025). Lightweight Pest Segmentation Model Based on Improved YOLO11-Seg. Trans. Chin. Soc. Agric. Eng., (In Chinese).
17. Ez-zaiym, M., Senhaji, Y., Rachid, M., El Moutaouakil, K., and Palade, V. (2025). Fractional Optimizers for LSTM Networks in Financial Time Series Forecasting. Mathematics, 13.10.3390/math13132068 ↗
18. El Moutaouakil, K., Palade, V., Safouan, S., and Charroud, A. (2023). FP-Conv-CM: Fuzzy Probabilistic Convolution C-Means. Mathematics, 11.10.3390/math11081931 ↗
19. Photovoltaic Modules Fault Detection, Power Output, and Parameter Estimation: A Deep Learning Approach Based on Electroluminescence Images10.1016/j.enconman.2024.118866 ↗
20. Zhou, J. (2024). Dust Detection for Photovoltaic Panels Based on Improved YOLOv8. [Ph.D. Thesis, Jiangxi University of Science and Technology]. (In Chinese).
21. He, Y. (2024). Research on Surface Defect Detection of Photovoltaic Panels Based on Deep Learning. [Ph.D. Thesis, Xi’an University of Technology]. (In Chinese).
22. Photovoltaic Module Surface Defect Detection Based on RD-YOLO
23. Domain Adaptation Using Transformer Models for Automated Detection of Exterior Cladding Materials in Street View Images
24. Yildiz, A.S., Meng, H., and Swash, M.R. (2025). Real-Time Object Detection and Distance Measurement Enhanced with Semantic 3D Depth Sensing Using Camera–LiDAR Fusion. Appl. Sci., 15.10.3390/app15105543 ↗
25. Morphological Parameter Measurement for Mushroom Fruiting Bodies Based on Improved YOLO v8-Seg
26. Citrus Pose Estimation Based on YOLO v5-MNv4S and RANSAC-GN
27. Hou, Q., Zhou, D., and Feng, J. (2021, January 20–25). Coordinate Attention for Efficient Mobile Network Design. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR46437.2021.01350 ↗
28. ACDet: Contour Detection for Pharmaceutical Packaging with Enhanced Self-Attention
29. Di, R., Fan, H., Feng, H., Lv, Z., Shu, L., Xie, R., and Qian, R. (2026). MFE-YOLO: A Multi-Scale Feature Enhanced Network for PCB Defect Detection with Cross-Group Attention and FIoU Loss. Entropy, 28.10.3390/e28020174 ↗
30. Jiao, Y., and Zhang, J. (2026). SFFA-YOLO: A Multi-Scale Fusion Algorithm for Fire Smoke Detection. Appl. Sci., 16.10.3390/app16031599 ↗
31. Wang, H., Wu, Y., Liang, J., and Xie, X. (2025). PERE: Prior-Enhanced and Resolution-Extended Object Detection for Industrial Laminated Panel Scenes. Appl. Sci., 15.10.3390/app15084468 ↗
32. Yan, H., Wang, Y., and Chen, R. (2025). Frequency-Domain Enhancement and Dynamic Feature Fusion for Lightweight Aerial Small-Target Detection. Comput. Eng. Appl., (In Chinese).
33. Liu, J., Zhou, G., Liu, H., Wang, J., and Jia, Z. (2025). WTNet-YOLO: Cotton-Field Pest Detection Combining DWT and Transformer. Comput. Eng. Appl., (In Chinese).
34. Ding, G., Guo, Y., and Zhou, J. (2014, January 23–28). Collective Matrix Factorization Hashing for Multimodal Data. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA.10.1109/CVPR.2014.267 ↗
35. Building Façade Datasets for Analyzing Building Characteristics Using Deep Learning
36. Pan, Y., Chen, Y., Tong, X., Liu, M., Huang, A., Zhou, M., and Hu, Y. (2026). YOLO-CSB: A Model for Real-Time and Accurate Detection and Localization of Occluded Apples in Complex Orchard Environments. Agronomy, 16.10.3390/agronomy16030390 ↗
37. Mi, Q., Chao, J., Chen, A., Zhang, K., and Lai, J. (2026). YOLO11s-UAV: An Advanced Algorithm for Small Object Detection in UAV Aerial Imagery. J. Imaging, 12.10.3390/jimaging12020069 ↗