journal article·2025-05-31Open access

EER-DETR: An Improved Method for Detecting Defects on the Surface of Solar Panels Based on RT-DETR

Jiajun Dun, Hai Yang, Shixin Yuan, Ying Tang

Applied Sciences· Volume 15· Issue 11

Abstract

In the context of the rapid popularization of clean energy, the precise identification of surface defects on photovoltaic modules has become a core technical bottleneck limiting the operational efficiency of power stations. In response to the shortcomings of existing detection methods in identifying tiny defects and model efficiency, this study innovatively constructed the EER-DETR detection framework: firstly, a feature reconstruction module WDBB with a differentiable branch structure was introduced to significantly enhance the feature retention ability for fine cracks and other small targets; secondly, an adaptive feature pyramid network EHFPN was innovatively designed, which achieved efficient integration of multi-level features through a dynamic weight allocation mechanism, reducing the model complexity by 9.7% while maintaining detection accuracy, solving the industry problem of “precision—efficiency imbalance” in traditional feature pyramid networks; finally, an enhanced upsampling component was introduced to effectively address the problem of detail loss that occurs in traditional methods during image resolution enhancement. Experimental verification shows that the improved algorithm increased the average precision (mAP@0.5) on the panel dataset by 1.9%, and its comprehensive performance also exceeded RT-DETR. Based on the industry standard PVEL-AD, the detection rate of typical defects significantly improved compared to the baseline model. The core innovation of this research lies in the combination of differentiable architecture design and dynamic feature management, providing a detection tool for the intelligent operation and maintenance of photovoltaic power stations that possesses both high precision and lightweight characteristics. It has significant engineering application value and academic reference significance.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Industrial Vision Systems and Defect Detection · Advanced Neural Network Applications · Photovoltaic System Optimization Techniques

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

College of Mechanical and Electrical Engineering, Chengdu University of Technology, Chengdu 610059, China

References (34)

Show source-provided references
1. Solar cell efficiency tables (version 56)10.1002/pip.3303 ↗
2. Polly, S.J., Dann, M., Fedorenko, A., Hubbard, S., Landi, B., Schauerman, C., Ganter, M., and Raffaelle, R. (2018, January 10–15). Development of a nano-enabled space power system. Proceedings of the 7th World Conference on Photovoltaic Energy Conversion (IEEE), Waikoloa, HI, USA.10.1109/PVSC.2018.8547441 ↗
3. Performance and degradation analysis for long term reliability of solar photovoltaic systems: A review10.1016/j.rser.2013.07.046 ↗
4. Influence of damp heat on the electrical properties of Cu (in,Ga) Se2 solar cells10.1016/S0040-6090(99)00820-2 ↗
5. Banda, P., and Barnard, L. (2018, January 26–28). A deep learning approach to photovoltaic cell defect classification. Proceedings of the Annual Conference of the South African Institute of Computer Scientists and Information Technologists on (SAICSIT), Port Elizabeth, South Africa.10.1145/3278681.3278707 ↗
6. The general inefficiency of batch training for gradient descent learning10.1016/S0893-6080(03)00138-2 ↗
7. Memon, S.A., Javed, Q., Kim, W.G., Mahmood, Z., Khan, U., and Shahzad, M. (2022). A Machine-Learning-Based Robust Classification Method for PV Panel Faults. Sensors, 22.10.3390/s22218515 ↗
8. Xie, H., Yuan, B., Hu, C., Gao, Y., Wang, F., Wang, C., Wang, Y., and Chu, P. (2024). ST-YOLO: A defect detection method for photovoltaic modules based on infrared thermal imaging and machine vision technology. PLoS ONE, 19.10.1371/journal.pone.0310742 ↗
9. Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S. (2020). End-to-End Object Detection with Transformers. arXiv.10.1007/978-3-030-58452-8_13 ↗
10. Object Detection Based on K-Nearest Neighbor Contour Fragment Group
11. Bartler, A., Mauch, L., Yang, B., Reuter, M., and Stoicescu, L. (, January 3–8). Automated Detection of Solar Cell Defects with Deep Learning. Proceedings of the 26th European Signal Processing Conference (EUSIPCO), Rome, Italy.
12. Deep learning based automatic defect identification of photovoltaic module using electroluminescence images10.1016/j.solener.2020.03.049 ↗
13. Multiyear Study of Crack-Induced Degradation in Fielded Photovoltaic Modules10.1016/j.solener.2022.06.031 ↗
14. A review of automated solar photovoltaic defect detection systems: Approaches, challenges, and future orientations10.1016/j.solener.2023.112186 ↗
15. Wang, Y., Guo, J., Qi, Y., Liu, X., Han, J., Zhang, J., Zhang, Z., Lian, J., and Yin, X. (2024). Research Progress on Deep Learning Based Defect Detection Technology for Solar Panels. EAI Endorsed Trans. Energy Web, 11.10.4108/ew.5740 ↗
16. Redmon, J., Divvala, S.K., Girshick, R.B., and Farhadi, A. (2016, January 27–30). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
17. Infrared Thermal Imaging Defect Detection for Photovoltaic Modules Based on Improved YOLO v5 Algorithm
18. Wang, Y., Zhao, J., Yan, Y., Zhao, Z., and Hu, X. (2024). Pushing the Boundaries of Solar Panel Inspection: Elevated Defect Detection with YOLOv7-GX Technology. Electronics, 13.10.3390/electronics13081467 ↗
19. Jia, S., and Dong, H. (2023). Real-Time Fault Diagnosis of Photovoltaic Modules for Integrated Energy Systems Based on YOLOv7. Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023), Hangyou, China, 26–28 May 2023, SPIE.
20. Research on Surface Defect Detection Method of Photovoltaic Power Generation Panels—Comparative Analysis of Detecting Model Accuracy
21. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv.
22. Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S. (2020, January 23–28). End-to-end object detection with transformers. Proceedings of the European Conference on Computer Vision, Glasgow, UK.10.1007/978-3-030-58452-8_13 ↗
23. Zhu, X., Su, W., Lu, L., Li, B., Wang, X., and Dai, J. (2020). Deformable detr: Deformable transformers for end-to-end object detection. arXiv.
24. Yao, Z., Ai, J., Li, B., and Zhang, C. (2021). Efficient detr: Improving end-to-end object detector with dense prior. arXiv.
25. Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., and Chen, J. (2023). Detrs beat yolos on real-time object detection. arXiv.10.1109/CVPR52733.2024.01605 ↗
26. YOLO-MIF: Improved YOLOv8 with Multi-Information fusion for object detection in Gray-Scale images10.1016/j.aei.2024.102709 ↗
27. Ding, X., and Ding, G. (2021). Diverse Branch Block: Building a Convolution as an Inception-like Unit. arXiv.10.1109/CVPR46437.2021.01074 ↗
28. A Real Time Drone RF Signal Detection Method Under Low SNR Condition
29. Liu, Z., Sun, C., and Wang, X. (2024). DST-DETR: Image Dehazing RT-DETR for Safety Helmet Detection in Foggy Weather. Sensors, 24.10.3390/s24144628 ↗
30. Tan, M., Pang, R., and Le, Q.V. (2020, January 13–19). Efffcientdet: Scalable and efffcient object detection. Proceedings of the Conference on Computer Vision and Pattern Recognition (IEEE/CVF), Seattle, WA, USA.10.1109/CVPR42600.2020.01079 ↗
31. Semantic Coarse-to-Fine Granularity Learning for Two-Stage Few-Shot Anomaly Detection
32. Rahman, M.M., Munir, M., and Marculescu, R. (2024, January 21). EMCAD: Efficient Multi-Scale Convolutional Attention Decoding for Medical Image Segmentation. Proceedings of the Conference on Computer Vision and Pattern Recognition (IEEE/CVF), Seattle, WA, USA.10.1109/CVPR52733.2024.01118 ↗
33. Deng, J., Chen, Z., Chen, M., Xu, L., Yang, J., Luo, Z., and Qin, P. (2024). Pneumonia App: A mobile application for efficient pediatric pneumonia diagnosis using explainable convolutional neural networks (CNN). arXiv.
34. PVEL-AD: A Large-Scale Open-World Dataset for Photovoltaic Cell Anomaly Detection10.1109/TII.2022.3162846 ↗