Affiliation:
1. School of Automation, Southeast University, Nanjing 210096, China
2. Shenzhen Research Institute, Southeast University, Shenzhen 518000, China
Abstract
Considering the defect detection issues in electroluminescence (EL) of photovoltaic (PV) cell systems, lots of factors result in performance degradation, including defect diversity, data imbalance, scale difference, etc. Focal-EIoU loss, an effective defect detection solution for EL, is proposed based on the improved YOLOv5. Firstly, by analyzing the detection background and scale characteristics of EL defects, a binary classification is carried out in the system. Subsequently, a cascade detection network based on YOLOv5 is designed to further extract features from the binary-classified defects. The defect localization and classification are achieved in this way. To address the problem of imbalanced defect samples, a loss function is designed based on EIoU and Focal-F1 Loss. Experimental results are illustrated to show the effectiveness. Compared with the existing CNN-based deep learning approaches, the proposed focal loss calculation-based method can effectively improve the performance of handling sample imbalance. Moreover, in the detection of 12 types of defects, the Yolov5 algorithms can always obtain higher MAP (mean average precision) even with different parameter levels (Yolov5m: 0.791 vs. 0.857, Yolov5l: 0.798 vs. 0.862, Yolov5x: 0.802 vs. 0.867, Yolov5s: 0.793 vs. 0.865).
Funder
Shenzhen Science and Technology Program
Guangdong Basic and Applied Basic Research Foundation
Reference47 articles.
1. Hu, X., Tang, W., Bi, J., Chen, S., and Yan, W. (2021, January 26–28). CNN-based model for cell extraction from PV modules with EL images for PV defects detection. Proceedings of the Chinese Control Conference, Shanghai, China.
2. Dou, Z. (2013). Research of Online Defects Detection for Solar Panel Base on the EL Image. [Master’s Thesis, Zhejiang Sci-Tech University].
3. Wang, Z. (2014). Research on Defect Detection System for Solar Cells. [Master’s Thesis, Hebei University of Technology].
4. Solar cells surface defects detection based on deep learning;Wang;Pattern Recognit. Artif. Intell.,2014
5. Defect recognition for radiographic image based on deep learning network;Yu;Chin. J. Sci. Instrum.,2014