Defect object detection algorithm for electroluminescence image defects of photovoltaic modules based on deep learning. Issue 3 (12th January 2022)

• Record Type: Journal Article
• Authors: Meng, Ziyao; Xu, Shengzhi; Wang, Lichao; Gong, Youkang; Zhang, Xiaodan; Zhao, Ying
• Is Part Of: Energy science & engineering. Volume 10:Issue 3(2022)
• Page Start: 800
• Page End: 813
• Publication Date: 2022-01-12
• Subjects: deep learning -- electroluminescence image -- object detection -- photovoltaic modules -- YOLO algorithm; Energy industries -- Periodicals; Energy development -- Periodicals; Power resources -- Periodicals; 621.042
• DOI: 10.1002/ese3.1056
• Languages: English
• ISSNs: 2050-0505

Abstract

Abstract: Visual inspection of photovoltaic modules using electroluminescence (EL) images is a common method of quality inspection. Because human inspection requires a lot of time, object detection algorithm to replace human inspection is a popular research direction in recent years. To solve the problem of low accuracy and slow speed in EL image detection, we propose a YOLO‐based object detection algorithm YOLO‐PV, which achieves 94.55% of AP (average precision) on the photovoltaic module EL image data set, and the interference speed exceeds 35 fps. The improvement of speed and accuracy benefits from the targeted design of the network architecture according to the characteristics of EL image. First, we weaken the backbone's ability to extract deep‐level information so that it can focus on extracting the low‐level defect information. Second, the PAN network is used for feature fusion in the Neck part. But, only the single‐size feature map output is retained, which significantly reduces the amount of calculation. Also, we analyze the impact of data enhancement methods on model overfitting and performance. Finally, we give effective data enhancement methods. The results show that the object detection algorithm in this paper can meet the requirements for high‐precision and real‐time processing on the PV module production line. Abstract : In this paper, a fast and accurate defect detection algorithm for photovoltaic modules is proposed. The design of network structure and the training process are described in detail. The reliability of the algorithm is verified by using the El pictures of the actual production line.