Crack Defect Recognition Technology for Photovoltaic Panels Based on the YOLOv8 Target Detection Algorithm
Congcong Wang, Jingrao Xu, Yulu Ding, Ruihang Jiang, Xiaoming Song
Shandong Jianzhu University
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
To efficiently identify crack defects in photovoltaic panels, this paper proposes a photovoltaic system fault detection method based on the YOLOv8 detection model. It establishes a multi-type image library of damaged photovoltaic modules and pre-labels them. A lightweight convolutional neural network is used to accurately extract the information from the photovoltaic module damage image library. By adjusting the loss function and updating the decoupling detection head scheme, Improve the accuracy of fault identification for photovoltaic modules. Experiments show that this method demonstrates excellent performance in multiple aspects such as recognition accuracy, recall rate, and$\text{mAP50}$, providing reliable support for the operation and maintenance of photovoltaic systems.
逐年被引趋势
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
工程Industrial Vision Systems and Defect Detection
Infrastructure Maintenance and Monitoring · Advanced Neural Network Applications
参考文献 5
此处列出前 3 条
引用本文 2
按被引量排序,此处列出前 3 条