"Solar Panel Anomaly Detection Dataset Based on Solar Insecticidal Lamp Internet of Things"

"The rapid growth of solar energy infrastructure necessitates efficient and automated inspection methods to maintain the performance and longevity of photovoltaic (PV) panels. Traditional manual inspection is time-consuming, labor-intensive, and prone to human error. In this study, we propose a computer vision-based approach for the automated detection of surface anomalies on solar panels using a YOLO object detection model. Our method focuses on identifying common physical defects\u2014including physical cracks, bird droppings, and dust accumulation\u2014from standard RGB images. To support model development and evaluation, we introduce a publicly available annotated image dataset containing diverse examples of solar panel anomalies under various environmental and lighting conditions."

随着太阳能发电基础设施的快速发展，亟需高效且自动化的检测手段以保障光伏（Photovoltaic，PV）面板的运行性能与服役寿命。传统人工巡检方式不仅耗时耗力，还极易引入人为误差。本研究提出了一种基于计算机视觉的检测方案，借助YOLO目标检测模型实现太阳能面板表面异常的自动化识别。该方案聚焦于从标准RGB图像中识别常见物理缺陷，包括表面裂纹、鸟粪污渍以及积尘。为支撑模型开发与评估工作，本研究发布了一套公开可用的带标注图像数据集，涵盖多种环境与光照条件下的各类太阳能面板异常样本。