基于无人机视觉巡航的光伏发电坏点定位技术  

RESEARCH ON PHOTOVOLTAIC POWER GENERATION BAD POINT LOCALIZATION TECHNOLOGY BASED ON DRONE VISUAL CRUISE CONTROL

作　　者：黄绪勇 唐标 秦雄鹏 林中爱 许守东 Huang Xuyong;Tang Biao;Qin Xiongpeng;Lin Zhongai;Xu Shoudong(Electric Power Research Institute of Yunnan Power Grid Co.,Ltd.,Kunming 650012,China;School of Information,Yunnan University,Kunming 650012,China;Yunnan Electric Power Technology Co.,Ltd.,Kunming 650012,China)

机构地区：[1]云南电网有限责任公司电力科学研究院,昆明650012 [2]云南大学信息学院,昆明650012 [3]云南电力技术有限责任公司,昆明650012

出　　处：《太阳能学报》2025年第1期594-600,共7页Acta Energiae Solaris Sinica

基　　金：云南电网有限责任公司电力科学研究院云南电科院三维激光点云数据纠偏维护项目(056200MS62210003)。

摘　　要：通过无人机采集光伏组件的图像后,利用小波尺度分解技术来增强图像的对比度和细节,重构无人机视觉巡航成像结果。为消除影响坏点定位准确性的噪声,采用中值滤波法对重构图像进行滤波,同时保留边缘信息和图像清晰度;使用门限二值化将图像中的背景和感兴趣区域进行分割;通过最大类间方差方法计算分割处理得到的背景和感兴趣区域的类间方差,能确定最优门限值,以此将感兴趣区域中的坏点范围单独提取出来;最后,为更加精确定位具体的坏点位置,引入改进的区域生长方法,通过设置生长阈值和梯度振幅门限,能有效定位光伏发电系统中存在的坏点位置。实验证明,所提方法对光伏发电坏点定位误差小,检测精准度高,能有效辅助维护电网安全。After collecting images of photovoltaic modules through drones,wavelet scale decomposition technology is used to enhance the contrast and details of the images,and the visual cruise imaging results of drones are reconstructed.In order to eliminate noise that affects the accuracy of bad point localization,the median filtering method is used to filter the reconstructed image,while preserving edge information and image clarity.Using threshold binarization to segment the background and regions of interest in the image.By using the maximum inter class variance method to calculate the inter class variance of the background and region of interest obtained from segmentation,the optimal threshold value can be determined,thereby extracting the range of bad points in the region of interest separately.Finally,in order to more accurately locate specific bad point locations,an improved region growth method was introduced.By setting growth thresholds and gradient amplitude thresholds,the bad point locations present in photovoltaic power generation systems can be effectively located.The experiment proves that the proposed method has small positioning error for photovoltaic power generation bad points,high detection accuracy,and can effectively assist in maintaining power grid security.

关 键 词：无人机 光伏发电 遥感 坏点定位 灰度均值 

分 类 号：TM615[电气工程—电力系统及自动化]