基于无人机的光伏电站智能巡检

王浩; 闫号; 叶海瑞; 柏嵩; 李艺达

基于无人机的光伏电站智能巡检

1.
国家电投集团江苏电力有限公司, 江苏南京 210000
2.
南京航空航天大学机电学院, 江苏南京 210000
3.
国家电投集团江苏新能源有限公司, 江苏盐城 224000

详细信息

作者简介:
王浩（1986-），男，江苏徐州人，硕士，工程师，主要研究方向：网络通信及信息化。E-mail: wanghao05@spic.com.cn

中图分类号: TN219
计量
- 文章访问数: 335
- HTML全文浏览量: 48
- PDF下载量: 60
- 被引次数: 0
出版历程
- 收稿日期: 2021-07-19
- 修回日期: 2021-10-12
- 刊出日期: 2022-05-20

Intelligent Patrol Inspection of Photovoltaic Power Station Based on UAVs

1.
Jiangsu Electric Power Co., Ltd., State Power Investment Corporation, Nanjing 21000, China
2.
College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 21000, China
3.
Jiangsu New Energy Co., Ltd., State Power Investment Corporation, Nanjing 21000, China

摘要

摘要: 太阳能光伏发电是国家能源结构性调整的重要组成部分，近几年随着光伏发电产业规模迅速扩张，光伏电站的日常运维压力日益增加。针对光伏电站面积大、人工检测效率低等问题，文章对基于无人机的光伏电站智能巡检技术进行研究，提出了一个基于无人机的光伏电站智能巡检完整技术路线，实现了光伏面板图像数据自动化采集与分析，并对基于计算机视觉的缺陷检测方法进行研究，采用自适应动态阈值法并结合图像增强技术，基于红外图像实现了鲁棒的光伏面板缺陷检测，结合可见光数据实现缺陷类型判别，进一步根据相机POS数据及相机模型解算缺陷坐标，实现缺陷定位，并在实际场景中验证了所提出技术路线的有效性。
- 无人机 /
- 光伏电站 /
- 缺陷检测 /
- 智能巡检
Abstract: Solar photovoltaic power generation is an important component of a country's energy structural adjustment. With the rapid expansion of the scale of the photovoltaic power generation industry in recent years, the need for an automated daily maintenance of photovoltaic power stations has increased. Traditional manual detection methods are inefficient because photovoltaic power stations are spread over a large area. In this study, we investigate the intelligent inspection technology of a photovoltaic power station based on an unmanned aerial vehicle (UAV). A technical route for an intelligent inspection of a UAV-based photovoltaic power station is proposed. We achieve the automation of photovoltaic panel image data acquisition and analysis and investigate defect detection based on computer vision. We realize photovoltaic panel defect detection based on infrared images using an adaptive dynamic threshold method combined with image enhancement technology, facilitating the classification of defects to be determined by using visible light images. The defect locations are further calculated by combining the POS data and the camera model. Finally, we verify the effectiveness of the proposed technical route in an actual scenario.
- UAV /
- photovoltaic power station /
- defect detection /
- intelligent patrol inspection

HTML全文

图 1 数据采集硬件平台

Figure 1. Hardware platform for data acquisition

下载: 全尺寸图片幻灯片

图 2 无人机数据采集

Figure 2. Data acquisition by UAV

下载: 全尺寸图片幻灯片

图 3 巡检系统工作流程图

Figure 3. Workflow of the inspection system

下载: 全尺寸图片幻灯片

图 4 缺陷检测算法流程

Figure 4. Flow of defect detection algorithm

下载: 全尺寸图片幻灯片

图 5 红外数据的灰度图及灰度直方图

Figure 5. Grayscale diagram and gray histogram of infrared data

下载: 全尺寸图片幻灯片

图 6 检测算法处理过程

Figure 6. Detection algorithm processing process

下载: 全尺寸图片幻灯片

图 7 缺陷定位坐标关系示意

Figure 7. Defect location coordinate relationship

下载: 全尺寸图片幻灯片

图 8 部分任务航线示意

Figure 8. Schematic diagram of partial mission routes

下载: 全尺寸图片幻灯片

图 9 部分缺陷检测结果

Figure 9. Some defect detection results

下载: 全尺寸图片幻灯片

表 1 缺陷检测统计结果

Table 1. Statistical results of defect detection

Hot spots Detections Missed detections False detections

102 113 5 16

下载: 导出CSV

参考文献(13)

[1]	彭向阳, 钱金菊, 吴功平, 等. 架空输电线路机器人全自主巡检系统及示范应用[J]. 高电压技术, 2017, 43(8): 2582-2591. https://www.cnki.com.cn/Article/CJFDTOTAL-GDYJ201708019.htm PENG Xiangyang, QIAN Jinju, WU Gongping, et al. Full automatic inspection system and its demonstration application based on robot for overhead transmission lines[J]. High Voltage Engineering, 2017, 43(8): 2582-2591. https://www.cnki.com.cn/Article/CJFDTOTAL-GDYJ201708019.htm
[2]	黄山, 吴振升, 任志刚, 等. 电力智能巡检机器人研究综述[J]. 电测与仪表, 2020, 57(2): 26-38. https://www.cnki.com.cn/Article/CJFDTOTAL-DCYQ202002005.htm HUANG Shan, WU Zhensheng, REN Zhigang, et al. Review of electric power intelligent inspection robot[J]. Electrical Measurement & Instrumentation, 2020, 57(2): 26-38. https://www.cnki.com.cn/Article/CJFDTOTAL-DCYQ202002005.htm
[3]	王培珍, 郑诗程. 基于红外图像的太阳能光伏阵列故障分析[J]. 太阳能学报, 2010, 31(2): 197–202. https://www.cnki.com.cn/Article/CJFDTOTAL-TYLX201002013.htm WANG Peizhen, ZHENG Shicheng. Fault analysis of photovoltaic array based on infrared image[J]. Journal of Solar Energy, 2010, 31(2): 197-202. https://www.cnki.com.cn/Article/CJFDTOTAL-TYLX201002013.htm
[4]	闫萍, 王赶强. 电致发光成像测试晶体硅光伏组件缺陷的方法标准解读[J]. 标准化研究, 2020(9): 29-31. https://www.cnki.com.cn/Article/CJFDTOTAL-DZBZ202009014.htm YAN Ping, WANG Ganqiang. Interpretation of standard for test method for cell defects in crystalline silicon photovoltaic modules by electroluminescence (EL) imaging[J]. Standardization Research, 2020(9): 29-31. https://www.cnki.com.cn/Article/CJFDTOTAL-DZBZ202009014.htm
[5]	陆成龙, 刘忠德, 张皖军, 等. 无人机智能巡检在检测风电光伏故障中的应用研究[J]. 电子设计工程, 2021, 29(6): 130-134. https://www.cnki.com.cn/Article/CJFDTOTAL-GWDZ202106026.htm LU Chenglong, LIU Zhongde, ZHANG Wanjun, et al. Research on the application of UAV intelligent inspection in the detection of wind power photovoltaic fault[J]. Electronic Design Engineering, 2021, 29(6): 130-134. https://www.cnki.com.cn/Article/CJFDTOTAL-GWDZ202106026.htm
[6]	王栓虎, 温向炜. 无人机在光伏组件巡视检查中的应用分析[J]. 太阳能, 2021(1): 51-54. https://www.cnki.com.cn/Article/CJFDTOTAL-TYNZ202101009.htm WANG Shuanhu, WEN Xiangwei. Application analysis of unmanned aerial vehicle in pv modules inspection[J]. Solar Energy, 2021(1): 51-54. https://www.cnki.com.cn/Article/CJFDTOTAL-TYNZ202101009.htm
[7]	赵玲玲, 汪烨, 刘俊. 基于无人机与HSV空间的光伏电池板检测分析[J]. 红外技术, 2020, 42(10): 978-982. http://hwjs.nvir.cn/article/id/hwjs202010010 ZHAO Lingling, WANG Ye, LIU Jun. Detection and analysis of photovoltaic panels based on UAV and HSV space[J]. Infrared Technology, 2020, 42(10): 978-982. http://hwjs.nvir.cn/article/id/hwjs202010010
[8]	李香凡, 唐志伟, 胡家龙, 等. 无人机光伏巡检的图像目标检测算法[J]. 电子世界, 2020(11): 7-8. https://www.cnki.com.cn/Article/CJFDTOTAL-ELEW202011002.htm LI Xiangfan, TANG Zhiwei, HU Jialong, et al. Image target detection algorithm of UAV photovoltaic inspection[J]. Electronics World, 2020(11): 7-8. https://www.cnki.com.cn/Article/CJFDTOTAL-ELEW202011002.htm
[9]	Roggi G, Niccolai A, Grimaccia F, et al. A computer vision line-tracking algorithm for automatic UAV photovoltaic plants monitoring applications[J]. Energies, 2020, 13(4): 1-15.
[10]	金映谷, 张涛, 杨亚宁, 等. 基于深度学习的产品缺陷检测方法综述[J]. 大连民族大学学报, 2020, 22(5): 420-427. https://www.cnki.com.cn/Article/CJFDTOTAL-DLMY202005007.htm JIN Yinggu, ZHANG Tao, YANG Yaning, et al. Review of product defect detection methods based on deep learning[J]. Journal of Dalian Minzu University, 2020, 22(5): 420-427. https://www.cnki.com.cn/Article/CJFDTOTAL-DLMY202005007.htm
[11]	Otsu N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems Man and Cybernetics, 2007, 9(1): 62-66
[12]	Natale F, Boato G. Detecting morphological filtering of binary images[J]. Transactions on Information Forensics and Security, 2017, 12(5): 1207-1217.
[13]	徐立波. 渔光互补光伏发电系统设计[J]. 科技风, 2020(33): 3-4. https://www.cnki.com.cn/Article/CJFDTOTAL-KJFT202033003.htm XU Libo. Design of fishing light complementary photovoltaic power generation system[J]. Technology Wind, 2020(33): 3-4. https://www.cnki.com.cn/Article/CJFDTOTAL-KJFT202033003.htm