Path planning strategy of UAV inspection of large-scale photovoltaic power stations

doi:10.3969/j.issn.2097-0706.2024.11.006

Abstract

Abstract:

With the development of the photovoltaic industry， daily operation and maintenance costs for large-scale photovoltaic power stations， which mainly rely on manual inspections， are increasing. The widespread application of unmanned aerial vehicle（UAV）inspection technology effectively reduces inspection costs and improves inspection efficiency. To address the inspection challenges of large-scale photovoltaic power stations， a UAV path planning method based on clustering algorithm and ant colony algorithm was proposed. Based on the regular layout of photovoltaic clusters in large-scale photovoltaic power plants， and considering the field of view and flying altitude of drones， photographic points were planned to cover all clusters， and a scatter plot of these points was constructed. Considering the endurance of UAV， a condensed K-means clustering algorithm was proposed to divide the large-scale photovoltaic power station into multiple inspection sub-regions. For multiple inspection sub-regions， a coverage-based elite ant colony algorithm was proposed for path planning， ensuring that all photovoltaic strings within the inspection area were covered， which effectively reduced the inspection path length and energy consumption of UAV. The effectiveness of the proposed algorithm was then validated in a real-world photovoltaic power station （30 MWp） scenario.

Key words: unmanned aerial vehicle, photovoltaic inspection, regional division, path planning, ant colony optimization

CLC Number:

TK01：TM615

WU Zhangyu, WU Chili, YU Huiming, ZHENG Xingnan, ZHANG Xiaoyu. Path planning strategy of UAV inspection of large-scale photovoltaic power stations[J]. Integrated Intelligent Energy, 2024, 46(11): 46-53.

Figures/Tables 12

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Table 1

Table 2

Table 3

Fig.8

Fig.9

References 25

[1]	经济参考报. 解读光伏新政策,无人机光伏巡检迎来新风口[EB/OL](2022-04-28)[2024-08-01]. http://www.jjckb.cn/2022-04/28/c_1310578008.htm.
[2]	夏德喜, 刘浩满, 芦璐. 无人机自动化巡检技术在光伏电站中的应用[J]. 太阳能, 2023(12):74-81.
	XIA Dexi, LIU Haoman, LU Lu. Application of UAV automatic inspection technology in photovoltaic power station[J]. Solar Energy, 2023(12):74-81.
[3]	陈天啸. 基于高分辨率机器视觉的光伏电站智能巡检技术研究[J]. 电子设计工程, 2024, 32(11):28-32.
	CHEN Tianxiao. Research on intelligent inspection technology of photovoltaic power station based on high-resolution machine vision[J]. Electronic design engineering, 2024, 32(11):28-32.
[4]	王浩, 闫号, 叶海瑞, 等. 基于无人机的光伏电站智能巡检[J]. 红外技术, 2022, 44(5):537-542.
	WANG Hao, YAN Hao, YE Hairui, et al. Intelligent inspection of photovoltaic power station based on UAV[J]. Infrared Technology, 2022, 44(5):537-542.
[5]	赖菲, 陈亚鹏, 单正涛, 等. 深度学习算法在光伏电站无人机智能运维中应用[J]. 热力发电, 2019, 48(9):139-144.
	LAI Fei, CHEN Yapeng, SHAN Zhengtao, et al. Application of deep learning algorithm in intelligent operation and maintenance of UAV in photovoltaic power station[J]. Thermal Power Generation, 2019, 48(9):139-144.
[6]	席志鹏, 楼卓, 李晓霞, 等. 集中式光伏电站巡检无人机视觉定位与导航[J]. 浙江大学学报(工学版), 2019, 53(5):880-888.
	XI Zhipeng, LOU Zhuo, LI Xiaoxia, et al. Visual positioning and navigation of unmanned aerial vehicle for centralized photovoltaic power station inspection[J]. Journal of Zhejiang University (Engineering Edition), 2019, 53(5):880-888.
[7]	戴健, 许菲, 陈琪锋. 多无人机协同搜索区域划分与路径规划[J]. 航空学报, 2020, 41(S1):149-156.
	DAI Jian, XU Fei, CHEN Qifeng. Multi-UAV cooperative search area division and path planning[J]. Acta Aeronautical, 2020, 41(S1):149-156.
[8]	鲁旭涛, 智超群, 张丽娜, 等. 应急搜索UAV集群协同任务规划策略[J]. 电子与信息学报, 2022, 44(1):187-194.
	LU Xutao, ZHI Chaoqun, ZHANG Lina, et al. Collaborative Task Planning Strategy for Emergency Search UAV Cluster[J]. Journal of Electronics and Information, 2022, 44(1):187-194.
[9]	高云飞, 胡钰林, 刘鸣柳, 等. 多无人机输电线路巡检联合轨迹设计方法[J]. 电子与信报, 2024, 46(5):1958-1967.
	GAO Yunfei, HU Yulin, LIU Mingliu, et al. Joint trajectory design method for multi-UAV transmission line inspection[J]. Journal of Electronics and Information, 2024, 46(5):1958-1967.
[10]	LOFSTAD-LIE V, MARSTEIN E S, SIMONSEN A, et al. Cost-effective flight strategy for aeria l thermography inspection of photovoltaic power plants[J]. IEEE Journal of Photovoltaics, 2022, 12(6):1543-1549.
[11]	陈艺, 于纪言. 复杂环境下无人机全覆盖三维路径规划算法[J]. 计算机集成制造系统, 2023, 29(8):2563-2573.
	CHEN Yi, YU Jiyan. Cost-effective method of UAV full coverage three-dimensional path planning in complex environment[J]. Computer Integrated Manufacturing System, 2023, 29(8):2563-2573.
[12]	CABREIRA T M, DI F C, FERREIRA P R, et al. Energy-aware spiral coverage path planning for UAV photogrammetric applications[C]// 2018:3662-3668.DOI:10.1109/LRA.2018.2854967.
[13]	陈丽, 陈洋, 杨艳华. 面向三维结构视觉检测的无人机覆盖路径规划[J]. 电子测量与仪器学报, 2023, 37(2):1-10.
	CHEN Li, CHEN Yang,YANG Yanhua. UAV coverage path planning for 3d structure vision inspection[J]. Journal of Electronic Measurement and Instrument, 2023, 37(2):1-10.
[14]	于全友, 徐止政, 段纳, 等. 基于改进ACO的带续航约束无人机全覆盖作业路径规划[J]. 航空学报, 2023, 44 (12):303-315.
	YU Quanyou, XU Zhizheng, DUAN Na, et al. Path planning of UAV with endurance constraints based on improved ACO[J]. Acta Aeronautical, 2023, 44(12):303-315.
[15]	焦嵩鸣, 首云锋, 白健鹏, 等. 变电站巡检无人机分层运动规划方法研究[J]. 系统仿真学报, 2023, 35(9):1975-1984. doi: 10.16182/j.issn1004731x.joss.22-0519
	JIAO Songming, SHOU Yunfeng, BAI Jianpeng, et al. Research on hierarchical motion planning method of UAV for substation inspection[J]. Journal of System Simulation, 2023, 35(9):1975-1984. doi: 10.16182/j.issn1004731x.joss.22-0519
[16]	ZHANG Y R, DING S F, WANG Y R, et al. Chameleon algorithm based on improved natural neighbor graph generating sub-clusters[J]. Appl Intelligence, 2021, 51(11):8399-8415.
[17]	李长明, 张红臣, 王超, 等. 一种高效的阴阳k-Means聚类算法[J]. 吉林大学学报(理学版), 2021, 59(6):1455-1460,
	LI Changming, ZHANG Hongchen, WANG Chao, et al. An efficient k-Means clustering algorithm for yin and yang[J]. Journal of Jilin University(Science Edition) 2021, 59(6):1455-1460.
[18]	吴越安, 杜昌平, 杨睿, 等. 基于改进遗传算法的倾转旋翼无人机区域覆盖路径规划[J]. 浙江大学学报(工学版), 2024, 58(10):2031-2039.
	WU Yuean, DU Changping, YANG Rui, et al. Area coverage path planning for tilt-rotor unmanned aerial vehicle based on enhanced genetic algorithm[J]. Journal of Zhejiang University(Engineering Science), 2024, 58(10):2031-2039.
[19]	张驰, 任焰辉, 张立, 等. 基于蚁群算法优化的无人机巡检路径规划[J]. 信息技术, 2024(7):180-186.
	ZHANG Chi, REN Yanhui, ZHANG Li, et al. Optimization of unmanned aerial vehicle inspection path planning based on ant colony algorithm[J]. Information Technology, 2024(7):180-186.
[20]	李晓辉, 张路, 刘传水, 等. 电力巡检中的无人机群路径规划算法[J]. 计算机系统应用, 2022, 31(3):241-247.
	LI Xiaohui, ZHANG Lu, LIU Chuanshui, et al. UAVs routing planning algorithm in power inspection[J]. Computer Systems & Applications, 2022, 31(3):241-247.
[21]	DING Y F, CAO R, LIANG S M, et al. Density-based optimal UAV path planning for photovoltaic farm inspection in complex topography[C]// 2020 Chinese Control And Decision Conference (CCDC),Hefei, 2020: 3931-3936.
[22]	孔凡尧. 基于深度学习与仿生算法的无人机光伏巡检路径规划[D]. 哈尔滨: 哈尔滨工程大学, 2022.
	KONG Fanyao. Path planning of UAV photovoltaic inspection based on deep learning and bionic algorithm[D]. Harbin:Harbin Engineering University, 2022.
[23]	辛国江, 邹北骥, 李建锋, 等. 结合最大方差比准则和PCNN模型的图像分割[J]. 中国图象图形学报, 2011, 16(7):1310-1316.
	XIN Guojiang, ZOU Beiji, LI Jianfeng, et al. Image segmentation based on maximum variance ratio criterion and PCNN model[J]. Journal of Image and Graphics, 2011, 16(7):1310-1316.
[24]	郭靖, 侯苏. K-means算法最佳聚类数评价指标研究[J]. 软件导刊, 2017, 16(11):5-8.
	GUO Jing, HOU Su. Research on the evaluation index of the best clustering number of K-means algorithm[J]. Software Guide, 2017, 16(11):5-8.
[25]	付春龍, 盛腾. 常用聚类内部评价指标的对比分析[J]. 电脑编程技巧与维护, 2023(4):3-5,9.
	FU Chunlong, SHENG Teng. Comparative analysis of common internal evaluation indexes of clustering[J]. Computer programming skills and maintenance, 2023(4):3-5,9.

项目	聚类指标
项目	轮廓系数	方差比准则	DBI值
K-means	0.452	556.9	0.736
AHC	0.427	446.0	0.823
谱聚类	0.443	539.8	0.776
密度聚类	0.355	314.7	1.332
本文算法	0.452	557.3	0.732

参数	数值
蚂蚁数量	50
最大迭代次数	500
信息素影响权重	1
启发式函数影响权重	5
调整速率	0.1
信息素常量系数	1

项目	路径长度/km	转弯次数	飞行时间/s
贪婪算法	15.39	181	2 987
传统ACO	13.93	153	2 620
遗传算法	35.67	207	5 223
模拟退火算法	31.47	141	4 277
粒子群算法	45.38	288	6 842
本文算法	13.85	134	2 457