Unmanned aerial vehicle wind farm inspection path planning based on real-time potential landing safety constraints

doi:10.16265/j.cnki.issn1003-3033.2025.02.0865

Abstract

Abstract:

In order to improve the inspection efficiency and safety of UAV inspections for wind turbines, a reasonable planning of the UAV inspection path was proposed. A method for UAV inspection path planning based on real-time emergency landing safety constraints was introduced. First, a safety calculation model for emergency landing areas was established. It based on the dynamic endurance capacity of UAV affected by wind speed and direction, as well as constraints such as flight path emergency landing, to assess the safety of the inspection path and establish safety constraints. Then, regarding the objective function of the length of UAV inspection path, an optimal inspection path planning method based on the characteristics of RSA was proposed. This method effectively solved TSP for UAV inspections in wind farms under safety constraints, utilizing the discrete and multi-agent characteristics of RSA algorithm to plan the inspection path for wind farms. Finally, comparative experiments and simulations of wind farms were conducted for different algorithms. results indicated that the real-time emergency landing safety constraint model can comprehensively calculate safe routes by integrating various risk factors, enhancing the safety of the inspection path. RSA algorithm can quickly solve TSP problem for wind farm inspections under safety constraints, improving the level of inspection path planning.

Key words: real-time emergency landing, safety constraint, wind farm, unmanned aerial vehicle (UAV), inspection, path planning, ripple spreading algorithm (RSA), traveling salesman problem (TSP)

CLC Number:

X949

HU Xiaobing, LU Ze, LI Hang, ZHOU Hang. Unmanned aerial vehicle wind farm inspection path planning based on real-time potential landing safety constraints[J]. China Safety Science Journal, 2025, 35(2): 28-39.

Figures/Tables 17

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Table 1

Fig.10

Fig.11

Table 2

Table 3

Fig.12

Fig.13

Fig.14

References 15

[1]	刘智勇, 赵晓丹, 祁宏昌, 等. 新时代无人机电力巡检技术展望[J]. 南方能源建设, 2019, 6(4): 1-5.
	LIU Zhiyong, ZHAO Xiaodan, QI Hongchang, et al. Prospect of UAV power inspection technology in new era[J]. Southern Energy Construction, 2019, 6(4): 1-5.
[2]	高珩, 鲍鹏. 旅行商问题求解算法综述[J]. 软件导刊, 2009, 8(11): 67-68.
[3]	DENG Yanlan, XIONG Juxia, WANG Qiuhong. A hybrid cellular genetic algorithm for the traveling salesman problem[J]. Mathematical Problems in Engineering, 2021, 2021(2):DOI:10.1155/2021/6697598.
[4]	EZUGWU E A, ADEWUMI O A, FRINCU E M. Simulated annealing based symbiotic organisms search optimization algorithm for traveling salesman problem[J]. Expert Systems With Applications, 2017, 77: 189-210.
[5]	余丽, 陆锋, 杨林. 交通网络旅行商路径优化的遗传禁忌搜索算法[J]. 测绘学报, 2014, 43(11): 1197-1203. doi: 10.13485/j.cnki.11-2089.2014.0184
	YU Li, LU Feng, YANG Lin. A hybrid algorithm for traveling salesman problem in road network[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(11): 1197-1203. doi: 10.13485/j.cnki.11-2089.2014.0184
[6]	陈科胜, 鲜思东, 郭鹏. 求解旅行商问题的自适应升温模拟退火算法[J]. 控制理论与应用, 2021, 38(2): 245-254.
	CHEN Kesheng, XIAN Sidong, GUO Peng. Adaptive temperature rising simulated annealing algorithm fortraveling salesman problem[J]. Control Theory and Applications, 2021, 38(2): 245-254.
[7]	刘海龙, 雷斌, 王菀莹, 等. 求解TSP问题的改进融合遗传灰狼优化算法[J]. 计算机仿真, 2023, 40(9): 333-338.
	LIU Hailong, LEI Bin, WANG Wanying, et al. Improved fused genetic grey wolf optimization algorithm for solving TSP[J]. Computer Simulation, 2023, 40(9): 333-338.
[8]	张树卓. 计及风场的输电线路无人机巡检路径规划研究[D]. 济南: 山东大学, 2021.
	ZHANG Shuzhuo. Research on UAV path planning of transmission line inspection considering wind field[D]. Jinan: Shandong University, 2021.
[9]	韩鹏, 张冰玉. 基于改进蚁群算法的无人机安全航路规划研究[J]. 中国安全科学学报, 2021, 31(1): 24-29. doi: 10.16265/j.cnki.issn 1003-3033.2021.01.004
	HAN Peng, ZHANG Bingyu. Safety route planing of UAV based on improved ant colony algorithm[J]. China Safety Science Journal. 2021. 31(1):24-29. doi: 10.16265/j.cnki.issn 1003-3033.2021.01.004
[10]	王猛, 王道波, 王博航, 等. 基于改进NSGA-II的多无人机三维空间协同航迹规划研究[J]. 机械与电子, 2021, 39(11): 73-80.
	WANG Meng, WANG Daobo, WANG Bohang, et al. Three-dimensional multi -UAV cooperative path planning based on an improved NSGA-II algorithm[J]. Machinery & Electronics, 2021, 39(11): 73-80.
[11]	韩鹏, 赵嶷飞. 基于飞行环境建模的UAV地面撞击风险研究[J]. 中国安全科学学报, 2020, 30(1): 142-147. doi: 10.16265/j.cnki.issn1003-3033.2020.01.022
	HAN Peng, ZHAO Yifei. Study on ground impact risk of UAV based on flight environment[J]. China Safety Science Journal, 2020, 30(1): 142-147. doi: 10.16265/j.cnki.issn1003-3033.2020.01.022
[12]	曾薇, 孟祥旭, 杨承磊, 等. 平面多边形域的快速约束Delaunay三角化[J]. 计算机辅助设计与图形学学报, 2005, 17(9): 1933-1940.
	ZENG Wei, MENG Xiangxu, YANG Chenglei, et al. Fast constrained delaunay triangulation for planar polygonal domains[J]. Journal of Computer-Aided Design & Computer Graphics, 2005, 17(9): 1933-1940.
[13]	HU Xiaobing, WANG Ming, LEESON M S, et al. Deterministic agent-based path optimization by mimicking the spreading of ripples[J]. Evolutionary Computation, 2016, 24(2): 319-46. doi: 10.1162/EVCO_a_00156 pmid: 26066805
[14]	胡小兵, 袁莉燕, 李航, 等. 基于涟漪扩散算法的应急疏散路径优化方法研究[J]. 交通运输系统工程与信息, 2024, 24(1): 253-261.
	HU Xiaobing, YUAN Liyan, LI Hang, et al. Optimization of emergency evacuation route based on ripple-spreading algorithm[J]. Journal of Transportation Systems Engineering and Information, 2024, 24(1): 253-261.
[15]	王永峰, 徐莹, 王涛. 基于数字高程模型制作山区坡度分级栅格数据[J]. 测绘与空间地理信息, 2014, 37(12): 36-38.
	WANG Yongfeng, XU Ying, WANG Tao. Mapping slope graded map of mountainous area based on digital elevation model[J]. Geomatics & Spatial Information Technology, 2014, 37(12): 36-38.

变量符号	含义
G	G={n₁,n₂,…,n_n}网格节点坐标集合
n_k	TSP问题的起始和终止节点
S(n_i,n_j)	表示n_i和n_j节点间的路径为风险路径
c_ij	表示n_i和n_j节点间路径的距离
F	节点间的路径距离集合
v	涟漪的传播速度
D_max	涟漪的最大传播范围,等于最大节点间距离
Ω_A	处于激活状态涟漪的集合
Ω_S	处于等待状态涟漪的集合
E	E={e₁_j,e₂_j,…,e_ij}为链接集合
R_n	产生的第n个涟漪,按时间先后顺序产生

节点数量/个	限制链接
5	1—5,2—4
10、11、12	1—5,6—7,3—8
13、14、15	2—3,4—6,1—9
16、17、18、19、20	3—5、4—7、1—6、2—8

节点数量	对比参数	穷举算法	RSA算法	遗传算法 (第1组)	遗传算法 (第2组)
5	路径长度/m	4 920.455 7	4 920.455 7	4 920.455 7	4 920.455 7
5	平均计算时间/s	0.003 6	0.062 5	0.204 6	0.204 6
10	路径长度/m	6 302.533 4	6 302.533 4	6 302.533 4	6 302.533 4
10	平均计算时间/s	1.703 1	0.328 1	0.343 7	1.451 6
11	路径长度/m	6 312.800 3	6 312.800 3	6 312.800 3	6 312.800 3
11	平均计算时间/s	18.904 0	0.3714	0.380 6	1.677 1
12	路径长度/m	—	6 518.413 2	6 995.178	6 518.413 2
12	平均计算时间/s	>12 h→43 200	0.609 4	0.437 5	1.698 9
13	路径长度/m	—	7 102.741 8	7255.3917	7179.808 6
13	平均计算时间/s	>12 h→43 200	0.640 6	0.454 7	1.821 5
14	路径长度/m	—	7 551.191 3	7703.8413	8212.586 8
14	平均计算时间/s	>12 h→43 200	2.625 0	0.447 3	2.162 9
15	路径长度/m	—	7 883.196 6	8 111.321 7	7 969.666 8
15	平均计算时间/s	>12 h→43 200	3.875 0	0.450 6	1.885 3
16	路径长度/m	—	8 224.882 9	8 290.993 4	8 290.993 4
16	平均计算时间/s	>12 h→43 200	12.578 1	0.504 2	2.106 1
17	路径长度/m	—	8 295.178 0	8 582.807 7	9 186.072 6
17	平均计算时间/s	>12 h→43 200	43.328 1	0.486 5	2.096 5
18	路径长度/m	—	8 347.271 1	8 654.3731	8 347.271 1
18	平均计算时间/s	>12 h→43 200	89.187 5	0.580 9	2.219 3
19	路径长度/m	—	8 424.510 6	9 725.751 1	9947.725 4
19	平均计算时间/s	>12 h→43 200	311.03 13	0.600 2	2.249 7
20	路径长度/m	—	8 435.145 6	8 727.888 6	8 497.369 1
20	平均计算时间/s	>12 h→43 200	469.062 5	0.592 3	2.382 3