面向飞机表面巡检的多无人机覆盖路径规划

doi:10.12305/j.issn.1001-506X.2026.02.28

摘要/Abstract

摘要：

为了确保飞机飞行安全并及时发现潜在缺陷，飞机表面巡检变得尤为重要。传统人工巡检人力成本高、效率低下，无人机自动化巡检可以极大降低检测成本、提高检测效率。本文提出一种面向飞机表面巡检任务的多无人机覆盖路径规划方案，目的是优化覆盖率并提高巡检效率。结合采用自组织映射(self-organizing map，Som)神经网络和K-means算法，对飞机三维点云模型进行区域划分，在淘金优化(gold rush optimizer, GRO)算法基础上加入路径转弯惩罚项和协同约束，规划无人机群覆盖路径。考虑无人机群能源消耗的情况下，缩短路径长度和完成时间。仿真结果表明，所提方案在覆盖率方面达到99.98%，时间比单机缩短74.6%。

关键词: 飞机表面巡检, 无人机, 路径规划, 多机协同

Abstract:

In order to ensure the safety of aircraft flight and timely detection of potential defects, aircraft surface inspection has become particularly important. Traditional manual inspection has high labor cost and low efficiency, while automated inspection by unmanned aerial vehicles （UAVs） can greatly reduce the inspection cost and improve the inspection efficiency. In this paper, a multi-UAV coverage path planning scheme for aircraft surface inspection tasks is proposed with the aim of optimizing coverage and improving inspection efficiency. Combining the use of self-organizing map （Som） neural network and K-means algorithm, the three-dimensional point cloud model of the aircraft is divided into regions, and the UAV swarm coverage paths are planned by adding the path turning penalty term and collaborative constraints based on the gold rush optimizer （GRO） algorithm. Considering the energy consumption of UAV swarm, the path length and the completion time are shortened. Simulation results show that the proposed scheme achieves 99.98% in coverage rate and 74.6% in time reduction compared with a single aircraft.

Key words: aircraft surface inspection, unmanned aerial vehicles （UAVs）, path planning, multi-UAV collaboration

中图分类号:

TP 242

李淑凤, 韩璐羽. 面向飞机表面巡检的多无人机覆盖路径规划[J]. 系统工程与电子技术, 2026, 48(2): 684-693.

Shufeng LI, Luyu HAN. Multi-UAV coverage path planning for aircraft surface inspection[J]. Systems Engineering and Electronics, 2026, 48(2): 684-693.

图/表 20

图1

图2

表1

图3

图4

表2

表3

图5

图6

图7

图8

图9

图10

图11

图12

表4

表5

图13

表6

图14

参考文献 43

1	LIU Y P, DONG J X, LI Y D, et al. A UAV-based aircraft surface defect inspection system via external constraints and deep learning[J]. IEEE Trans. on Instrumentation and Measurement, 2022, 71, 5019315.
2	ZHANG Y D, WANG W, GUO Z H, et al. Research on oriented surface defect detection in the aircraft skin-coating process based on an attention detector[J]. IET Image Process, 2024, 18 (5): 1213- 1228. doi: 10.1049/ipr2.13020
3	DIDIER A R, CRISTIAN L T. Inspection of aircrafts and airports using UAS: a review[J]. Results in Engineering, 2024, 22, 102330- 102343. doi: 10.1016/j.rineng.2024.102330
4	AVDELIDIS N P, TSOURDOS A. LAFIOSCA P, et al. Defects recognition algorithm development from visual UAV inspections[J]. Sensors, 2022, 22 (13): 4682- 4694. doi: 10.3390/s22134682
5	FEVGAS G, LAGKAS T, ARGYRIOU V, et al. Coverage path planning methods focusing on energy efficient and cooperative strategies for unmanned aerial vehicles[J]. Sensors, 2022, 22 (3): 1235- 1254. doi: 10.3390/s22031235
6	TAN C S, MOHD-MOKHTAR R, ARSHAD M R. A comprehensive review of coverage path planning in robotics using classical and heuristic algorithms[J]. IEEE Access, 2021, 9, 119310- 119342. doi: 10.1109/ACCESS.2021.3108177
7	EMILE G, PASQUALE F, DARIUSZ C. Coverage path planning with targeted viewpoint sampling for robotic free-form surface inspection[J]. Robotics and Computer-Integrated, 2020, 61, 101843. doi: 10.1016/j.rcim.2019.101843
8	KRISHAN K, NEERAJ K. Region coverage-aware path planning for unmanned aerial vehicles: a systematic review[J]. Physical Communication, 2023, 59, 102073- 102094. doi: 10.1016/j.phycom.2023.102073
9	SUI H G, ZHANG H, GOU G H, et al. Multi-UAV cooperative and continuous path planning for high-resolution 3D scene reconstruction[J]. Drones, 2023, 7 (9): 544- 569. doi: 10.3390/drones7090544
10	ZHOU Y, XIONG Y H. Multi-UAV coverage path planning method based on improved particle swarm optimization[C]// Proc. of the China Automation Congress, 2024: 2364−2369.
11	CHEN J C, LING F Y, ZHANG Y, et al. Coverage path planning of heterogeneous unmanned aerial vehicles based on ant colony system[J]. Swarm and Evolutionary Computation, 2022, 69, 101005. doi: 10.1016/j.swevo.2021.101005
12	FU Z J, MAO Y H, HE D J, et al. Secure multi-UAV collaborative task allocation[J]. IEEE Access, 2019, 7, 35579- 35587. doi: 10.1109/ACCESS.2019.2902221
13	ZHAO W Z, LIU Y H, LI Y Z, et al. Multi-robot coverage path planning for dimensional inspection of large free-form surfaces based on hierarchical optimization[J]. The International Journal of Advanced Manufacturing Technology, 2023, 127 (11): 5471- 5486.
14	HU H W, FU Z F, LIU Z. Research on collaborative inspection key technologies for multi-UAVs and multi-nests[J]. AIP Advances, 2024, 14 (6): 065208. doi: 10.1063/5.0212773
15	NI J J, GU Y, TANG G Y, et al. Cooperative coverage path planning for multi-mobile robots based on improved K-means clustering and deep reinforcement learning[J]. Electronics, 2024, 13 (5): 944- 960. doi: 10.3390/electronics13050944
16	YUAN Y D, YANG P, JIANG H B, et al. A multi-robot task allocation method based on the synergy of the K-means++ algorithm and the particle swarm algorithm[J]. Biomimetics, 2024, 9 (11): 694- 713. doi: 10.3390/biomimetics9110694
17	罗志远, 丰硕, 刘小峰, 等. 一种基于分步遗传算法的多无人清洁车区域覆盖路径规划方法[J]. 电子测量与仪器学报, 2020, 34 (8): 43- 50.
	LUO Z Y, FENG S, LIU X F, et al. A multi-unmanned cleaning vehicle area coverage path planning method based on stepwise genetic algorithm[J]. Journal of Electronic Measurement and Instrumentation, 2020, 34 (8): 43- 50.
18	於世振. 面向目标跟踪的无人机集群任务分配与路径规划方法研究[D]. 沈阳: 沈阳工业大学, 2023.
	YU S Z. Research on task allocation and path planning methods for UAV swarm targeting tracking[D]. Shenyang: Shenyang University of Technology, 2023.
19	ZHAO B C, HUO M Y, ZHENG L, et al. Clustering-based hyper-heuristic algorithm for multi-region coverage path planning of heterogeneous UAVs[J]. Neurocomputing, 2024, 610, 128528. doi: 10.1016/j.neucom.2024.128528
20	JAEHAN I, BYUNG-YOON L. Multi-agent inspection path planning with large-scale vehicle routing problem[J]. Journal of Aerospace Information Systems, 2023, 20 (7): 378- 386. doi: 10.2514/1.I011202
21	罗刚, 秦小林. 多无人机编队分组覆盖路径规划算法[J]. 计算机应用, 2022, 42 (S02): 148- 154.
	LUO G, QIN X L. Multi-UAV formation grouping coverage path planning algorithm[J]. Journal of Computer Applications, 2022, 42 (S02): 148- 154.
22	赵玉花, 石永康, 万晓燕. 基于粒子群优化的多无人机区域覆盖航迹规划[J]. 农机化研究, 2024, 46 (6): 63- 67. doi: 10.3969/j.issn.1003-188X.2024.06.009
	ZHAO Y H, SHI Y K, WAN X Y. Multi-UAV region coverage trajectory planning based on particle swarm optimization[J]. Journal of Agricultural Mechanization Research, 2024, 46 (6): 63- 67. doi: 10.3969/j.issn.1003-188X.2024.06.009
23	VOLKAN P, PERIHAN P. An efficient path planning approach for autonomous multi-UAV system in target coverage problems[J]. Aircraft Engineering and Aerospace Technology, 2024, 96 (5): 690- 706. doi: 10.1108/AEAT-10-2023-0258
24	HU W J, YAO Y, LIU S M, et al. Multi-UAV coverage path planning: a distributed online cooperation method[J]. IEEE Trans. on Vehicular Technology, 2023, 72 (9): 11727- 11740. doi: 10.1109/TVT.2023.3266817
25	阮姗娜, 陈俊风, 顾菁, 等. 一种基于邻域搜索机制的旅行商问题求解[J]. 微处理机, 2015, 36 (6): 44- 46. doi: 10.3969/j.issn.1002-2279.2015.06.012
	RUAN S N, CHEN J F, GU J, et al. A solution to the traveling salesman problem based on neighborhood search mechanism[J]. Microprocessors, 2015, 36 (6): 44- 46. doi: 10.3969/j.issn.1002-2279.2015.06.012
26	XIE J, CARRILLO L R G, JIN L. Path planning for UAV to cover multiple separated convex polygonal regions[J]. IEEE Access, 2020, 8, 51770- 51785. doi: 10.1109/ACCESS.2020.2980203
27	SHI Y, ZHANG Y Y. The neural network methods for solving traveling salesman problem[J]. Procedia Computer Science, 2022, 199, 681- 686. doi: 10.1016/j.procs.2022.01.084
28	PATRICK S, ROBERT C. Aircraft Inspection by multirotor UAV using coverage path planning[C]// Proc. of the International Conference on Unmanned Aircraft Systems, 2021: 575−581.
29	WANG Q, TAN Y, MEI Z Y. Computational methods of acquisition and processing of 3D point cloud data for construction applications[J]. Archives of Computational Methods in Engineering, 2020, 27, 479- 499. doi: 10.1007/s11831-019-09320-4
30	SHAO Y H, XU X L. Three-dimensional multi-UAV trajectory design for cooperative video inspection and uploading[J]. IEEE Trans. on Vehicular Technology, 2023, 72 (10): 13547- 13558. doi: 10.1109/TVT.2023.3277482
31	KOTYRBA M, VOLNA E, JARUSEK R, et al. The use of conventional clustering methods combined with SOM to increase the efficiency[J]. Neural Computing and Applications, 2021, 33, 16519- 16531. doi: 10.1007/s00521-021-06251-9
32	JIANG N, LIU T. An improved speech segmentation and clustering algorithm based on SOM and K-means[J]. Mathematical Problems in Engineering, 2020, 2020 (1): 3608286.
33	LAI H, HUANG T, LU B, et al. Silhouette coefficient-based weighting k-means algorithm[J]. Neural Computing and Applications, 2025, 37, 3061- 3075. doi: 10.1007/s00521-024-10706-0
34	LI K, YAN X X, HAN Y, et al. Many-objective optimization based path planning of multiple UAVs in oilfield inspection[J]. Applied Intelligence, 2022, 52, 12668- 12683. doi: 10.1007/s10489-021-02977-0
35	高庆吉, 谈政, 管若乔. 基于DEPSO算法的多无人机绕检机队规模优化方法[J]. 计算机应用与软件, 2022, 39 (4): 39- 45. doi: 10.3969/j.issn.1000-386x.2022.04.007
	GAO Q J, TAN Z, GUAN R Q. Optimization of multi-UAV inspection fleet size based on DEPSO algorithm[J]. Computer Applications and Software, 2022, 39 (4): 39- 45. doi: 10.3969/j.issn.1000-386x.2022.04.007
36	ZOLFI K. Gold rush optimizer: a new population-based metaheuristic algorithm[J]. Operations Research and Decisions, 2023, 33 (1): 113- 150.
37	WANG J Q. Intelligent path planning of mobile robot based on genetic algorithm[J]. Journal of Physics: Conference Series, 2023, 2547 (1): 012001- 012009. doi: 10.1088/1742-6596/2547/1/012001
38	BAI Z Z, ZHOU H Y, WEI J H, et al. An exploration-enhanced hybrid algorithm based on regularity evolution for multi-objective multi-UAV 3-D path planning[J]. Complex & Intelligent Systems, 2025, 11 (5): 225- 245.
39	FU Y W, YANG S, LIU B, et al. Multi-UAV cooperative trajectory planning based on the modified cheetah optimization algorithm[J]. Entropy, 2023, 25 (9): 1277- 1300. doi: 10.3390/e25091277
40	LIU X X, SU Y Z, WU Y, et al. Multi-conflict-based optimal algorithm for multi-UAV cooperative path planning[J]. Drones, 2023, 7 (3): 217- 241. doi: 10.3390/drones7030217
41	吴军, 石改琴, 卢帅员, 等. 采用无人机视觉的飞机蒙皮损伤智能检测方法[J]. 中国测试, 2021, 47 (11): 119- 126.
	WU J, SHI G Q, LU S Y, et al. Intelligent detection method for aircraft skin damage using UAV vision[J]. China Testing, 2021, 47 (11): 119- 126.
42	ZHANG J, DU X, DONG Q C, et al. Distributed collaborative complete coverage path planning based on hybrid strategy[J]. Journal of Systems Engineering and Electronics, 2024, 35 (2): 463- 472. doi: 10.23919/JSEE.2023.000118
43	来磊, 邹鲲, 吴德伟, 等. 交互策略改进MOFA进化的多UAV协同航迹规划[J]. 系统工程与电子技术, 2021, 43 (8): 2282- 2289.
	LAI L, ZOU K, WU D W, et al. Multi-UAV cooperative path planning based on improved MOFA evolution of interactive strategy[J]. Systems Engineering and Electronics, 2021, 43 (8): 2282- 2289.

无人机参数	参数设置
探测角/（°）	60
分辨率/px	1280×720
帧率/fps	30

飞机划分区域	采样网格设置	视点数量	覆盖率/%
机身	1.2	215	100.00
左机翼	1.2	59	96.59
右机翼	1.2	59	96.59
尾翼	1.2	34	90.21

飞机划分区域	采样网格设置	视点数量	覆盖率/%
机身	1.2	215	100.00
左机翼	1.16	96	99.96
右机翼	1.16	96	99.96
尾翼	1.15	58	99.98

算法	路径长度
算法	3簇	4簇	5簇
Som	613.17	605.90	622.03
K-means	633.30	612.63	621.85
Som-K-means	610.67	593.89	620.66

算法	4架无人机总路径长度/m	急转弯数量/次
GRO	866.71	189
ACO	1008.72	202
SA	851.11	186
改进GRO	593.89	142