基于固定机巢的输变配无人机智能巡检方法

doi:10.3969/j.issn.1674-8484.2024.05.005

摘要/Abstract

摘要：

为了实现输变配设备的跨专业无人机（UAV）自动巡检，提出了一种考虑到输变配不同巡检频率的固定机巢巡检策略。基于集合覆盖模型建立了固定机巢选址模型；通过改进k-means聚类算法设计了巡检任务分配模型；将无人机路径规划问题建模为带时间窗的多旅行商问题（MTSPTW），设计了自适应大邻域搜索（ALNS）算法完成求解; 并且使用某实际运维区域进行大规模数据的实例验证。结果表明：某机巢的无人机通过130次起降、703余千米的总飞行距离完成了一个月内共计1 838次输变配混合巡检任务。提出的该方法打破了单个机巢单专业巡视思路，具有大规模巡检场景下的实用性和有效性。

关键词: 无人机（UAV）, 电力巡检, 固定机巢选址, 任务分配, 路径规划, 自适应大邻域搜索（ALNS）

Abstract:

To achieve automated inspection of power transmission towers, substations and distribution poles, a fixed unmanned aerial vehicle (UAV) nest was proposed based strategy that accounts for varying inspection frequencies. A fixed UAV nest deployment model was established based on a set cover problem, and the task assignment model for inspections was developed by enhancing the k-means clustering algorithm. The UAV path planning problem was formulated as a Multi-trip Traveling Salesman Problem with Time Windows (MTSPTW), and solved with an Adaptive Large Neighborhood Search (ALNS) algorithm. The real-world data validation was verified by utilizing a real operational and maintenance environment as an example. The results show that a single UAV nest completes 1 838 mixed inspection tasks over one month, with 130 takeoffs and a total flight distance of over 703 km. The proposed method overcomes the limitations of single-type inspections, proving effective for large-scale scenarios.

Key words: unmanned aerial vehicle (UAV), power inspection, UAV nest deployment, task allocation, path planning, adaptive large neighborhood search(ALNS)

中图分类号:

TM755
V279

黄郑, 王红星, 杜彪, 高嵩, 高峰. 基于固定机巢的输变配无人机智能巡检方法[J]. 汽车安全与节能学报, 2024, 15(5): 670-679.

HUANG Zheng, WANG Hongxing, DU Biao, GAO Song, GAO Feng. Intelligent inspection method for power transmission towers, substations, and distribution poles using fixed UAV nests[J]. Journal of Automotive Safety and Energy, 2024, 15(5): 670-679.

图/表 9

参考文献 33

[1]	LI Linxin. The UAV intelligent inspection of transmission lines[C]// Proceed 2015 Int’l Conf Advan Mech Engi Indu Info. Atlantis Press, Zhengzhou, China. 2015: 1542-1545.
[2]	ZHAI Yongjie, ZHAO Hailong, ZHAO Meng, et al. Design of electric patrol UAVs based on a dual antenna system[J]. Energies, 2018, 11(4): No 866.
[3]	LIU Zifa, WANG Xinyue, LIU Yunyang. Application of unmanned aerial vehicle hangar in transmission tower inspection considering the risk probabilities of steel towers[J]. IEEE Access, 2019, 7: 159048-159057.
[4]	Zormpas A, Moirogiorgou K, Kalaitzakis K, et al. Power transmission lines inspection using properly equipped unmanned aerial vehicle (UAV)[C]// 2018 IEEE Int’l Conf Imag Syst Tech (IST) (IST). Kraków, Poland. IEEE, 2018: 1-5.
[5]	李杰, 董林杰, 汤小兵, 等. 变电站二次设备全向巡检机器人精确定位与作业辨识[J]. 电力工程技术, 2024, 43(3): 234-243.
	LI Jie, DONG Linjie, TANG Xiaobing, et al. Precise positioning and identification of omnidirectional inspection robot for substation secondary equipment[J]. Elect Power Engi Tech, 2024, 43(3): 234-243. (in Chinese)
[6]	周文青, 刘刚. 基于深度学习和无人机图像的架空线路缺陷巡检综述[J]. 电力工程术, 2024, 43(2): 73-82.
	ZHOU Wenqing, LIU Gang. Review of overhead line defect inspection based on deep learning and UAV images[J]. Elect Power Engi Tech, 2024, 43(2): 7 3-82. (in Chinese)
[7]	张东东, 万武艺, 刘欣, 等. 基于无人机的绝缘子带电零值检测技术[J]. 电力工程技术, 2023, 42(1): 234-242.
	ZHANG Dongdong, WAN Wuyi, LIU Xin, et al. Live zero value detection technology of insulator string based on UAV[J]. Elect Power Engi Tech, 2023, 42(1): 234-242. (in Chinese)
[8]	李章萍, 贺亚蒙. 基于 GA-SA 组合算法的山区复杂环境无人机起降点选址[J]. 科学技术与工程, 2024, 24(2): 850-857.
	LI Zhangping, HE Yameng. Site selection of unmanned aerial vehicle take-off and landing points in mountainous complex environment based on GA-SA combination algorithm[J]. Sci Tech Engi, 2024, 24(2): 850-857. (in Chinese)
[9]	谢文茜. 城市物流无人机配送中心选址-分配问题研究[J]. 物流工程与管理, 2024, 46(6): 83-86.
	XIE Wenxi. Research on the location-allocation problem of urban logistics UAV distribution centers[J]. Logist Engi Manag, 2024, 46(6): 83-86. (in Chinese)
[10]	戴永东, 黄政, 高超, 等. 多目标优化最低代价无人机机巢选址方法研究[J]. 重庆大学学报, 2023, 46(6): 136-144.
	DAI Yongdong, HUANG Zheng, GAO Chao, et al. A UAV nest deployment method with multi-target optimization and minimum cost[J]. J Chongqing Univ, 2023, 46(6): 136-144. (in Chinese)
[11]	刘光才, 马寅松. 城市物流无人机配送中心选址及任务分配研究[J]. 飞行力学, 2023, 41(3): 88-94.
	LIU Guangcai, MA Yinsong. Research on location and task allocation of urban logistics UAV distribution center[J]. Flight Dyna, 2023, 41(3): 88-94. (in Chinese)
[12]	Zahedi M H, Sobouti M J, Mohajerzadeh A H, et al. Fuzzy based efficient drone base stations (DBSs) placement in the 5G cellular network[J]. Iran J Fuzz Syst, 2020, 17(2): 29-38.
[13]	Savkin A V, Huang H. Deployment of unmanned aerial vehicle base stations for optimal quality of coverage[J]. IEEE Wire Commun Letts, 2018, 8(1): 321-324.
[14]	Bernardino R, Paias A. Solving the family traveling salesman problem[J]. Europ J Operat Res, 2018, 267(2): 453-466.
[15]	王婷, 符小卫, 高晓光. 基于改进遗传算法的异构多无人机任务分配[J]. 火力与指挥控制, 2013, 38(5): 37-41.
	WANG Ting, FU Xiaowei, GAO Xiaoguang. Cooperative task assignment for heterogeneous multi- UAVs based on improved genetic algorithm[J]. Fire Contr Comm Contr, 2013, 38(5): 37-41. (in Chinese)
[16]	沈林成, 霍霄华, 牛轶峰. 离散粒子群优化算法研究现状综述[J]. 系统工程与电子技术, 2008, 30(10): 1986-1990.
	SHEN Lincheng, HUO Xiao-hua, NIU Yi feng. Survey of discrete particle swarm optimization algorithm[J]. Syst Engi Elect, 2008, 30(10): 1986-1990. (in Chinese)
[17]	Cekmez U, Ozsiginan M, Sahingoz O K. A UAV path planning with parallel ACO algorithm on CUDA platform[C]// 2014 Int’l Conf Unman Aircraf Syst (ICUAS). Orlando, USA. IEEE, 2014: 347-354.
[18]	宋敏, 魏瑞轩, 冯志明. 基于差分进化算法的异构多无人机任务分配[J]. 系统仿真学报, 2010 (7): 1706-1710.
	SONG Min, WEI Ruixuan, FENG Zhiming. Cooperative task assignment for heterogeneous multi-UAVs based on differential evolution algorithm[J]. J Syst Simul, 2010 (7): 1706-1710. (in Chinese)
[19]	霍霄华, 陈岩, 朱华勇, 等. 多UCAV协同控制中的任务分配模型及算法[J]. 国防科技大学学报, 2006(3): 83-88.
	HUO Xiaohua, CHEN Yan, ZHU Huayong, et al. Study on task allocation model and algorithm for multi-UCAV cooperative control[J]. J National Univ Defen Tech, 2006, 28(3): 83-88. (in Chinese)
[20]	XIE Songyan, ZHANG An, BI Wenhao, et al. Multi-UAV mission allocation under constraint[J]. Appl Sci, 2019, 9(11): No 2184.
[21]	YIN Youlong, YIN Yong, LV Qianwei, et al. Multi UAV cooperative task allocation method for intensive corridors of transmission lines inspection[C]// 2021 IEEE Int’l Conf Comput Sci, Elect Info Engi Intel Contr Tech (CEI). Fuzhou, China. IEEE, 2021: 203-208.
[22]	HUANG Qiang, SHENG Zhichao, FANG Yong, et al. A simulated annealing-particle swarm optimization algorithm for UAV multi-target path planning[C]// 2022 2nd Int’l Conf Consum Elect Comput Engi (ICCECE). Guangzhou, China. IEEE, 2022: 906-910.
[23]	HE Wenbiao, LI Wenguang, HU Yongjiang. UAV mission planning based on fish swarm-ant colony optimization[C]// 2023 5th Int’l Conf Intel Contr, Measure Sign Proc (ICMSP). Chengdu, China. IEEE, 2023: 428-432.
[24]	XIANG Chentong, HAO Peng, ZHANG Xuejun. The path planning study of multi-task logistics UAVS under complex low airspace[C]// 2021 33rd Chin Contr Deci Conf (CCDC). Kunming, China. IEEE, 2021: 5238-5242.
[25]	Semiz F, Polat F. Solving the area coverage problem with UAVs: A vehicle routing with time windows variation[J]. Robot Autonom Syst, 2020, 126: No 103435.
[26]	GUO Haonan, WANG Yun, SHANG Pan, et al. Customised bus route design with passenger-to-station assignment optimization[J]. Transportmetrica A: Transport Sci 20, 2024(3): 2214631.
[27]	DUAN Haibin, ZHAO Jianixa, DENG Yimin, et al. Dynamic discrete pigeon-inspired optimization for multi-UAV cooperative search-attack mission planning[J]. IEEE Trans Aeros Elect Syst, 2020, 57(1): 706-720.
[28]	Schwarzrock J, Zacarias I, Bazzan A L C, et al. Solving task allocation problem in multi unmanned aerial vehicles systems using swarm intelligence[J]. Engi Appl Artif Intel, 2018, 72: 10-20.
[29]	Kurdi H, Al-Megren S, Aloboud E, et al. Bee-inspired task allocation algorithm for multi-UAV search and rescue missions[J]. Int’l J Bio-Inspir Comput, 2020, 16(4): 252-263.
[30]	国网江苏省电力有限公司电力科学研究院. GB/T 37136-2018: 电力用户供配电设施运行维护规范[S]. 北京: 中国标准出版社, 2018.
	State Grid Jiangsu Electric Power Co., Ltd. Electric Power Science Research Institute. GB/T 37136-2018: Operation and maintenance standards for power user's distribution and supply facilities [S]. Beijing: Standards Press of China, 2018. (in Chinese)
[31]	国家电网有限公司. 国家电网公司2022年500(330)千伏及以上变电站远程智能巡视系统检测方案[S]. 国家电网有限公司, 2022.
	State Grid Corporation of China. State Grid Corporation's 2022 remote intelligent inspection system detection plan for 500 (330) kV and above substations[S]. State Grid Corporation of China, 2022. (in Chinese)
[32]	ZHAO Xinchao. Simulated annealing algorithm with adaptive neighborhood[J]. Appl Soft Comput, 2011, 11(2): 1827-1836.
[33]	Santini A, Ropke S, Hvattum L M. A comparison of acceptance criteria for the adaptive large neighbourhood search metaheuristic[J]. J Heuristics, 2018, 24: 783-815.

机巢编号	X / km	Y / km	机巢编号	X / km	Y / km
UAV1	2.383 7	2.248 0	UAV7	11.029 2	6.086 3
UAV2	6.194 7	2.277 1	UAV8	16.334 9	6.401 0
UAV3	13.454 9	2.240 6	UAV9	5.682 6	9.745 6
UAV4	18.417 4	0.910 1	UAV10	12.657 7	9.623 1
UAV5	4.381 0	7.210 0	UAV11	16.401 0	9.174 7
UAV6	9.783 9	5.589 9	?	?	?

机巢编号	X / km	Y / km	机巢编号	X / km	Y / km
UAV1	2.383 7	2.248 0	UAV7	11.029 2	6.086 3
UAV2	6.194 7	2.277 1	UAV8	16.334 9	6.401 0
UAV3	13.454 9	2.240 6	UAV9	5.682 6	9.745 6
UAV4	18.417 4	0.910 1	UAV10	12.657 7	9.623 1
UAV5	4.381 0	7.210 0	UAV11	16.401 0	9.174 7
UAV6	9.783 9	5.589 9	?	?	?

参数	取值	参数	取值
rand_d_max	0.1	μ	0.8
rand_d_min	0.4	α₁	30
worst_d_min	3	α₂	20
worst_d_max	10	α₃	10
regret_n	3	η	0.6
T₀	100	δ	50
T_f	0.1	max_iter	500

参数	取值	参数	取值
rand_d_max	0.1	μ	0.8
rand_d_min	0.4	α₁	30
worst_d_min	3	α₂	20
worst_d_max	10	α₃	10
regret_n	3	η	0.6
T₀	100	δ	50
T_f	0.1	max_iter	500

天数	任务轮次	飞行距离/ km	天数	任务轮次	飞行距离/ km
1	5	25.845 6	15	5	26.711 1
2	5	31.949 5	16	5	31.367 9
3	7	27.005 9	17	7	25.193 3
4	2	11.040 7	18	2	11.885 7
5	4	23.681 7	19	4	23.763 3
6	6	35.884 3	20	5	32.267 9
7	4	24.201 7	21	4	24.191 5
8	5	26.753 4	22	5	26.543 4
9	5	31.297 4	23	5	30.768 8
10	7	25.491 1	24	7	24.366 1
11	2	10.862 2	25	2	11.408 8
12	4	23.397 2	26	4	24.067 1
13	6	35.458 7	27	5	30.516 0
14	4	23.635 5	28	4	23.817 1