船舶燃油品质监测无人机巡航路径优化

周云鹏; 封学军; 许博; 沈金星

doi:10.16411/j.cnki.issn1006-7736.2020.03.011

大连海事大学学报 >

2020 , Vol. 46 >Issue 3: 95 - 100

DOI: https://doi.org/10.16411/j.cnki.issn1006-7736.2020.03.011

船舶与海洋工程

船舶燃油品质监测无人机巡航路径优化

周云鹏 ,
封学军 ,
许博 ,
沈金星

展开

（1.河海大学 a.港口海岸与近海工程学院；b.土木与交通学院，南京 210098；2.长江保护与绿色发展研究院，南京 210098）

周云鹏（1996 — ），男，硕士生，E-mail：745051642@qq.com.

收稿日期: 2020-04-13

修回日期: 2020-05-13

网络出版日期: 2020-05-13

基金资助

国家重点研发课题（2019YFC0409004）；江苏省交通运输科技项目（2018Y01/2019Y30）.

收起

Route optimization of UAV in detecting marine fuel quality

ZHOU Yun-peng ,
FENG Xue-jun ,
XU Bo ,
SHEN Jin-xing

Expand

（1a. College of Harbour, Costal and Offshore Engineering;1b.College of Civil and Transportation Engineering, Hohai University, Nanjing 210098, China; 2.Yangtze Institute for Conservation and Development, Nanjing 210098, China）

Received date: 2020-04-13

Revised date: 2020-05-13

Online published: 2020-05-13

Fold

摘要

随着我国船舶排放控制区（SECA）建设从沿海向内河的推进，基于无人机和嗅探法的船舶燃油硫含量检测问题成为行业研究热点.基于移动目标旅行商理论（MTTSP），结合检测过程特点，提出一种航迹预测方法，构建无人机巡检路径优化模型（D-SSP）.针对该模型设计一种遗传算法进行求解，并基于AIS信息服务平台历史数据，在12种不同场景下进行测试与分析.结果显示：随着船舶数量的增加，TSP模型的最优路径时间为D-SSP模型最优解的2.0~79.5倍，证明了D-SSP模型的科学性.算例分析结果可为无人机自动化巡检系统的建立提供参考.

关键词： 无人机; (UAV); 路径优化; 船舶燃油品质监测; 移动目标旅行商问题(MTTSP); 遗传算法

本文引用格式

周云鹏 , 封学军 , 许博 , 沈金星 . 船舶燃油品质监测无人机巡航路径优化[J]. 大连海事大学学报, 2020 , 46(3) : 95 -100 . DOI: 10.16411/j.cnki.issn1006-7736.2020.03.011

Abstract

With the development of China’s ship emission control area (SECA) from coastal areas to inland rivers, the detection of sulfur content in marine fuel oil based on unmanned aerial vehicle(UAV) and sniffer method is becoming a research hotspot in the industry. Based on the theory of moving target traveling salesman (MTTSP) and in consideration of detection characteristics, a track prediction method was proposed to establish a route optimization model of UAV automatic inspection (D-SSP) . A genetic algorithm was designed to solve the model. Based on the historical data of AIS information service platform, the model was tested and analyzed in 12 different scenes. The results show that with the increase of the ships number, the optimal path time of TSP model is 2.0~79.5 times that of D-SSP model, which proves the scientificity of D-SSP model. The results of example analysis can provide reference for the establishment of UAV automatic inspection system.

Key words： unmanned aerial vehicle(UAV); route optimization; detection of marine fuel quality; moving target traveling salesman problem(MTTSP); genetic algorithm

参考文献

[1]徐文文, 殷承启, 许雪记, 张玮.江苏省内河船舶大气污染物排放清单及特征[J].环境科学, 2019, 40(06):2595-2606
[3]胡健波, 朱建华, 彭士涛, 赵宏鑫, 洪宁宁.通过尾气估算船用燃油硫含量的岸基嗅探法实验[J].水道港口, 2018, 39(06):735-738
[5]Balzani L??v J M, Alfoldy B, Beecken J, et al.Field test of available methods to measure remotely SO2 and NOx emissions from ships[J].Atmospheric Measurement Techniques, 2014, 6(6):9735-9782
[6]王蕾, 徐永锋, 胡萌赋.船舶尾气监测在海事排放控制区监管中的应用[J].中国海事, 2019(12):59-60.
[8]史一凡, 孙健, 胡昊.基于无人机技术的低空海洋溢油监测巡航路径[J].中国航海, 2014, 37(01):136-140
[10]孙纯岭, 李影, 任磊磊, 高发荣.无人机灾情巡查区域搜索的建模与求解[J].数学的实践与认识, 2018, 48(15):83-93
[12]魏蕾, 李云斌.无人机海事巡航路径优化研究[J].天津航海, 2015(04):61-64.
[14]Jun Xia, Kai Wang, Shuaian Wang.Drone scheduling to monitor vessels in emission control areas[J]. Transportation Research Part B, 2019, 119:174-196.
[15]胡健波, 朱建华, 彭士涛, 赵宏鑫, 洪宁宁.嗅探法:通过监测尾气估算船用燃油硫含量的技术[J].水道港口, 2018, 39(05):619-625
[17]胡健波, 朱建华, 彭士涛, 赵宏鑫, 洪宁宁, 叶寅.通过尾气估算船用燃油硫含量的跟船嗅探法实验[J].水道港口, 2019, 40(04):450-455
[19]王剑文, 戴光明, 谢柏桥, 张全元.求解TSP问题算法综述[J].计算机工程与科学, 2008(02):72-74+155.
[20]Helvig C.S,Gabriel Robins,Alex ZelikovskyThe moving-target traveling salesman problem[J].Journal of Algorithms, 2003, 49(1):153-174
[21]Bourjolly J-M, Gurtuna O, Lyngvi A.On-orbit servicing: a time-dependent,moving-target traveling salesman problem[J].International Transactions in Operational Research, 2006, 13(5):461-481
[22]Sel?uk K.??leyen, Ukbe U?ar, Figen Balo. A New Solution Approach for Maritime Surveillance Operation: The Case of Aegean Sea[J]. Mathematical Problems in Engineering, 2019, 2019:1-16.
[23]Carlos Groba, Antonio Sartal, Xosé H.Vázquez. Solving the dynamic traveling salesman problem using a genetic algorithm with trajectory prediction: An application to fish aggregating devices[J]. Computers and Operations Research, 2015, 56:22-32.
[24]Groba C, Sartal A, Vázquez XH.Integrating forecasting in metaheuristic methods to solve dynamic routing problems: Evidence from the logistic processes of tuna vessels[J]. Engineering Applications of Artificial Intelligence, 2018(76):55-66.
[25]Rodrigo S.de Moraes, Edison P. de Freitas. Experimental analysis of heuristic solutions for the moving target traveling salesman problem applied to a moving targets monitoring system[J]. Expert Systems With Applications, 2019, 136:392-409.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献