船舶燃油品质监测的无人机巡航路径优化

Route optimization of UAV in detecting marine fuel quality

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.

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.