基于DEPSO算法的多无人机绕检机队规模优化方法  

OPTIMIZATION OF MULTI-UAV INSPECTION FLEET SIZE BASED ON DEPSO ALGORITHM

作　　者：高庆吉[1] 谈政 管若乔 Gao Qingji;Tan Zheng;Guan Ruoqiao(Robotics Institute,Civil Aviation University of China,Tianjin 300300,China)

机构地区：[1]中国民航大学机器人研究所,天津300300

出　　处：《计算机应用与软件》2022年第4期39-45,共7页Computer Applications and Software

基　　金：国家自然科学基金委员会-中国民航局民航联合研究基金项目(U1533203)。

摘　　要：为提高民航客机航前航后绕检效率、减少人工成本,研究无人机绕检时多机协作的机队规模优化算法。从多机协作的航迹规划出发,构建客机外观绕检模型,并采用栅格法对绕检作业空间进行离散化;建立航迹规划的约束条件,设计航迹规划代价函数;采用基于差分进化粒子群算法(DEPSO)对机队规模优化,引入差分进化更新粒子群,通过自适应方法调整粒子的惯性权重。仿真结果表明,所研究的方法可获得代价函数指标下的最佳机队规模。In order to improve the efficiency of pre flight and post flight inspection and reduce the labor cost, the optimization algorithm of UAV fleet size is studied. Starting from the path planning of multi aircraft cooperation, this paper constructed the model of aircraft appearance inspection, and discretized the inspection space by grid method;it established the constraint conditions of route planning, and designed the cost function of route planning;it optimized the fleet scale based on differential evolution particle swarm optimization(DEPSO), introduced differential evolution to update particle swarm optimization, and adjusted the inertial weight of particles by adaptive method. The simulation results show that this algorithm can obtain the optimal fleet size under the cost function index.

关 键 词：绕检 无人机 代价函数 差分进化 粒子群算法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]