一种改进的粒子群优化算法及其在无人机航路规划中的应用  

An Improved Particle Swarm Optimization Algorithm and Its Application to UAV Route Planning

作　　者：李鹏[1] 李兵舰[1] 亓亮[1] 陈凯翔 李迪[1] LI Peng;LI Bing-jian;QI Liang;CHEN Kai-xiang;LI Di(The 723 Institute of CSIC,Yangzhou 225101,China)

机构地区：[1]中国船舶重工集团公司第七二三研究所

出　　处：《舰船电子对抗》2019年第5期59-64,共6页Shipboard Electronic Countermeasure

摘　　要：粒子群优化(PSO)算法原理简单、通用性强、搜索能力全面,特别适合用于无人机航路规划。常规的PSO算法容易陷入局部最优,结合遗传算法,对PSO算法的种群进行交叉、变异等操作,根据适应值优劣,对粒子先判断后更新,提高了种群的多样性,避免种群陷入“早熟”,提高了收敛速度。通过对基准测试函数进行测试,结果表明,改进的遗传-粒子群优化(GA-PSO)算法收敛速度更快,收敛精度更高。针对无人机航路规划问题,采用GA-PSO算法进行仿真,仿真结果验证了GA-PSO算法在航路规划中的有效性。Particle swarm optimization(PSO)algorithm has the advantages of simple principle,good generality and comprehensive search capability,is very suitable for unmanned aerial vehicle(UAV)route planning.The conventional PSO algorithm has the defect that easily fall into local optimum.In this paper,genetic algorithm(GA)is combined with the PSO algorithm,and cross and variation is performed on the population of PSO algorithm.According to the adaptive value,the particle is judged and then updated,which increases the diversity of the population,prevents the population from becoming precocious,and improves the rate of convergence.By testing the algorithm by reference test function,the results show that the improved GA-PSO algorithm converges faster and has higher convergence accuracy.For the problem of route planning for UAVs,the GA-PSO algorithm is used to perform simulation and the result verifies the effectiveness of the GA-PSO algorithm in the route planning.

关 键 词：粒子群优化 航路规划 遗传算法 

分 类 号：V249[航空宇航科学与技术—飞行器设计] O221[理学—运筹学与控制论]