改进的多目标粒子群优化算法及其在雷达布站中的应用  

Improved Multi-Objective Particle Swarm Optimization Algorithm and Its Application in Radar Station Distribution

作　　者：何羚 舒文江 陈良 阎啸 王茜 HE Ling;SHU Wen-jiang;CHEN Liang;YAN Xiao;WANG Qian(School of Aeronautics and Astronautics,University of Electronic and Technology of China,Chengdu 611731;Aircraft Swarm Intelligent Sensing and Cooperative Control Key Laboratory of Sichuan Province,Chengdu 611731;Chengdu Monitoring Station of National Radio Monitoring Center,Chengdu 611136)

机构地区：[1]电子科技大学航空航天学院,成都611731 [2]飞行器集群智能感知与协同控制四川省重点实验室,成都611731 [3]国家无线电监测中心成都监测站,成都611136

出　　处：《电子科技大学学报》2020年第6期806-811,共6页Journal of University of Electronic Science and Technology of China

基　　金：国家自然科学基金(61801093)。

摘　　要：为更好地解决多目标问题,提高多目标优化算法的多样性和收敛性,提出一种改进的多目标粒子群优化算法。算法将种群分为多个子种群同时进行优化搜索并改进粒子速度更新公式,扩大Pareto最优解集的覆盖面;利用反三角函数logistic映射初始化种群,使初始种群分布更均匀;并使用时变变异方法对外部档案进行变异,避免陷入局部最优。通过与标准多目标粒子群优化算法(MOPSO)和NSGA-Ⅱ在标准测试函数ZDT1、ZDT2、KUR上的仿真实验对比,验证了该文提出的改进算法的有效性,并将其应用于雷达优化布站。In order to better solve multi-objective problem and improve the diversity and convergence of multi-objective optimization algorithms,an improved multi-objective particle swarm optimization algorithm is proposed.The algorithm divides the population into several subpopulations for optimization search and improves the particle velocity updating formula to expend the coverage of Pareto optimal solution set,and use inverse trigonometric logistic mapping to initialize the population to make the distribution of initial population more uniform.The time-varying variation method is used to change the external files to avoid local optimization.By comparing the performance of improved algorithm,standard multi-objective particle swarm optimization(MOPSO)algorithms and NSGA-Ⅱon the standard test function,the effectiveness of the improved algorithm proposed in this paper is verified in an optimal radar distribution station.

关 键 词：反三角函数logistics映射 多目标粒子群优化算法 多种群搜索 雷达布站 时变变异 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]