基于伪群交叉算法的细金属柱体目标识别  

Target identification of thin metallic cylinders based on pseudo swarm crosser

作　　者：钟卫军[1] 童创明[1] 吕丹[1] 李烟[1] 

机构地区：[1]空军工程大学导弹学院,陕西三原713800

出　　处：《系统工程与电子技术》2009年第6期1328-1331,共4页Systems Engineering and Electronics

基　　金：陕西省自然科学基金项目(2005F23);毫米波国家重点实验室基金项目(K200818)资助课题

摘　　要：从线性分布细金属柱体的散射模型出发,利用多极子展开技术求解电磁散射问题,以测量的散射场和计算散射场间的偏差作为目标函数,将待优化变量设置为描述细金属柱体中心位置的向径和幅角,通过伪群交叉算法(pseudo swarm crossover,PSC)对待优化变量进行优化,使目标函数达到最小值来对自由空间中线性分布的细金属柱体族进行电磁成像。研究结果证实了PSC比多相粒子群算法(multi-phase particle swarm optimiza-tion,MPPSO)有更好的收敛性能、成像精度和更强的抗随机噪声干扰能力。A scattering model based on a multiple expansion is used to solve the scattering problem in this paper. The error between measured scattering data and computed scattering data is considered as an object function. The center position of each thin metallic cylinder is denoted by polar coordinates parameters. The inverse scattering problem is transferred into an optimization problem by minimizing the object function with the polar coordinates parameters being optimization parameters which is solved by pseudo swarm crossover （PSC）. A comparison between the multi-phase particle swarm optimization （MPPSO） and PSC is carried out. The results show that PSC has the better convergence and imaging precision, more robust anti-jamming.

关 键 词：电磁逆散射 伪群交叉算法 多相粒子群算法 收敛 

分 类 号：TN011[电子电信—物理电子学]