异构多种群双交换遗传算法综合矩形平面阵列  

Synthesis of Plane Array Using Double-crossover Genetic Algorithm Based on Isomerous Multi-population

作　　者：刘洪[1] 王玉峰 周正[1] 蒋挺[1] 庞伟正[2] 

机构地区：[1]北京邮电大学无线网络实验室,北京100876 [2]哈尔滨工程大学信息与通信工程学院,哈尔滨150001

出　　处：《弹箭与制导学报》2007年第2期304-306,共3页Journal of Projectiles,Rockets,Missiles and Guidance

基　　金：国家自然科学基金项目(60372097;60432040);北京市自然科学基金项目(4052021);韩国仁荷大学IT研究中心项目(INHAUWB-ITRC)

摘　　要：提出了一种异构多种群双交换遗传算法并应用该算法来综合矩形平面阵列。该算法通过多个异构子种群并行进化与对精英解的双交换遗传策略相结合的方法,摆脱了传统遗传算法收敛对初始群体的依赖性,克服了收敛陷入局部最优值的缺陷。为了说明该算法的有效性和实用性,运用异构多种群双交换遗传算法对矩形平面阵列的激励幅度和阵元位置进行了优化。The double-crossover genetic algorithm based on isomerous multi-population is presented, and which is used to synthesis plane array. The convergence get rid of the dependence to initial population through combining parallel evolution of multiple heterogeneous populations and genetic strategy of double-crossover operator, and which overcomes the bug of getting in local optimal value. The algorithm is used to optimize the excitation amplitude and element position of plane array in order to show its validity and practicability.

关 键 词：遗传算法 阵列天线 天线阵综合 

分 类 号：TN823[电子电信—信息与通信工程]