改进克隆选择算法的层叠滤波器的优化设计  

Optimal design of stack filters using an improved clonal selection algorithm

作　　者：赵春晖[1] 赵华 万建[1] 

机构地区：[1]哈尔滨工程大学信息与通信工程学院,黑龙江哈尔滨150001

出　　处：《智能系统学报》2008年第3期254-258,共5页CAAI Transactions on Intelligent Systems

基　　金：国家自然科学基金资助项目(60672034)

摘　　要：层叠滤波器优化设计的核心是正布尔函数最优化的问题.为了提高优化速度并对层叠滤波器进行全局优化设计,提出了一种改进的克隆选择算法.该算法引入多克隆算子和记忆单元及保留群体同时进化的思想.多克隆算子中的个体克隆规模根据个体的亲和度浓度自适应变化;重组操作在父代记忆个体与子代变异后的记忆个体之间展开,避免了近亲繁殖;保留群体的变异保证了群体的多样性.实验结果证明,该算法优化的层叠滤波器能在较短的时间内得到较好的滤波结果.The optimal design of stack filters is actually an optimization of a positive Boolean function. In order to speed up the optimizing rate and produce a global optimal design of the stack filters, an improved clonal selection algorithm （ICSA） is presented, which introduces a polyclonal operator and simultaneous evolution of the memory unit and the reserved group. The number of clonal particles in the memory unit can adaptively change with their affinity concentration. Regrouping operations are made between parent generations and child generations in the memory unit, avoiding problems caused by breeding two close particles. The preservation of group mutations guarantees diversity. Our experimental results confirmed that stack filters optimized with ICSA produce better filtering results in less time.

关 键 词：层叠滤波器 多克隆算子 克隆选择 变异 重组 

分 类 号：TN713[电子电信—电路与系统]