分级变异的动态克隆选择算法  

Dynamic clonal selection algorithm with classified mutation

作　　者：胡江强[1] 郭晨[2] 尹建川[1] 李铁山[1] 

机构地区：[1]大连海事大学航海学院,辽宁大连116026 [2]大连海事大学自动化与电气工程学院,辽宁大连116026

出　　处：《控制与决策》2007年第6期608-612,共5页Control and Decision

基　　金：国家自然科学基金项目(60474014);教育部高等学校博士学科点专项基金项目(20040151007);交通部应用基础研究项目(200432922504)

摘　　要：基于浮点数编码,提出一种分级变异的动态免疫克隆选择优化算法.根据抗体的亲和度将种群分解为3个子种群,分配以不同的搜索任务,实施不同的变异策略.在进化过程中动态改变种群规模、克隆规模和变异参数,从而加快了全局搜索速度,提高了局部搜索精度.对5个复杂函数的优化仿真实验表明了该算法的有效性.A dynamic immune clonal selection algorithm with classified mutation is proposed based on floating point coding. To speed up the global search and improve the local convergence precision, the following two main strategies are introduced. According to the antibody affinity in relation to the antigen, the antibody population is decomposed into several subsets, and they are submitted to respective mutation processes for their different given tasks. Then, the population size, the clone size and the mutation parameters are dynamically changed with evolution processing. The proposed algorithm is used to optimize 5 complex functions for testing and the results show its effectiveness.

关 键 词：浮点数编码 克隆选择 进化算法 动态参数 函数优化 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]