遗传算法多样性测度问题研究  

Research on Diversity Measure of Genetic Algorithms

作　　者：武晓今[1] 朱仲英[1] 

机构地区：[1]上海交通大学自动化系,上海200030

出　　处：《信息与控制》2005年第4期416-422,共7页Information and Control

摘　　要：对个体多样性测度方法做了比较详细的概括,对于基因型遗传进化过程,还从编码层次上讨论了它对多样性的影响.以相对顺序欺骗函数和Rastrigin函数为例,讨论了交换和变异操作对多样性的影响.同时,探讨了增强多样性的方法,验证了参数自适应控制方法对顺序编码的控制和对二进制问题的多样性控制方法,提出了对二进制编码的适值自适应调整方法,并通过仿真验证了该方法的有效性.This paper summarizes the individual diversity measuring methods in detail, and discusses the effect of genotype genetic evolution process on diversity frou the point of viem of coding. Order deceptive function and Rastrigin function are taken as examples to discuss effect of the cross and mutation operation on the diversity. At the same time, the paper discusses the reinforcement methods of diversity, verifies the parameter self-adaptive control method to order and binary coding problems, and proposes a fitness self-adaptive adjustment method to binary, coding problems. The simulation experiments show the validity, of this method.

关 键 词：遗传算法 多样性测度 自适应调整 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]