基于模式比较的遗传算法  

Genetic algorithm based on schema comparison

作　　者：徐金荣[1] 李允[1] 

机构地区：[1]西南交通大学信息科学与技术学院,成都610031

出　　处：《计算机应用》2008年第2期275-278,共4页journal of Computer Applications

基　　金：国家863计划项目(2005AA1Z2130)

摘　　要：在分析了模式阶、模式定义长度和种群多样性三者之间关系的基础上,提出一种新的基于模式比较的遗传算法。该算法的核心在于,使用配对算子来提高子代种群的多样性。配对算子不像简单遗传算法那样随机选择配对,而是根据模式阶和模式长度对染色体进行配对。实验结果表明,该算法有效地避免了简单遗传算法中因种群多样性较差而造成的早熟现象,显著地提高了收敛速度和搜索全局最优解的能力。After analyzing the relationships between schema order, schema defining length and population diversity, a new Genetic Algorithm based on the Schema Comparison （SCGA） was proposed. The key to this algorithm is to use mating operator to improve the offspring＇s population diversity. Different from Simple Genetic Algorithm that adopts random mating strategy, mating operator mates chromosomes according to schema order and schema defining length. The experimental results show that this algorithm can effectively avoid the premature convergence caused by the low population diversity. Moreover, this algorithm improves the ability of searching an optimum solution and increases the convergent speed.

关 键 词：模式 遗传算法 配对算子 种群多样性 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]