单亲遗传算法及其全局收敛性分析

A PARTHENO GENETIC ALGORITHM AND ANALYSIS ON ITS GLOBAL CONVERGENCE

序号编码的遗传算法（ＧＡ）不能在两条染色体的任意位置进行交叉，必须使用ＰＭＸ，ＣＸ和ＯＸ等特殊的交叉算子，而这些交叉算子实施起来都很麻烦．针对序号编码ＧＡ的上述不足，提出一种单亲遗传算法（ＰＧＡ）．ＰＧＡ采用序号编码，不使用交叉算子，而代之以隐含序号编码ＧＡ交叉算子功能的基因换位等遗传算子，简化了遗传操作，并且不要求初始群体具有多样性，也不存在“早熟收敛”问题．

Genetic algorithms(GA) using ordinal strings must use special crossover operators such as PMX,OX and CX,instead of general crossover operators.Considering the above deficiency of GA using ordinal strings,this paper proposes a partheno genetic algorithm(PGA) that uses ordinal strings and repeals crossover operators while introduces some particular genetic operators such as gene exchange operator which have the same function as crossover operators.Therefore genetic operation of PGA is simple and its initial population need not be varied and there is no immature convergence in PGA.Calculating examples show the efficiency of PGA.