基本遗传算法设计及改进

The basic design and improvement of genetic algorithm

遗传算法是由美国的J.Holland教授于1975年在他的专著《Adaptation in Natural and Artificial Systems》中首先提出的,它是一类借鉴生物界自然选择和自然遗传机制的随机化搜索算法。遗传算法模拟自然选择和自然遗传过程中发生的繁殖、交叉和基因突变现象,在每次迭代中都保留一组候选解,并按某种指标从解群中选取较优的个体,利用遗传算子(选择、交叉和变异)对这些个体进行组合,产生新一代的候选解群,重复此过程,直到满足某种收敛指标为止。

Genetic algorithm is proposed for the first time by American j. Holland professor in 1975 in his treatise 《Adaptation in Natural and Artificial Systems》. It is a kind of random search algorithm referencing on natural selection and natural genetic process. Genetic algorithm is simulated by natural selection process of natural genetic breeding, crossover and mutation phenomenon. At each iteration, a group of the candidate are kept and selected from population of individuals according to some indexes. Using genetic operator （selection, crossover and mutation）, these individuals are combined and a new generation of candidate is generated. Repeating this process, it is stopped until some convergence index is finished.