改进的遗传算法

Some Improvement of the Genetic Algorithm

文章指出了传统遗传算法具有收敛速度慢及易于陷入局部最优值误区的缺陷,分析了它们产生的原因,提出了解决这些缺陷的方法。通过增加外族个体来增大种群的多样性,加快种群的收敛速度,提出了一重演化和二重演化的新结构,给出了二重演化的步骤。

This paper states that the traditional genetic algorithm tends to be slow in convergence speed and it has the defect of reaching the part best value easily.After analyzing the causes of these defects,it mamages to get solutions,of which the first one is to expand the variety of population by means of increasing the outer race individual.In this way,it can accelerate the convergence speed of the population and the evolutionary process can avoid falling into the trap of the part best value,thus better individuals evolve.The author also puts forward a new structure consisting of the once evolution and twice evolution,and works out the procedures of the twice evolution as well.