利用改进遗传算法求解多极值点函数

The Solution of Multi-Extremum Function by Using Improved Genetic Algorithms

提出了适应度标定公式,解决遗传算法初始阶段和临近结束阶段群体的选择压力,正确引导群体发展方向,解决标定后适应值非负问题.定义了相似度概念,可以在不增加群体规模的前提下增加群体的多样性,解决算法易收敛到局部最优解问题.

In this paper, a new formula for scaling fitness is introduced in order to solve the difficulty for selecting the population at the initial or final phases when using GA, guide the development direction of the population correctly, and solove the problem that the fitness value will be nonnegative after scaling. And the similarity is also defined to increase the varieties of the population without increasing the number of the population, which can solve the problem that the algorithm is prone to be converged on the local optimum.