论文部分内容阅读
将一种改进的实数遗传算法用于函数全局优化。改进的算法建立在对基本实数遗传算法搜索特性判断的基础上。文中对实数遗传算法的基本操作进行了简单的讨论和选择 ,将一种混沌序列作为刺激因素加入到算法中 ,并将区域划分与取舍的思想应用到算法结构改进中。数值实验显示 ,新方法对寻找复杂问题的全局解、提高搜索精度方面较基本实数遗传算法有较大改进。
An improved real-number genetic algorithm is used for global optimization of functions. The improved algorithm is based on the judgment of search characteristics of the basic real-number genetic algorithm. In this paper, the basic operation of real-number genetic algorithm is simply discussed and selected. A chaotic sequence is added as a stimulus to the algorithm, and the idea of dividing and selecting regions is applied to the structural improvement of the algorithm. Numerical experiments show that the new method is more effective than the basic real-number genetic algorithm in finding global solutions to complex problems and improving the search accuracy.