基于知识的遗传算法研究

Research on Knowledge-based Genetic Algorithms

为了提高遗传算法的搜索效率,笔者将遗传算法的迭代过程中产生的数据视为一个信息系统,利用粗糙集可以在没有先验信息的情况下从与问题相关的数据集合中获取知识的能力,对进化过程产生的数据进行知识发现。利用所发现的知识判断被求解问题的类型,确定搜索子空间,指导进化的方向,实现了知识指导下的进化算法。函数优化实验结果表明,该方法能够显著提高遗传算法的搜索效率和寻优精度。

In order to improve the searching efficiency of genetic algorithm, the data generated in the iterative process of genetic algorithm was treated as an information system for the knowlodge discovery of the data generated in evolution process with the help of the ability of rough set to obtain knowledge from problem-relevant data sets without a priori information. The discovered knowledge was used to judge the type of problem to be solved, determine searching subspace, guide evolving direction,and realize knowlege-oriented evolution algorithm. Function optimization experiment results show that the algorithm can significantly improve the searching efficiency and optimal precision of genetic algorithm.