基于水平集的遗传算法优化的改进  

Improving Optimization for Genetic Algorithms Based on Level Set

作　　者：李庆华[1,2] 杨世达[1,2] 阮幼林[1,2] 

机构地区：[1]国家高性能计算中心(武汉),武汉430074 [2]华中科技大学计算机科学与技术学院,武汉430074

出　　处：《计算机研究与发展》2006年第9期1624-1629,共6页Journal of Computer Research and Development

基　　金：国家自然科学基金项目(60273075);国家"八六三"高技术研究发展计划基金项目(863306ZD110106)

摘　　要：现有的遗传算法大多数没有给出收敛性准则,且存在早熟收敛和收敛速度较慢的难题,为此提出一类新型遗传算法.该算法首先从被优化函数的因变量出发,引入了水平集的新概念,对每一代种群进行分类,把与目标相关的所有信息有机地结合在一起,从而提高了算法的优化速度;其次通过对变异算子进行改进,提高了种群的多样性,有效地避免了遗传算法的早熟收敛;同时还证明了变异算子能提高种群多样性以及新算法能收敛于全局最优解,最后给出了算法的收敛准则.实验表明,该算法正确有效,搜索效率与精度均优于其他方法.Most genetic algorithms now available do not give a convergence rule, and there are difficult problems about premature and slow convergence. To solve these problems, a new kind of genetic algorithms is presented in this paper. Firstly, proceeding from dependent variables of optimized function, a new concept ＂level set＂ is introduced. This method can classify population of each generation and arrange all the aim relevant information effectively, so as to obtain the algorithm with high searching speed. Secondly, through the improvement of mutation operator, the diversity of population can be also improved, which avoids the premature convergence effectively. Meanwhile, the new mutation operator is also proved to be able to improve the diversity Finally a convergence rule of search speed is faster and its population and the new algorithm can converge on the optimum solution. e algorithm is given. Computer simulations show that its convergence and iciency is higher than other algorithms.

关 键 词：遗传算法 水平集 平衡变异算子 收敛准则 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]