一种基于灾变的单亲遗传算法  

A Partheno-genetic Algorithm Based on Cataclysm

作　　者：周鹏[1] 

机构地区：[1]湖北汽车工业学院,湖北十堰442002

出　　处：《湖北汽车工业学院学报》2007年第2期19-21,共3页Journal of Hubei University Of Automotive Technology

基　　金：湖北省教育厅科学技术研究项目(B200623002)

摘　　要：遗传算法存在着计算时间过长和易导致早熟收敛等缺点。单亲遗传算法不使用基本遗传算法常用的交叉算子,简化了遗传操作过程,且不要求初始群体具有广泛多样性,计算速度较快。但单亲遗传算法使用加快收敛速度的选择算子时,仍容易导致早熟收敛现象。模拟自然界中导致生物大规模灭绝的灾变现象,引入灾变的概念来保证解空间的多样性。提出灾变发生时机的判定方法。将此算法应用在旅行商问题上,实验结果证明了该算法的有效性。Genetic algorithm （GA） has some shortcomings such as needing long computing time and easy to bring immature convergence. Partheno-genetic algorithm （PGA） does not use crossover operator of simple genetic algorithm. In PGA the genetic operator is simple and initial populations need not be varied. PGA makes the speed of convergence faster than GA. But it is easy to bring immature convergence when some choice operator is used to make the speed of convergence. Mimicking the cataclysm of the evolution of eco-system, Cataclysm is introduced to ensure the diversities of the solution spaces. A method is presented to decide when cataclysm occurs. The optimization computing of some examples on traveling salesman problem is made to show that it is useful and simple.

关 键 词：单亲遗传算法 早熟收敛 灾变 旅行商问题 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]