[1] Yuan Xiaohui, Cao Ling, Xia Liangzheng,. Adaptive genetic algorithm with the criterionof premature convergence [J]. Journal of Southeast University (English Edition), 2003, 19 (1): 40-43. [doi:10.3969/j.issn.1003-7985.2003.01.010]

Copy

Adaptive genetic algorithm with the criterionof premature convergence()

具有成熟前收敛判断的自适应遗传算法

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

19

Issue:

2003 1

Page:

40-43

Research Field:

Automation

Publishing date:

2003-03-30

Info

Title:

Adaptive genetic algorithm with the criterionof premature convergence

具有成熟前收敛判断的自适应遗传算法

Author(s):

Yuan Xiaohui, Cao Ling, Xia Liangzheng

Department of Automatic Control Engineering, Southeast University, Nanjing 210096, China

袁晓辉, 曹玲, 夏良正

东南大学自动控制系, 南京 210096

Keywords:

genetic algorithm;  premature convergence;  adaptation

遗传算法;  成熟前收敛;  自适应

PACS:

TP183

DOI:

10.3969/j.issn.1003-7985.2003.01.010

Abstract:

To counter the defect of traditional genetic algorithms, an improved adaptive genetic algorithm with the criterion of premature convergence is provided. The occurrence of premature convergence is forecasted using colony entropy and colony variance. When premature convergence occurs, new individuals are generated in proper scale randomly based on superior individuals in the colony. We use these new individuals to replace some individuals in the old colony. The updated individuals account for 30%-40% of all individuals and the size of scale is related to the distribution of the extreme value of the target function. Simulation tests show that there is much improvement in the speed of convergence and the probability of global convergence.

针对传统的简单遗传算法的缺陷, 提出了改进的具有成熟前收敛判断的自适应遗传算法.用群体熵值和均方差来预报成熟前收敛的发生.当成熟前收敛发生时, 提出以群体中的最优个体为基础, 在其一定大小领域内随机产生若干个体, 取代原种群中的部分个体, 其中更新的个体数占群体中个体总数的30%~40%, 领域大小与目标函数极值点分布有关.仿真实验证明, 算法的收敛速度和全局收敛概率都有显著的提高.

References:

[1] Holland J H. Adaptation in natural and artificial systems[M].Ann Arbor, Mich: University of Michigan Press, 1975.
[2] Srinivas M, Patnaik L M. Genetic algorithm: a survey[J]. Computer, 1994, 27(6):17-27.
[3] Srinivas M, Patnaik L M. Adaptive probabilities of crossover and mutation in genetic algorithms[J]. IEEE Trans on Systems, Man and Cybernetics, 1994, 24(4): 656-667.
[4] Wang Chongyan, Lu Jinghui. Base of information[M]. Beijing: Weapon Engineering Press, 1992.(in Chinese)
[5] Goldberg D E. Genetic algorithms in search, optimization, and machine learning[M]. MA: Addision-Wesley, 1989.

Memo

Memo:

Biographies: Yuan Xiaohui(1962—), male, associate professor, yuan-xh@sina.com.cn.

Common functions