Back to Search Start Over

A modified particle swarm optimization algorithm based on dynamic learning factors and sharing method(基于动态因子和共享适应度的改进粒子群算法)

Authors :
TANYifeng(谭熠峰)
SUNTingting(孙婷婷)
XUXinming(徐新民)
Source :
Zhejiang Daxue xuebao. Lixue ban, Vol 43, Iss 6, Pp 696-700 (2016)
Publication Year :
2016
Publisher :
Zhejiang University Press, 2016.

Abstract

为提高粒子群算法的收敛速度和优化性能,避免陷入局部最优,提出了一种基于动态学习因子和共享适应度函数的改进粒子群算法.在惯性权重w随着迭代次数非线性减少而动态调整学习因子的基础上,引入共享适应度函数.当算法未达到终止条件而收敛时,利用粒子和最优解间距离挑选一批粒子重新初始化形成新群体,并用共享适应度函数对新群体进行评价,新旧2个群体分别追随自己的局部最优解直至迭代结束.对4个典型多峰复杂函数的测试结果表明,该改进算法不仅加快了寻得最优解的速度,而且提高了粒子群算法全局收敛的性能.

Details

Language :
Chinese
ISSN :
10089497
Volume :
43
Issue :
6
Database :
Directory of Open Access Journals
Journal :
Zhejiang Daxue xuebao. Lixue ban
Publication Type :
Academic Journal
Accession number :
edsdoj.362d80ad809f4f7ba41aada92cb40b3b
Document Type :
article
Full Text :
https://doi.org/10.3785/j.issn.1008-9497.2016.06.014