a modified particle swarm optimization via particle visual modeling     analysis

ISCAS OpenIR > 互联网软件技术实验室

	a modified particle swarm optimization via particle visual modeling analysis
	Zhao Yuxin; Zu Wei; Zeng Haitao
	2009
会议名称	2nd International Conference on Bio-inspired Computing
页码	2022-2029
会议日期	SEP 14-17,
会议地点	Zhengzhou, PEOPLES R CHINA
出版地	THE BOULEVARD, LANGFORD LANE, KIDLINGTON, OXFORD OX5 1GB, ENGLAND
出版者	COMPUTERS & MATHEMATICS WITH APPLICATIONS
ISSN	0898-1221
部门归属	Zhao, Yuxin Harbin Inst Technol, Sch Aerosp, Harbin 150006, Peoples R China. Zhao, Yuxin; Zu, Wei Harbin Engn Univ, Sch Automat, Harbin 150001, Peoples R China. Zeng, Haitao Chinese Acad Sci, Inst Software, Beijing 100080, Peoples R China.
摘要	A particle is treated as a whole individual in all researches on particle swarm optimization (PSO) currently, these are not concerned with the information of every particles dimensional vector. A visual modeling method describing particles dimensional vector behavior is presented in this paper. Based on the analysis of visual modeling, the reason for premature convergence and diversity loss in PSO is explained, and a new modified algorithm is proposed to ensure the rational flight of every particles dimensional component. Meanwhile, two parameters of particle-distribution-degree and particle-dimension-distance are introduced into the proposed algorithm in order to avoid premature convergence. Simulation results of the new PSO algorithm show that it has a better ability of finding the global optimum, and still keeps a rapid convergence as with the standard PSO. (c) 2008 Elsevier Ltd. All rights reserved.
关键词	Particle Swarm Optimization Visual Modeling Method Premature Convergence Particle-distribution-degree
语种	英语
内容类型	会议论文
URI标识	http://ir.iscas.ac.cn/handle/311060/8188
专题	互联网软件技术实验室
推荐引用方式 GB/T 7714	Zhao Yuxin,Zu Wei,Zeng Haitao. a modified particle swarm optimization via particle visual modeling analysis[C]. THE BOULEVARD, LANGFORD LANE, KIDLINGTON, OXFORD OX5 1GB, ENGLAND:COMPUTERS & MATHEMATICS WITH APPLICATIONS,2009:2022-2029.