东北大学学报（自然科学版）

东北大学学报(自然科学版) ›› 2005, Vol. 26 ›› Issue (5): 488-491.DOI: -

• 论著 • 上一篇    下一篇

压缩搜索空间与速度范围粒子群优化算法

陈炳瑞;冯夏庭   

  1. 东北大学资源与土木工程学院;东北大学资源与土木工程学院 辽宁沈阳　110004
  • 收稿日期:2013-06-24 修回日期:2013-06-24 出版日期:2005-05-15 发布日期:2013-06-24
  • 通讯作者: Chen, B.-R.
  • 作者简介:-
  • 基金资助:
    国家重点基础研究发展规划项目(2002CB412708);;国家杰出青年科学基金资助项目(50325414)

Particle swarm optimization with contracted ranges of both search space and velocity

Chen, Bing-Rui (1); Feng, Xia-Ting (1)   

  1. (1) School of Resources and Civil Engineering, Northeastern University, Shenyang 110004, China
  • Received:2013-06-24 Revised:2013-06-24 Online:2005-05-15 Published:2013-06-24
  • Contact: Chen, B.-R.
  • About author:-
  • Supported by:
    -

RichHTML

0

PDF (PC)

1885

摘要： 为了改善粒子群优化(PSO)算法的搜索性能,提出一种改进的粒子群算法CSV PSO算法·该算法在粒子群进化的过程中根据粒子群的最佳适应值动态地压缩粒子群的搜索空间与粒子群飞行速度范围;针对PSO算法可能出现的暂时停滞现象,引入分区重新初始化机制·数值仿真结果表明:随着粒子群进化,适当的压缩粒子群搜索空间与飞行速度范围,有利于加速算法收敛,提高收敛精度;该算法收敛速度更快,精度更高,运行更为稳定·

关键词: 粒子群优化, 群智能, 进化计算, 随机优化, 自适应

Abstract: To improve further the performance of PSO (Particle Swarm Optimization), a modified PSO algorithm is proposed and called CSV-PSO algorithm. Based on the best fitness of the particles, the ranges of both search space and velocity of the particles are contracted dynamically with the evolution of particle swarm in CSV-PSO algorithm. To avoid the possible occurrence of stagnation phenomenon in the PSO algorithm, the re-initialization mechanism based on different search spaces is introduced in the CSV-PSO. Numerical examples show that it is of advantage to accelerating the algorithm's convergence and improving its calculation accuracy so as to contract appropriately the ranges of both search space and velocity of particles in evolutionary progress and the algorithm is easier for convergence, more accurate for calculation and more stable for running.

中图分类号: