作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2012, Vol. 38 ›› Issue (21): 145-147. doi: 10.3969/j.issn.1000-3428.2012.21.039

• 人工智能及识别技术 • 上一篇    下一篇

一种改进的小波变异粒子群优化算法

高东慧,董平平,田雨波,周昊天   

  1. (江苏科技大学电子信息学院,江苏 镇江 212003)
  • 收稿日期:2011-11-18 出版日期:2012-11-05 发布日期:2012-11-02
  • 作者简介:高东慧(1987-),男,硕士研究生,主研方向:智能优化算法,神经网络;董平平,硕士研究生;田雨波,教授、博士;周昊天,硕士研究生
  • 基金资助:
    国家部委基金资助项目;江苏省高校自然科学基础研究基金资助项目(07KJB510032);江苏省普通高校研究生科研创新计划基金资助项目(CX10S_007Z)

An Improved Particle Swarm Optimization Algorithm with Wavelet Mutation

GAO Dong-hui, DONG Ping-ping, TIAN Yu-bo, ZHOU Hao-tian   

  1. (School of Electronics and Information, Jiangsu University of Science and Technology, Zhenjiang 212003, China)
  • Received:2011-11-18 Online:2012-11-05 Published:2012-11-02

摘要: 为提高粒子群优化(PSO)算法的优化性能,提出一种改进的小波变异粒子群算法(IPSOWM)。在每次迭代时以一定的概率选中粒子进行小波变异扰动,从而克服PSO算法后期易发生早熟收敛和陷入局部最优的缺点。数值仿真结果表明,IPSOWM算法的搜索精度、收敛速度及稳定性均优于PSO和PSOWM算法。

关键词: 粒子群优化算法, 小波变异, 小波变异粒子群优化算法, 全局最优, 鲁棒性

Abstract: Particle Swarm Optimization(PSO) algorithm is difficult to deal with the problems of premature and local convergence. In order to solve the problems, an Improved PSO with Wavelet Mutation(IPSOWM) algorithm is proposed. In IPSOWM, mutation operator is undertaken by selecting particles with certain small probability so as to overcome the PSO’s drawback of occurring premature convergence and trapping in the local optima. Experimental results on benchmark functions show that the performance of IPSOWM algorithm is obviously superior to that of the other PSO algorithms in references, including convergence precision, convergence rate and stability.

Key words: Particle Swarm Optimization(PSO) algorithm, wavelet mutation, PSO algorithm with wavelet mutation, global optimal, robustness

中图分类号: