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 ›› 2008, Vol. 34 ›› Issue (17): 205-207,. doi: 10.3969/j.issn.1000-3428.2008.17.073

• 人工智能及识别技术 • 上一篇    下一篇

一种局部与全局相结合的微粒群优化算法

胡乃平,宋世芳   

  1. (青岛科技大学信息科学技术学院,青岛 266042)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-09-05 发布日期:2008-09-05

Local and Global Combined Particle Swarm Optimization Algorithm

HU Nai-ping, SONG Shi-fang   

  1. (School of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266042)
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-09-05 Published:2008-09-05

摘要: 提出一种基于局部与全局搜索相结合的粒子群算法。该算法结合全局和局部PSO算法的优点,摆脱局部极优点的束缚,保持前期搜索速度快的特性,提高全局搜索能力。仿真实验表明,与标准微粒群优化算法相比,该算法的全局收敛性能得到显著提高,有效地避免微粒群优化算法中的局部收敛问题,并快速搜索到全局最优解。

关键词: 微粒群优化, 局部, 全局, 仿真

Abstract: This paper proposes a particle swarm optimization based on local and global combined search. Combining the strongpoint of local search and global search, the new algorithm reduces the possibility of trapping at the local optimum. The advanced algorithm maintains the characteristic of fast search in the early convergence phase, and improves the global search ability. Experimental results indicate that Local and Global Combined Particle Swarm Optimization (LGCPSO) has the advantage of convergence property over PSO. The algorithm avoids the local convergence problem effectively, and has the ability to get a convergence velocity quickly.

Key words: Particle Swarm Optimization(PSO), local, global, simulation

中图分类号: