J4 ›› 2012, Vol. 50 ›› Issue (4): 725-732.

• 计算机科学 • 上一篇    下一篇

 基于解空间划分的PSO改进算法

赵伟1, 蔡兴盛1,2   

  1. 1. 吉林农业大学 信息技术学院, 长春 130118; 2. 空军航空大学 飞行训练基地| 长春 130062)
  • 出版日期:2012-07-01 发布日期:2012-09-07
  • 通讯作者: 蔡兴盛 E-mail:cxsh131@163.com.

PSO Improved Algorithmg Based on the Solution Space Division

ZHAO Wei1, CAI Xingsheng 1,2   

  1. 1. College of Information Technology, Jilin Agriculture University, Changchun 130118, China;
    2. Base of Flight Training, Aviation University of Air Force, Changchun 130062, China)
  • Online:2012-07-01 Published:2012-09-07
  • Contact: CAI Xingsheng E-mail:cxsh131@163.com.

摘要:

 提出一种基于解空间划分的粒子群优化算法, 该算法在保持粒子群搜索能力的前提下对解空间进行预处理, 寻找最佳搜索区间, 提高了粒子群搜索效率; 在粒子群搜索过程中设置检查点, 动态更新解空间区间划分. 实验结果表明, 该算法有效提高了粒子群的搜索效率, 并使粒子群算法不易陷入局部极值. 同时, 在自适应状态下, 该算法能搜寻到指定精度下粒子群所需的最小迭代次数, 并得到较满意的最优值.

关键词:  局部极值, PSO算法, 解空间划分

Abstract:

 A particle swarm optimization algorithm based on the solution space division was presented. On the premise of no impact on the particle swarm optimization, this algorithm can preprocess the solution space in order to get the optimal-intervals and improve the particle swarm optimization algorithm’s efficiency. Meanwhile, the checkpoints would be set up to update the solution space division dynamically. Experiments show that the algorithm can effectively improve the particle swarm optimization algorithm’s efficiency and solve the problem of trapping the local minimum. Furthermore, the algorithm can get minimum iteration times by designated precision and the results are satisfactory in the adaptive state.

Key words: local extremum, PSO algorithm, solution space division

中图分类号: 

  •