直觉模糊离散粒子群算法  

Intuitionistic fuzzy discrete particle swarm algorithm

作　　者：汪禹喆[1] 雷英杰[1] 周林[1] 李润玲 

机构地区：[1]空军工程大学导弹学院,陕西三原713800 [2]北京军代局232厂,北京100000

出　　处：《控制与决策》2012年第11期1735-1739,共5页Control and Decision

基　　金：国家自然科学基金项目(60773209);陕西省自然科学基金项目(2006F18)

摘　　要：在研究和分析离散粒子群算法(DBPSO)的基础上,提出一种基于直觉模糊熵的改进离散粒子群算法(IFDPSO).该算法以直觉模糊熵作为粒子群状态测度和速度变异的基本参数,同时加入了位置变异策略以保证算法在有限时间内尽可能多地遍历到次优位置及其邻域,增强了算法的全局寻优能力.实验数据表明,在求解较大规模整数规划问题(如0-1背包问题)时,IFDPSO比DPSO和蚁群算法(ACO)更为有效,从而为解决这类问题提供了新的途径和方法.On the basis of the analysis and research on discrete particle swarm optimization algorithm（DPSO）,an improved DPSO algorithm（IFDPSO） based on intuitionistic fuzzy entropy is proposed,which takes the intuitionistic fuzzy entropy as the measure of the state of particle swarm and the parameter of velocity mutation.With the location mutation strategy,the IFDPSO can possibly search as much as possible sub-optimal location and its neighborhood,and the algorithm ability of searching global best value is intensified.The experimental data shows that,in solving large scale integer programming problem such as 0-1 knapsack problem,IFDPSO algorithm represents more effective than DPSO algorithm and ant colony optimization（ACO） algorithm,which provides a new way for solving 0-1 knapsack problem.

关 键 词：离散粒子群算法 直觉模糊熵 直觉模糊离散粒子群算法 背包问题 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]