摘要
提出了一种2输入和2输出的模糊粒子群优化算法。将群体适应度方差和极值差均值作为模糊控制器的两个输入参量,分别用来度量群体在搜索空间分布的离散程度和群体中个体的多样性,从而自适应地控制PSO算法在进化过程中的惯性权重和扩展项的学习因子。测试函数仿真结果表明,该算法很好地平衡了"开发"与"探测",取得了比文献中已有的模糊粒子群算法更好的优化性能。
A new fuzzy PSO algorithm（FPSO） with two inputs and two outputs is proposed on the basis of analyzing some existed FPSOs.Fitness variance and mean extremal deviation are considered as the input parameters of FC so as to measure the discreteness of population in space and the population diversity,respectively.Through this way,the inertia weight and learning factor of the extended term can be adaptively adjusted during the evolutionary process.The simulation results have shown that FPSO balances the exploration and exploitation well and obtains better optimization performance than that obtained in literatures.
出处
《计算机工程与设计》
CSCD
北大核心
2010年第24期5335-5338,共4页
Computer Engineering and Design
基金
陕西省教育厅科研计划基金项目(09JK335)
关键词
模糊粒子群优化
模糊控制器
方差
极值差均值
惯性权重
学习因子
fuzzy particle swarm optimization（FPSO）
fuzzy controller（FC）
variance
mean extremal deviation
inertia weight
learning factor
