带极值抖动的变尺度粒子群优化算法  

Mutative scale particle swarm optimization algorithm with extremum disturbed

作　　者：刘进[1] 覃洁萍[2] 

机构地区：[1]广西师范学院,南宁530023 [2]广西中医学院,南宁530001

出　　处：《计算机工程与应用》2011年第30期53-57,共5页Computer Engineering and Applications

基　　金：广西科学自然资金计划资助项目(桂科自1013054)

摘　　要：为克服粒子群优化算法容易陷入局部最优解的问题,提出一种带极值抖动的变尺度粒子群优化算法,该算法在粒子进化过程中动态调整学习因子,改善粒子的搜索性能,利用极值抖动方法帮助粒子逃离局部最优解,采用变尺度方法逐步缩小算法的优化范围,提高算法搜索密度。实验表明,该算法对9个具有代表性的基准测试函数,其优化效率及优化精度均优于以往提出的典型粒子群优化改进算法。To overcome the drawbacks of usually being trapped into local minima when solving complex optimal problem using the algorithm of particle swarm optimization,a mutative scale particle swarm optimization algorithm with extremum disturbed is proposed.In the procedure of the particles evolution,the proposed algorithm dynamically adjusts learning factors for improving the search performance,introduces in extremum disturbed method to help the particles escape unexpected local minima,adopts the method of mutative scale shortening the optimal range to increase search density.Experiment results show that the proposed algorithm is superior to previously improved PSO algorithm in efficiency and precision on 9 well-known benchmark test functions.

关 键 词：粒子群优化算法 极值抖动 变尺度 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]