解决全局优化问题的粒子群进化算法  

A Particle Swarm Evolutionary Algorithm for Solving Global Optimization Problems

作　　者：白旭英[1] 杨有龙[2] 

机构地区：[1]西北农林科技大学,理学院陕西西安710021 [2]西安电子科技大学理学院,陕西西安710071

出　　处：《现代电子技术》2008年第10期120-122,共3页Modern Electronics Technique

摘　　要：针对复杂全局优化问题,提出一种粒子群进化算法(PSOEA)。针对粒子群算法容易陷入局部最优等缺点,设计一个新的变异算子,使得粒子能够在整个空间进行搜索,同时保证了算法的收敛性。用概率论的有关知识证明了算法的收敛性。仿真结果表明,对于全局优化问题,算法寻优性能优良,特别是对于超高维优化问题,该算法能获得更高精度的解。A particle swarm evolutionary algorithm/or solving global optimization is proposed. Firstly,a new mutation operator is proposed in order to escape from the local optimum. Meanwhile, the convergence of algorithm can he ensured. Finally, the convergence of this algorithm is proved based on the probability. The simulation results show that the algorithm is effective for global optimization problems with high dimension.

关 键 词：粒子群算法 变异 全局优化 概率 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]