计算Banach不动点的进化策略算法  

An Algorithm of Evolution Strategies for Computing Banach Fixed Point

作　　者：张明[1,2] 周永权[2] 许丽艳[3] 

机构地区：[1]大连水产学院理学院,辽宁大连116023 [2]广西民族大学数学与计算机科学学院,广西南宁530006 [3]哈尔滨工程大学理学院,黑龙江哈尔滨150001

出　　处：《计算机仿真》2009年第7期126-129,共4页Computer Simulation

基　　金：国家自然科学基金(60461001);广西自然科学基金(0542048)

摘　　要：针对目前计算Banach不动点的迭代算法存在着收敛性和性能特征在很大程度上依赖于初始点和计算过程因串行运行造成效率低等问题,提出了应用进化策略算法来计算Banach不动点的并行算法,充分发挥了进化策略算法的群体搜索和全局收敛的特性,快速的并行搜索,有效地克服了经典Banach不动点的迭代算法初始点敏感和效率低的问题。数值计算结果表明该算法收敛速度快、精度高、鲁棒性强,为计算Banach不动点提供了一种可行的方法。Using iteration algorithm to solve Banach fixed point has the problems that the convergence and per-formance characteristics may be highly sensitive to the initial guess and the low efficiency. This paper presents a parallel algorithm for solving Banach fixed point. The method sufficiently takes the advantage of evolution strategies such as group search and global convergence, and quick parallel search can efficiently overcome the problems of high sensitivity to initial guess and the low efficiency. The numerical computation results indicate that the algorithm has high convergence rate and high accuracy, offers an effective way to solve Banach fixed point.

关 键 词：算子方程 巴拿赫不动点定理 进化策略 突变 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]