改进的单亲遗传算法在汇水盆地三维建模中的应用研究  

Application and Study of Improved Partheno-Genetic Algorithm to Catchment Basin’s 3-D Modeling

作　　者：杨威[1,2,3] 侯鲲[4] 林和平[4] 于繁华[5] 

机构地区：[1]东北师范大学城市与环境科学学院 [2]东北师范大学计算机学院,长春130117 [3]长春师范学院信息技术学院,长春130032 [4]东北师范大学计算机学院 [5]长春师范学院信息技术学院

出　　处：《系统仿真学报》2005年第11期2749-2751,2755,共4页Journal of System Simulation

基　　金：国家自然科学基金资助项目(40272051)

摘　　要：汇水盆地在地球化学等领域的研究中占有重要地位,但在利用计算机对其进行建模时,根据其传统定义却很难对汇水盆地进行自动提取,因此给出了一个基于点的汇水盆地定义,并针对此定义的特点,提出了一种改进的单亲遗传算法。此算法引入“宽容选择”等机制,简化了遗传操作过程,提高了计算效率,且不要求初始群体的多样性,也有效地克服了“早熟收敛”现象。算法很好地解决了以往用爬山算法对汇水盆地进行三维建模时陷入局部极小点而无法绘制出比较完整的汇水盆地的问题;在进行比较实验时,也证明该算法是十分有效的。Catchment basin is quite important in geochemistry and other domains. But it is rather difficult to auto-detect catchment basin based on its traditional definition when it is modelled with computer. So a definition of Catchment Basin based on dot was given, and an improved Partheno-Genedc algorithm was brought forward according to the definition. The algorithm brought ＂tolerative choice＂ and other improved method simplified genetic operation and increased the computing efficiency. Diversity of initial population was not necessary any more and ＂premature convergence＂ problem was overcome well. This algorithm could work out entire basin in catchment basin＇s 3-D modeling, while the hill-climbing algorithm fellinto local minimum. Experiment also testifies the efficiency of this algorithm.

关 键 词：单亲遗传算法 基于点的汇水盆地 爬山算法 GIS 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]