针对人工河网难于结构化综合的问题,引入路径系统模型组织人工河网数据,并在形态上对沟渠进行分级、分类。建立基于遗传多目标优化的人工河网自动选取模型,并对模型建立中的几个关键问题进行讨论,给出影响模型选取的三个关键因素,即人工水网选取总量、沟渠最小间距指标、初始化选取中加入少量“骨架”沟渠。选取过程采取分层次进行的办法。首先运用知识规则进行初始化选取,剩下的待选沟渠采用遗传算法进行结构化选取。实验结果表明模型既顾及沟渠的质量特征,同时很好地保持人工河网的图形分布特征。模型能够适用于多种类型的人工河网,具备一定的智能化水平。
Aiming at the issue of ditch network structurally generalized difficultly, the Route System Model is imported to organize the ditch network data, and the ditch is classified morphologically. An automated selection model of ditch based on Multi-objective optimization by genetic algorithm is developed, several key problems in the process of building model are discussed, and three factors influencing model selection are proposed, which are the selection sums of ditches, minimum space between ditches, adding few "primary" ditches in initial selection. Layered method is adopted in selection, initial ditches are selected using knowledge principle, the others are structured selected by Genetic Algorithm. Experiments show that the model is not only considering the ditches' quality characteristics, but also keeping graphical distribution of ditches. The model is suitable for varieties of ditches, with a certain intelligence.