基于GIS和遗传-粒子群的公路智能选线方法  

Intelligent route selection of highway alignments based on GIS and hybrid genetic algorithm and particle swarm optimization

作　　者：涂圣文[1,2] 苏州 

机构地区：[1]长沙理工大学交通运输工程学院,湖南长沙410076 [2]东南大学交通学院,江苏南京210096 [3]湖北省公路局科学研究所,湖北武汉430030

出　　处：《长安大学学报（自然科学版）》2010年第4期39-45,共7页Journal of Chang’an University(Natural Science Edition)

基　　金：江苏省交通科学研究计划项目(05R26)

摘　　要：为克服现有路线优化方法难以用于生产实践的缺点,提出了一种基于GIS(地理信息系统)和遗传-粒子群混合算法的方法,以辅助路线平面方案的选择。该方法以AutoCAD Map为平台,直接支持DWG格式地形图,实时获取路线所经区域的空间信息,为方案决策提供依据;优化算法采用一种遗传-粒子群优化算法,该算法在基本粒子群算法中加入遗传算法的交叉、变异算子,综合了遗传算法和粒子群优化算法的优点。数字试验的结果表明:该算法能很快收敛到最优解,达到最优解迭代次数为35次左右;该方法具备较好的寻优性能,适用于公路智能选线的实践。An intelligent route selection methodology based on GIS and a hybrid genetic algorithm（GA） and particle swarm optimization（PSO） is presented to overcome the limitations of existing method in practical applications.AutoCAD Map is taken for the platform of the method and support the topographic maps in DWG format directly.The system built by proposed measure can obtain the spatial information of zones along highway alignments dynamically and offer support to the decision-making of highway route selection.In addition,a hybrid algorithm which integrates the merit of GA and PSO is introduced to perform optimization during route selection.The hybrid algorithm is realized by adding crossover operators and mutation operators of genetic algorithm to basic particle swarm optimization.The numerical example results indicate that the algorithm can quickly converge to the optimal solution for about 35 times of iteration,the presented methodology has good performance in search of the best highway alignment and is suited for the practical applications of intelligent route selection.1 tab,11 figs,16 refs.

关 键 词：道路工程 公路平面线形 智能选线方法 遗传-粒子群混合算法 

分 类 号：U412.32[交通运输工程—道路与铁道工程]