基于PSO⁃K⁃means算法的机场网络聚类分析  

Airport Network Clustering Analysis Based on PSO⁃K⁃Means Algorithm

作　　者：魏秀杰 李印凤 尚然然 刘元甲 杨璐 肖淑敏 WEI Xiujie;LI Yinfeng;SHANG Ranran;LIU Yuanjia;YANG Lu;XIAO Shumin(College of Civil and Architectural Engineering,North China University of Science and Technology,Tangshan 063210,Hebei,China;State Key Laboratory of Air Traffic Management System and Technology,Nanjing 210023,China;Air Traffic Control Center,China Civil Aviation Air Traffic Management Bureau in North China,Beijing 100621,China)

机构地区：[1]华北理工大学建筑工程学院,河北唐山063210 [2]空中交通管理系统与技术国家重点实验室,南京210023 [3]中国民用航空华北地区空中交通管理局空管中心,北京100621

出　　处：《指挥信息系统与技术》2023年第4期64-69,共6页Command Information System and Technology

基　　金：中国民用航空华北地区空中交通管理局科技资金(201904,202002);民航安全能力建设资金(202072)资助项目。

摘　　要：针对枢纽机场划分时未考虑机场地理空间位置的问题,构建了机场网络拓扑结构,并提出了基于粒子群优化K-均值(PSO-K-means)算法的机场网络聚类方法。首先,利用介数中心度和度值加权分别表征机场的地理空间位置和机场的繁忙程度;然后,基于PSO-K-means算法对机场网络进行聚类,并将国内枢纽机场划分为4个机场集群;最后,依据轮廓系数指标对聚类结果进行评价。研究结果表明,采用介数中心度和度值加权对枢纽机场分类进行量化,可使不同机场集群呈现出等级梯度变化并表现出较强差异性,方法有效且可行。Aimed at the lack of consideration of the geographical spatial location of the airport in the airport grades classification,a topology structure of airport network is constructed,and a method of airport network clustering based on swarm optimization K-means(PSO-K-means)algorithm is proposed.Firstly,the geographical spatial location and airport busyness of the airport are characterized by the betweenness centrality and the degree value weighting.Then,the airport network is clustered based on PSO-K-means algorithm,and the domestic hub airports are divided into four airport clusters.Finally,the clustering results are evaluated according to the silhouette coefficient index.Research results show that the hub airport classification is quantized with the betweenness centrality and the degree value weighting.It can make different airport clusters show the change of hub grade gradient and strong difference,and the method is effective and feasible.

关 键 词：粒子群优化算法 复杂网络中心 机场分类 机场网络 

分 类 号：U8[交通运输工程]