基于FCM-SVM方法的时空航路网交通状态识别研究  

Research on Traffic State Identification of Spatio-temporal Air Route Network Based on FCM-SVM Method

作　　者：李桂毅[1] 胡明华[1] 张洪海[1] LI Guiyi ,HU Minghua, ZHANG Honghai(College of Civil Avitation , Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China)

机构地区：[1]南京航空航天大学民航学院,南京211106

出　　处：《武汉理工大学学报（交通科学与工程版）》2018年第4期569-573,578,共6页Journal of Wuhan University of Technology（Transportation Science & Engineering）

基　　金：国家自然科学基金(61573181;U1333202);中央高校基本科研业务经费专项资金项目(NJ20140016)资助

摘　　要：识别时空航路网络交通状态,分析交通态势时空特性,可为管控航路交通拥挤提供科学依据.选取航段交通流量、交通密度和交通拥挤度作为评价参数,建立FCM航段交通状态等级划分模型,划分航路网航段交通状态等级;构建基于数据驱动的SVM航路网交通状态识别模型,计算路网交通拥挤指数,识别交通拥挤态势和拥挤瓶颈;采用雷达实测航迹数据对模型进行了验证,实验结果表明,模型符合实际,状态准确率较高,可用于航路网交通拥挤态势识别与监控.By identifying spatio-temporal air route network traffic state and analyzing the spatio-temporal characteristics of air route network traffic situation,this study provides scientific basis for controlling the air traffic congestion.Selecting the Fight segment traffic flow,traffic density and traffic congestion degree as evaluation parameters,a FCM segment traffic state classification model was established to classify the flight segment traffic states.A data-driven SVM air route network traffic state identification model was established to calculate the air route network traffic congestion index and identify congestion situation and congestion bottleneck of the air route network.The model was verified by ATC radar data.The results demonstrate that the model conforms to reality and has a high recognition accuracy,which has a certain value in the identification and monitoring of air route network congestion situation.

关 键 词：航空运输 航路网交通态势识别 模糊聚类分析 支持向量机 航路网拥挤指数 

分 类 号：U491.2[交通运输工程—交通运输规划与管理]