基于轨迹聚类的空中交通流自动识别方法研究  

Research on Automatic Identification of Air Traffic Flow Based on Flight Path Clustering

作　　者：李超群 李善梅[1] 马维宇 张程 LI Chao-qun;LI Shan-mei;MA Wei-yu;ZHANG Cheng(College of Air Traffic Management,Civil Aviation University of China,Tianjin 300300,China)

机构地区：[1]中国民航大学空管学院,天津300300

出　　处：《计算机仿真》2021年第10期73-77,共5页Computer Simulation

基　　金：国家自然科学基金(71801215);中国民航大学大学生创新创业训练计划项目(201910059075);中央高校基本科研业务费中国民航大学专项(3122016C009,3122018D026)。

摘　　要：针对空中交通流自动识别问题,采用极大值和重采样相结合的方法对飞行航迹聚类展开研究。综合飞行航迹的局部空间特征和整体分布特征,建立极大值方法的交通流个数自动判定方法,提出重采样轨迹数据的飞行轨迹相似性度量方法,构建空中交通流的谱聚类识别方法,利用终端区的真实飞行轨迹数据进行实例验证,结果表明上述方法能够快速、有效地实现对空中交通流的自动识别。Aiming at the problem of automatic identification of air traffic flow, the combination of maximum value and resampling was used to study the flight path clustering. Based on the characteristics of local space and global distribution of flight path, an automatic method for determining the number of traffic flows was established by maximum method. A method of flight path similarity measurement based on resampling trajectory data was proposed. A spectrum clustering recognition method for air traffic flow was constructed. The real flight trajectory data in the terminal area was used. The results show that the method can realize the automatic recognition of air traffic flow quickly and effectively.

关 键 词：空中交通流 谱聚类 轨迹 重采样 

分 类 号：V355[航空宇航科学与技术—人机与环境工程]