摘要
在复杂的终端区运行环境下,为了准确分析终端区进场航空器交通流分布情况以及有效评估中心轨迹的提取是否符合标准飞行程序,提出了一种基于自适应谱聚类的终端区进场轨迹识别方法。采用等时间间隔重采样方法对轨迹进行处理,利用多维特征计算轨迹间相似性,提出了基于多特征融合的自适应谱聚类算法,并选取各簇轨迹间距离之和的平均值最小的轨迹作为中心轨迹。试验表明该方法能够有效选取参数使聚类效果最优,并有效识别交通流分布规律。
In complex operating environment of terminal area,and to accurately analyze the traffic flow distribution of arriving aircraft in terminal area and to effectively evaluate whether the extraction of center trajectory conforms to the standard flight procedure,a terminal area entry trajectory recognition method based on adaptive spectral clustering is proposed.The trajectories are processed with the equal time interval resampling method.Using multi-dimensional features,the similarity between trajectories is calculated.Thus,an adaptive spectral clustering algorithm based on multi-feature fusion is proposed,and the track with the smallest average value of the sum of the distances between each cluster track is extracted as the center track.Experiments show that the method can effectively select parameters to optimize the clustering effect,and can effectively identify the traffic flow distribution rule.
作者
杨璐
李印凤
傅子涛
肖淑敏
魏秀杰
YANG Lu;LI Yinfeng;FU Zitao;XIAO Shumin;WEI Xiujie(College of Civil and Architectural Engineering,North China University of Science and Technology,Tangshan 063210,Hebei,China;China Civil Aviation Air Traffic Management Bureau in North China,Beijing 100621,China)
出处
《指挥信息系统与技术》
2022年第4期63-68,共6页
Command Information System and Technology
基金
中国民用航空局华北地区空中交通管理局科技项目(201803和202002)
中国民用航空局安全能力(202072)资助项目。
关键词
中心轨迹
轨迹聚类
谱聚类
center track
trajectory clustering
spectral clustering
