摘要
随着民航的快速发展,机场空域越发拥挤,迫切需要提高空域扇区规划的科学性。为解决传统方法指标单一、依赖人为经验因素的问题,提出了一种基于空中交通管制的雷达原始数据,采用轨迹信息数据挖掘算法确定空域扇区的方法。根据自回归模型和拉格朗日线性插值法处理航迹数据,建立特征点筛选模型,提取航向、速度、高度航迹特征点集,利用EM聚类得到特征点区域中心,基于特征点区域中心的分布建立拓扑关系,并建立最小成本函数的谱聚类算法优化模型,提出管制空域扇区方案。通过仿真验证了所提方案的可行性。
With the rapid development of civil aviation,airport airspace has become more crowded.How airspace sector planning methods can be improved has become a key research question.The traditional method has the shortcomings of over-simplified indicators and relying on human experiences.This research offered a novel approach to identify airspace sectors using the trajectory information data mining technique based on raw radar data from ATC.Firstly,effective trajectory data were screened using an autoregressive model.Secondly,a feature point screening model was established to extract the heading,speed,and altitude trajectory feature point set.Through EM clustering,the center of the feature areas was determined,and the regional center of aircraft traffic was identified.The distribution of distinctive regional centers and conflict sites was then used to develop a topological relationship between the centers of the feature area points,and an optimization model based on the spectral clustering technique was created.Finally,the approach control airspace sector scheme is proposed,and simulation results verified the feasibility of the method.
作者
曹兴武
姚頔
孙樊荣
闫鑫淼
CAO Xingwu;YAO Di;SUN Fanrong;YAN Xinmiao(School of Electronic and Information Engineering,Beihang University,Beijing 100191,China;China Airspace Management Centre,Beijing 100094,China;College of Civil Aviation,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China)
出处
《北京航空航天大学学报》
EI
CAS
CSCD
北大核心
2023年第12期3237-3244,共8页
Journal of Beijing University of Aeronautics and Astronautics
关键词
时间序列
航迹特征点
聚类分析
向量自回归
空域规划
time series
trajectory feature point
cluster analysis
vector autoregressive
airspace planning
作者简介
通信作者:孙樊荣.E-mail:sunfr@nuaa.edu.cn。
