基于密度聚类与匹配算法的异常飞行行为挖掘  

Abnormal Flight Behavior Mining Based on Density Clustering and Matching Algorithm

作　　者：吴欣蓬 汤新民[1] 毛继志[2] 郭鸿滨[2] 管祥民[3] WU Xinpeng;TANG Xinmin;MAO Jizhi;GUO Hongbin;GUAN Xiangmin(College of Civil Aviation,Nanjing University of Aeronautics&Astronautics,Nanjing 211106,China;Key Laboratory of National Defense Science and Technology of Avionics System Integrated Technology,China Institute of Aeronautical Radio and Electronics,Shanghai 200241,China;Key Laboratory of Civil Aviation General Aviation Operation,Civil Aviation Management Institute of China,Beijing 100102,China)

机构地区：[1]南京航空航天大学民航学院,南京211106 [2]中国航空无线电电子研究所航空电子系统综合技术国防科技重点实验室,上海200241 [3]中国民航管理干部学院民航通用航空运行重点实验室,北京100102

出　　处：《南京航空航天大学学报》2021年第6期863-871,共9页Journal of Nanjing University of Aeronautics & Astronautics

基　　金：国家自然科学基金(61773202)资助项目;中国航空无线电电子研究所航空电子系统综合技术国防科技重点实验室基金(6142505180407)资助项目;中国民航管理干部学院民航通用航空运行重点实验室开放基金(CAMICKFJJ-2019-04)资助项目。

摘　　要：在空中交通愈加拥挤的背景下,航空器的异常飞行行为的有效挖掘可以辅助管制员进行调配决策。现有方法只能辨识飞机空间位置特征异常,存在水平可扩展性的局限。本文考虑位置、速度、高度和航向4个异常特征,采用高度层划分策略、局部异常因子和快速覆盖树对基于密度的有噪声应用中的空间聚类(Density-based spatial clustering of applications with noise,DBSCAN)方法进行改进,提出局部异常因子改进的考虑速度、方向及高度的基于密度聚类方法(Density-based spatial clustering considering speed,direction and high level improved by local outlier factor,LOFDBSC-SDH)密度聚类算法对正常航迹模式进行快速准确提取。然后,基于正常航迹模式设计考虑过点时间和上述异常特征的航迹匹配算法,挖掘异常飞行行为。最后,通过实验仿真验证了本文方法的有效性和应用价值。As air traffic has become increasingly congested,the effective mining of abnormal flight behaviors can assist controllers to make decisions. Current methods can only identify abnormal spatial positions with limited horizontal scalability. This paper incorporates four abnormal characteristics,position,speed,altitude and heading,and improves the density-based spatial clustering of applications with noise(DBSCAN)by the altitude level division strategy,the local outlier factor and the faster cover tree. Then,the density clustering algorithm named density-based spatial clustering considering speed,direction and high level improved by local outlier factor(LOFDBSC-SDH) is proposed to effectively extract the normal track patterns of airplanes.Next,based on the normal track patterns,a track matching algorithm is designed to mine abnormal flight behavior patterns,including flights’ cross-point time and above abnormal features. Finally,the effectiveness of the proposed scheme is verified by the experimental simulation.

关 键 词：密度聚类 高度层划分 快速覆盖树 过点时间 异常飞行行为 

分 类 号：V328[航空宇航科学与技术—人机与环境工程]