基于聚类-贝叶斯方法的航班过站延误传播  

Flight Transit Delay Propagation Based on Clustering⁃Bayesian Method

作　　者：陈怡欣 杨尚文 胡锦标 羊钊[3] 张明伟 CHEN Yixin;YANG Shangwen;HU Jingbiao;YANG Zhao;ZHANG Mingwei(College of Civil Aviation,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China;State Key Laboratory of Air Traffic Management System,Nanjing 210023,China;College of General Aviation and Flight,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 [2]空中交通管理系统全国重点实验室,南京210023 [3]南京航空航天大学通用航空与飞行学院,南京211106

出　　处：《指挥信息系统与技术》2023年第5期43-49,共7页Command Information System and Technology

基　　金：国家自然科学基金面上(52172328);江苏省科技基金(BZ2020001);空中交通管理系统与技术国家重点实验室开放基金(SKLATM202107)资助项目。

摘　　要：针对航班过站延误问题,基于过站保障时刻节点数据,提出了基于聚类-贝叶斯方法的航班过站延误传播算法。首先,收集机场内所有航班过站保障流程中的节点时刻数据,将延误数据转化为每个节点的延误严重程度;然后,利用聚类-贝叶斯方法得到频繁延误的节点,并围绕这些延误节点研究前后相关流程之间的延误传播概率;最后,通过试验验证了算法的可行性和有效性。试验结果表明,该算法能够感知过站延误的典型阶段和传播特征,可为缓解航班延误提供依据。Aimed at the problem of flight transit delay,a flight transit delay propagation algorithm based on clustering-Bayesian method is proposed through the transit guarantee time node data.First-ly,the node time data of all flight transit guarantee processes in the airport are collected,and the delay data is converted into the delay severity of each node.Then,the frequent delay nodes are obtained by using the clustering-Bayesian method,and the delay propagation probability between relevant process-es is studied around these delay nodes.Finally,the feasibility and effectiveness of the algorithm are verified by experiments.Experimental results show that the algorithm can perceive the typical stages and propagation characteristics of transit delays.It can provide a reference for alleviating flight delay.

关 键 词：航班过站流程 时刻节点聚类 流程延误概率 贝叶斯网络 

分 类 号：V355[航空宇航科学与技术—人机与环境工程]