| 359 | 0 | 14 |
| 下载次数 | 被引频次 | 阅读次数 |
【背景】随着航空运输需求持续增长，航路网络日益复杂，延误问题变得愈发突出，且易通过航班联动效应在机场网络中传播，带来大范围运行扰动。【目标】延误传播研究旨在揭示延误在机场网络中的扩散路径及其影响机制，为航班调度优化和延误治理提供理论支持与决策依据。【数据】结合中国民用航空局提供的2024年FME航段运行数据。【方法】本文采用基于分层策略的消息传递图神经网络（Hierarchical Message Passing Graph Neural Network，HMPGNN）识别机场间的延误因果关系，构建延误传播动态网络，并进一步建立航线网络与航班量网络，结合复杂网络理论进行网络拓扑结构对比分析，并运用随机森林模型识别延误传播的关键影响因素。【结果】研究结果显示，中小机场在延误传播网络中具有更高的因果强度，延误传播能力更强；航班量度在所有网络指标中对延误传播的影响最为显著，是影响延误传播的主导因素。【应用】该研究成果可为识别延误传播的关键机场、优化航班调度策略提供决策支持，对提升航班运行韧性与航路网络整体效率具有重要现实意义。
Abstract：[Background] With the continuous growth of air transport demand and the increasing complexity of route networks， flight delays have become more prominent and are prone to propagate across airport networks through flight connectivity， resulting in widespread operational disruptions.[Objective] This study aims to reveal the propagation paths and underlying mechanisms of delay spread within airport networks， thereby providing theoretical support and decision-making guidance for flight scheduling optimization and delay mitigation.[Data] The analysis is based on FME segment-level operational data provided by the Civil Aviation Administration of China (CAAC) for 2024.[Methods] A hierarchical message passing graph neural network (HMPGNN) is employed to identify causal relationships of delay propagation between airports and to construct a dynamic delay propagation network. In addition， route and traffic volume networks are developed to compare topological structures using complex network theory， and a random forest model is applied to identify the key influencing factors of delay propagation. [Result] The results show that small and medium-sized airports exhibit higher causal intensity and stronger delay propagation capabilities. Among all network indicators， flight volume degree exerts the most significant influence and is the dominant factor driving delay propagation. [Application] The findings provide decision support for identifying critical airports in delay propagation and for optimizing flight scheduling strategies， thereby enhancing operational resilience and improving the overall efficiency of the route network.
[1] ABDELGHANY K F， SHAH S S， RAINA S， et al. A model for projecting flight delays during irregular operation conditions[J]. Journal of Air Transport Management， 2004， 10(6): 385-394.
[2] CAI K Q， ZHANG J， DU W B， et al. Analysis of the Chinese air route network as a complex network[J]. Chinese Physics B， 2012， 21(2): 028903.
[3] FLEURQUIN P， RAMASCO J J， EGUILUZ V M. Systemic delay propagation in the US airport network[J]. Scientific Reports， 2013， 3: 1159.
[4] 丁建立， 赵键涛， 曹卫东， 等. 基于动态贝叶斯网的航班延误传递分析[J]. 计算机工程与设计， 2015， 36(12): 3311-3316.
[5] ZHANG H， WU W， ZHANG S， et al. Simulation analysis on flight delay propagation under different network configurations[J]. IEEE Access， 2020， 8: 103236-103244.
[6] LI S， XIE D， ZHANG X， et al. Data-driven modeling of systemic air traffic delay propagation: an epidemic model approach[J]. Journal of Advanced Transportation， 2020， 2020: 8816615.
[7] 杜天成， 韩松臣， 韩云祥. 航路网络延误传播分析[J]. 现代计算机， 2022，28(10):1-9.
[8] CHEN S， DU W， LIU R， et al. Finding spatial and temporal features of delay propagation via multi-layer networks[J]. Physica A: Statistical Mechanics and Its Applications， 2023， 614: 128526.
[9] 单小轩， 康嘉伟， 张子捷， 等. 基于SIRS的航线网络延误传播机理研究[J]. 航空计算技术， 2023， 53(6): 40-44.
[10] TANG Z， HUANG S， ZHU X， et al. Research on the multilayer structure of flight delay in China air traffic network[J]. Physica A: Statistical Mechanics and Its Applications， 2023， 609: 128309.
[11] 贺怀清，韩丽旸，周钢，等.航班延误特征可视分析方法[J].计算机工程与设计，2024，45(10):3161-3169.
[12] 张兆宁， 孟凡淑. 基于复杂网络的多机场航班延误传播分析[J]. 科学技术与工程， 2024， 24(18): 7913-7920.
[13] SUGIHARA G， MAY R， YE H， et al. Detecting causality in complex ecosystems[J]. Science， 2012， 338(6106): 496-500.
[14] ZANIN M， BELKOURA S， ZHU Y. Network analysis of Chinese air transport delay propagation[J]. Chinese Journal of Aeronautics， 2017， 30(2): 491-499.
[15] DU W B， ZHANG M Y， ZHANG Y， et al. Delay causality network in air transport systems[J]. Transportation Research Part E: Logistics and Transportation Review， 2018， 118: 466-476.
[16] CAI Q， ALAM S， DUONG V N. A spatial–temporal network perspective for the propagation dynamics of air traffic delays[J]. Engineering， 2021， 7(4): 452-464.
[17] ZENG L， WANG B， WANG T， et al. Research on delay propagation mechanism of air traffic control system based on causal inference[J]. Transportation Research Part C: Emerging Technologies， 2022， 138: 103622.
[18] JIA Z， CAI X， HU Y， et al. Delay propagation network in air transport systems based on refined nonlinear Granger causality[J]. Transportmetrica B: Transport Dynamics， 2022， 10(1): 586-598.
[19] 王娟，郗艳华.基于传递熵的机场间延误传播关系网络[J].计算机应用与软件， 2024， 41(9): 377-382.
[20] SUN M， TIAN Y， WANG X， et al. Transport causality knowledge-guided GCN for propagated delay prediction in airport delay propagation networks[J]. Expert Systems with Applications， 2024， 240: 122426.
[21] 李千千，田勇，万莉莉，等.基于深度可分离注意力网络的机场网络因果时延关系探究[J].交通运输工程与信息学报，2024，22(03):80-92.
[22] LI Q， WU L， GUAN X， et al. Interplay of network topologies in aviation delay propagation: a complex network and machine learning analysis[J]. Physica A: Statistical Mechanics and Its Applications， 2024， 638: 129622.
[23] BREIMAN L. Random forests[J]. Machine Learning， 2001， 45: 5-32.
[24] 中国民用航空局.2024年民航行业发展统计公报[R].北京:中国民用航空局， 2025.
[25] LI Q， JING R. Characterization of delay propagation in the air traffic network[J]. Journal of Air Transport Management， 2021， 94: 102075.
[26] BAGLER G. Analysis of the airport network of India as a complex weighted network[J]. Physica A: Statistical Mechanics and Its Applications， 2008， 387(12): 2972-2980.
基本信息:
DOI：10.19961/j.cnki.1672-4747.2025.03.041
中图分类号:O157.5;V35
引用信息:
[1]黄海峰,王湛,田勇,等.基于因果复杂网络的机场延误传播分析[J].交通运输工程与信息学报().DOI:10.19961/j.cnki.1672-4747.2025.03.041.
基金信息:
江苏省卓越博士后基金（339414）; 南航科研启动基金（90YAT23004）; 2024年江苏省研究生科研与实践创新计划项目（xcxjh20240725）
2025-05-08
2025-05-08
2025-05-08