基于提升树模型的航空器离场滑行时间预测
Aircraft Taxi-Out Time Prediction Based on Boosting Tree Model
DOI: 10.12677/JAST.2019.73009, PDF,    国家科技经费支持
作者: 胡雨昕, 马园园：中国电子科技集团公司第二十八研究所，空中交通管理系统与技术国家重点实验室，江苏 南京；尹嘉男：南京航空航天大学，国家空管飞行流量管理技术重点实验室，江苏 南京
关键词: 民用航空器；离场滑行时间；预测；提升树；机器学习；Civil Aircraft； Taxi-Out Time； Prediction； Boosting Tree； Machine Learning
摘要: 为提升机场运行性能、支撑航空运输决策，提出了基于提升树模型的航空器离场滑行时间预测方法。考虑进场航空器场面运行对离场航空器滑行时间的影响，建立了涵盖四大类、八小类的滑行影响因素特征指标体系，采用提升树方法对离场滑行时间进行了机器学习建模，从多维视角建立了预测性能评价指标。选取上海浦东国际机场进行实例验证表明，所提方法具有较高的预测精度，可显著增强离场航空器滑行性能，并有效提升复杂机场的场面运行效率。
Abstract: In order to improve airport operation performance, and support air transportation decision-making, we propose a method for aircraft taxi-out time prediction based on boosting tree model. Considering the impact of arrivals on departure taxi-out time, an index system covering four categories and eight sub-categories is proposed to reflect the main factors influencing aircraft taxiing activities. Boosting tree method is applied to traina machine learning model for taxi-out time prediction, and then some prediction performance indices are established from a multi-dimensional perspective. A case study of Shanghai Pudong International Airport shows that the proposed method has a high prediction accuracy, which can significantly improve departure taxiing performance and surface operational efficiency at complex airport systems.
文章引用：胡雨昕, 马园园, 尹嘉男. 基于提升树模型的航空器离场滑行时间预测[J]. 国际航空航天科学, 2019, 7(3): 72-79. https://doi.org/10.12677/JAST.2019.73009

参考文献

[1] Yin, J., Hu, M., Ma, Y., Han, K. and Chen, D. (2018) Airport Taxi Situation Awareness with a Macroscopic Distribu-tion Network Analysis. Networks and Spatial Economics, 19, 669-695. [Google Scholar] [CrossRef] 
[2] 胡明华. 空中交通流量管理理论与方法[M]. 北京: 科学出版社, 2010.
[3] Shumsky, R.A. (1995) Dynamic Statistical Models for the Prediction of Aircraft Take-off Times. Ph.D. Thesis, Operations Research Center, MIT, Cambridge, MA.
[4] Herbert, E.J. and Dietz, D.C. (1997) Modeling and Analysis of an Airport Departure Process. Journal of Aircraft, 34, 43-47. [Google Scholar] [CrossRef] 
[5] Idris, H., Clarke, J.P., Bhuva, R., and Kang, L. (2007) Queuing Model for Taxi-Out Time Estimation. Air Traffic Control Quarterly, 10, 1-22. [Google Scholar] [CrossRef] 
[6] 尹嘉男. 平行跑道机场地面容量评估技术研究[D]: [硕士学位论文]. 南京: 南京航空航天大学, 2011.
[7] Lee, H., Malik, W., Zhang, B., Nagarajan, B., and Jung, Y.C. (2013) Taxi Time Prediction at Charlotte Airport Using Fast-Time Simulation and Machine Learning Techniques. 15th AIAA Aviation Technology, Integration, & Operations Conference, Dallas, TX, 22-26 June 2013, 1-11.
[8] Balakrishna, P., Ganesan, R., and Sherry, L. (2010) Accuracy of Reinforcement Learning Algorithms for Predicting Aircraft Taxi-out Times: A Case-Study of Tampa Bay Departures. Transportation Research Part C: Emerging Technologies, 18, 950-962. [Google Scholar] [CrossRef] 
[9] Yin, J., Hu, Y., Ma, Y., Xu, Y., Han, K. and Chen, D. (2018) Ma-chine Learning Techniques for Taxi-out Time Prediction with a Macroscopic Network Topology. IEEE/AIAA 37th Digital Avionics Systems Conference, London, 23-27 September 2018, 713-720. [Google Scholar] [CrossRef] 
[10] European Organisation for the Safety of Air Navigation (2017) Airport CDM Implementation Manual, Version 5. EUROCONTROL, Brussels.
[11] 尹嘉男, 胡雨昕, 马园园, 谢华, 胡明华. 高密度机场空中交通运行特性分析[J]. 科学技术与工程, 2019, 19(18): 346-355.
[12] Dietterich, T.G. (2000) An Experimental Comparison of Three Methods for Constructing Ensembles of Decision Trees: Bagging, Boosting, and Randomization. Machine Learning, 40, 139-157. [Google Scholar] [CrossRef] 

为你推荐