为了准确预测航空器的落地时间，提高空管部门间的协作效率，采用机器学习的方法对航空器进近阶段飞行时间进行了预测。从实际运行出发，分析航空器在进近管制空域飞行时间产生差异的原因，提出了影响航空器在进近空域飞行的8类因素和17个重要特征。以航空器在进近飞行时间为标签，基于提出的重要特征，采用岭回归、支持向量机、随机森林和神经网络算法，建立了4种基于机器学习的航空器进近飞行时间预测模型。以南京进近为实例，对4种机器学习模型进行训练、验证和测试，对模型的性能指标、特征重要性和影响因素展开分析。研究结果表明，对于航空器进近飞行时间的预测，基于随机森林的模型表现出了最高的预测性能，模型的泛化能力最好、精确度高，回归效果越显著；进场状态是影响航空器进近飞行时间的最重要因素，而进场点和进场高度特征则对结果的贡献度最大。
To improve the prediction accuracy of aircraft landing time, we propose a machine learning method to establish an approach time prediction model. Based on the actual operational situation, the primary reasons for different flying time in approach control are analyzed, including eight major factors with 17 important characteristics. Taking the aircraft flying time in approach airspace as labels, we use the proposed characteristics to build machine learning models with four popular machine learning algorithms:the ridge regression, random forest, support vector machine, and neural network. In the case of Nanjing Approach in China, four machine learning models are trained, validated and tested with practical operational data. The results show that the random forest based model exhibits the best prediction performance with good generalization ability, high accuracy and obvious regression effect. The initial arrival state of aircraft is the most important factor for approach time prediction, while the arrival point and initial altitude are two major characteristics for the prediction results.
[1] 中国民用航空局. 2018年民航行业发展统计公报[EB/OL]. (2019-05-08)[2020-04-24]. http://www.caac.gov.cn/XXGK/XXGK/TJSJ/201905/P020190508519529727887.pdf Civil Aviation Administration of China. 2018 Chinese civil aviation developed statistical bulletin[EB/OL]. (2019-05-08)[2020-04-24].http://www.caac.gov.cn/XXGK/XXGK/TJSJ/201905/P020190508519529727887.pdf.
[2] 王红勇, 赵嶷飞, 崔卫国. 基于网络复杂性的终端区空域结构优化[J].中国民航大学学报, 2014, 32(1):5-9. WANG H Y, ZHAO Y F, CUI W G. Optimization of terminal airspace structure based on network complexity[J].Journal of Civil Aviation University of China, 2014, 32(1):5-9(in Chinese).
[3] 王兴隆, 潘维煌, 赵末. 空中交通相依网络的脆弱性研究[J].航空学报, 2018, 39(12):322235. WANG X L, PAN W H, ZHAO M. Vulnerability of air traffic interdependent network[J].Acta Aeronautica et Astronautica Sinica, 2018, 39(12):322235(in Chinese).
[4] 张洪海, 杨磊, 别翌荟, 等. 终端区进场交通流广义跟驰行为与复杂相变分析[J].航空学报, 2015, 36(3):949-961. ZHANG H H, YANG L, BIE Y H, et al. Analysis on generalized following behavior and complex phase-transition law of approaching traffic flow in terminal airspace[J].Acta Aeronautic et Astronautica Sinica, 2015, 36(3):949-961(in Chinese).
[5] 万莉莉, 胡明华, 田勇, 等. 终端区进离场资源分配优化模型[J].交通运输工程学报, 2016, 16(2):109-117. WAN L L, HU M H, TIAN Y, et al. Optimization model of arrival and departure resource allocation in terminal area[J].Journal of Traffic and Transportation Engineering, 2016, 16(2):109-117(in Chinese).
[6] 王莉莉, 王航臣. 突发事件下大规模空中交通流量管理的组合优化模型[J].航空学报, 2019, 40(8):322898. WANG L L, WANG H C. Combined optimization method for large-scale air traffic flow management under emergencies[J].Acta Aeronautica et Astronautica Sinica, 2019, 40(8):322898(in Chinese).
[7] ROY K, LEVY B, TOMLIN C J. Target tracking and estimated time of arrival (ETA) prediction for arrival aircraft[C]//2006 AIAA Guidance, Navigation, and Control Conference. Reston:AIAA, 2006.
[8] KONYAK M A, DOUCETT S, GALLO E, et al. Improving ground-based trajectory prediction through communication of aircraft intent[C]//2009 AIAA Guidance, Navigation, and Control Conference. Reston:AIAA, 2009.
[9] YEPES J L, HWANG I, ROTEA M. New algorithms for aircraft intent inference and trajectory prediction[J].Journal of Guidance Control & Dynamics, 2007, 30(2):370-382.
[10] ZHANG J, LIU J, HU R, et al. Online four dimensional trajectory prediction method based on aircraft intent updating[J].Aerospace Science & Technology, 2018, 77:774-787.
[11] LEE J, LEE S, HWANG I. Hybrid system modeling and estimation for arrival time prediction in terminal airspace[J].Journal of Guidance Control & Dynamics, 2016, 39(4):903-910.
[12] LEEGE A D, PAASSEN M V, MULDER M. A machine learning approach to trajectory prediction[C]//2013 AIAA Guidance, Navigation, and Control Conference. Reston:AIAA, 2013.
[13] TASTAMBEKOV K, PUECHMOREL S, DELAHAYE D, et al. Aircraft trajectory forecasting using local functional regression in Sobolev space[J].Transportation Research Part C E, 2014, 39:1-22.
[14] HONG S, LEE K. Trajectory prediction for vectored area navigation arrivals[J].Journal of Aerospace Information Systems, 2015, 12(7):1-13.
[15] KIM M S. Analysis of short-term forecasting for flight arrival time[J].Journal of Air Transport Management, 2016, 52:35-41.
[16] WANG Z, LIANG M, DELAHAYE D. A hybrid machine learning model for short-term estimated time of arrival prediction in terminal maneuvering area[J].Transportation Research, 2018, 95:280-294.
[17] BARRATT S T, KOCHENDERFER M J, BOYD S P. Learning probabilistic trajectory models of aircraft in terminal airspace from position data[J].IEEE Transactions on Intelligent Transportation Systems, 2019,20(9):3536-3545.
[18] International Civil Aviation Organization. Procedures for air navigation services:Air traffic management (Sixteenth Edition) Doc4444[S]. Montreal, Canada:ICAO, 2016.
[19] International Civil Aviation Organization. Procedures for air navigation services:Aircraft operations (Sixteenth Edition) Doc8168[S]. Montreal, Canada:ICAO,2014.
[20] HOERL A E, KENNARD R W. Ridge regression:Biased estimation for nonorthogonal problems[J]. Technometrics, 1970, 12(1):55-67.
[21] CORTES C, VAPNIK V N. Support vector networks[J]. Machine Learning, 1995, 20(3):273-297.
[22] HO T K. The Random subspace method for constructing decision forests[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(8):832-844.
[23] BHADESHIA H K D H. Neural networks in materials science[J].ISIJ International,1999,39(10):966-979.
CJA