过站航班地面保障过程动态预测

王立文; 李彪; 邢志伟; 刘洪恩; 罗谦

doi:10.13700/j.bh.1001-5965.2020.0165

过站航班地面保障过程动态预测

doi: 10.13700/j.bh.1001-5965.2020.0165

王立文¹,
李彪^{1, 2},
邢志伟^2, ,,
刘洪恩²,
罗谦³

1.
中国民航大学航空工程学院, 天津 300300
2.
中国民航大学电子信息与自动化学院, 天津 300300
3.
中国民用航空局第二研究所工程技术研究中心, 成都 610041

基金项目:

国家重点研发计划 2018YFB1601200

国家自然科学基金委员会-中国民用航空局联合研究基金 U1533203

中央高校基本科研业务费-中国民航大学专项 3122019094

详细信息

通讯作者:
邢志伟. E-mail: cauc_xzw@163.com

中图分类号: V351;TP181
计量
- 文章访问数: 675
- HTML全文浏览量: 110
- PDF下载量: 94
- 被引次数: 0
出版历程
- 收稿日期: 2020-04-28
- 录用日期: 2020-06-12
- 网络出版日期: 2021-06-20

Dynamic prediction of ground support process for transit flight

WANG Liwen¹,
LI Biao^{1, 2},
XING Zhiwei^{2
, ,},
LIU Hong'en²,
LUO Qian³

1.
College of Aeronautical Engineering, Civil Aviation University of China, Tianjin 300300, China
2.
College of Electronic Information and Automation, Civil Aviation University of China, Tianjin 300300, China
3.
Engineering Technology Research Center, The Second Research Institute of Civil Aviation Administration of China, Chengdu 610041, China

Funds:

National Key R & D Program of China 2018YFB1601200

National Natural Science Foundation of China-China Civil Aviation Administration Joint Research Fund U1533203

the Fundamental Research Funds for the Central Universities (Special for Civil Aviation University of China) 3122019094

More Information

Corresponding author: XING Zhiwei. E-mail: cauc_xzw@163.com

摘要

摘要:
过站航班地面保障过程预测是机场协同决策系统的重要功能。针对目前无法实现过程精细化动态预测且精度较低的问题，提出了一种基于贝叶斯网络的过站航班地面保障过程动态预测方法。建立了地面保障过程贝叶斯网络模型，设计了基于航班属性的初始样本空间生成算法，结合高斯核概率密度估计构建了地面保障过程动态预测方法。某枢纽机场实际数据的仿真结果表明：所提方法在充分考虑航班运行属性的基础上实现了各保障节点的动态预测，其平均绝对误差仅为2.224 1 min，均方根误差相比其他方法低近2 min，能够为机场运行短时战术组织提供客观的决策依据。
- 航空运输 /
- 动态预测 /
- 地面保障过程 /
- 贝叶斯网络 /
- 航班属性 /
- 核概率密度估计
Abstract:
Prediction of ground support process for transit flights is an important function of airport collaborative decision-making system. Aimed at the problems that the refined dynamic prediction of the process cannot be achieved at present and the accuracy is low, a method for dynamic prediction of the transit ground support process based on the Bayesian network is proposed. A Bayesian network model of ground support process was established. The initial sample space generation algorithm based on flight attributes is designed. Dynamic prediction method of ground support process is constructed in conjunction with Gaussian kernel probability density estimation. According to the simulation results of the actual data of a hub airport, it is shown that the method realizes the dynamic prediction of each support node based on full consideration of flight operation attributes. The average absolute error of each node is only 2.224 1 min, and the root mean square error is about 2 min lower than other methods, which confirm that this method can provide an objective decision-making basis for the short-term tactical organization of airport operations.
- air transportation /
- dynamic prediction /
- ground support process /
- Bayesian network /
- flight attributes /
- kernel probability density estimation

HTML全文

图 1 过站航班地面保障过程

Figure 1. Ground support process for transit flight

下载: 全尺寸图片幻灯片

图 2 地面保障过程网络拓扑

Figure 2. Network topological graph of ground support process

下载: 全尺寸图片幻灯片

图 3 初始样本空间生成结果

Figure 3. Generation results of initial sample space

下载: 全尺寸图片幻灯片

图 4 关键保障节点先验概率模型

Figure 4. Prior kernel probability model of key support nodes

下载: 全尺寸图片幻灯片

图 5 航班到达后的保障过程初始预测结果

Figure 5. Initial prediction results of support process after flight arrival

下载: 全尺寸图片幻灯片

图 6 保障节点条件概率模型样例

Figure 6. Sample of conditional probability model for support nodes

下载: 全尺寸图片幻灯片

图 7 多航班关键保障节点预测结果

Figure 7. Key support node prediction results for multi-flight

下载: 全尺寸图片幻灯片

图 8 多航班预测误差分析结果

Figure 8. Error analysis results of multi-flight prediction

下载: 全尺寸图片幻灯片

图 9 单航班内部过程预测结果对比

Figure 9. Comparison of prediction results for single flight internal process

下载: 全尺寸图片幻灯片

图 10 多航班撤轮挡时间预测对比

Figure 10. Comparison of prediction results for multi-flight off block time

下载: 全尺寸图片幻灯片

表 1 过站航班运行过程属性

Table 1. Operation process attributes for transit flights

字段	属性
航司代码	CA
执飞日期	2019-05-10
机位	240
预计到达	14:13
前序架次	9
航班号	1796
机型	B738
航线性质	国内远程
实际到达	14:25
后序架次	12

下载: 导出CSV

表 2 过站航班运行过程共享时刻数据

Table 2. Shared time data of operation process for transit flights

保障节点	过程时刻
上轮挡	14:30
下客结束	14:38
机上清洁结束	14:47
垃圾完成	14:49
配餐完成	14:45
添加航油完成	14:51
货舱配载上传	14:55
允许上客发布	15:57
机务巡检确认	14:25
上客结束	15:16
撤轮挡	15:19
实际起飞	15:31

下载: 导出CSV

表 3 单航班动态预测结果

Table 3. Dynamic prediction results for single flight

保障节点	初始预测时间/min	最终预测时间/min	实际时间/min
x₁	5.2	5.2	5
x₂	14.5	14.1	13
x₃	25.4	24.1	22
x₄	24.1	28.6	24
x₅	17.7	19.2	20
x₆	23.3	25.8	26
x₇	32.5	32.7	30
x₈	22.8	22.7	23
x₉	29.1	35.9	32
x₁₀	45.4	43.8	41
x₁₁	51.0	54.5	54

下载: 导出CSV

表 4 单航班预测误差分析结果

Table 4. Error analysis results of single flight prediction

保障节点	MAE/min	MRE
x₁	0.247 5	0.049 5
x₂	1.285 1	0.098 9
x₃	4.053 5	0.184 2
x₄	2.495 3	0.104 0
x₅	1.892 3	0.094 6
x₆	0.952 5	0.036 6
x₇	3.816 2	0.127 2
x₈	0.894 7	0.038 9
x₉	2.561 9	0.080 1
x₁₀	4.441 9	0.108 3
x₁₁	1.824 4	0.033 8

下载: 导出CSV

表 5 预测精度参数对比

Table 5. Comparison of prediction accuracy parameters

方法	RMSE/min	TIC
贝叶斯网络演化	0.998 1	0.009 6
深度神经网络	2.921 7	0.029 7

下载: 导出CSV

参考文献(25)

[1]	HERREMA F, CURRAN R, VISSER H, et al. Taxi-out time prediction model at charles de gaulle airport[J]. Journal of Aerospace Information Systems, 2018, 15(3): 1-11. doi: 10.2514/1.I010502
[2]	冯霞, 张鑫, 陈锋. 飞机过站上客过程持续时间分布[J]. 交通运输工程学报, 2017, 17(2): 98-105. doi: 10.3969/j.issn.1671-1637.2017.02.011 FENG X, ZHANG X, CHEN F. Boarding duration distribution of aircraft turnaround[J]. Journal of Traffic and Transportation Engineering, 2017, 17(2): 98-105(in Chinese). doi: 10.3969/j.issn.1671-1637.2017.02.011
[3]	WEI K J, VIKRANT V, ALEXANDRE J. Airline timetable development and fleet assignment incorporating passenger choice[J]. Transportation Science, 2020, 54(1): 139-163. http://papers.ssrn.com/sol3/papers.cfm?abstract_id=3198882
[4]	LI M Z, MEGAN S R, HAMSA B. Topological data analysis for aviation applications[J]. Transportation Research Part E: Logistics and Transportation Review, 2019, 128(1): 1-11. http://www.sciencedirect.com/science/article/pii/S1366554518314558
[5]	CADRARSO L, CELISE D R. Integrated airline planning: Robust update of scheduling and fleet balancing under demand uncertainty[J]. Transportation Research, 2017, 81(8): 227-245. http://www.sciencedirect.com/science/article/pii/S0968090X17301560
[6]	WANG J, GUO H, BAKKER M, et al. An integrated approach for surgery scheduling under uncertainty[J]. Computers & Industrial Engineering, 2018, 118(4): 1-8. http://www.sciencedirect.com/science/article/pii/S0360835218300536
[7]	LUO Q, CHEN Y R, CHEN L Y, et al. Research on situation awareness of airport operation based on Petri nets[J]. IEEE Access, 2019, 7(1): 25438-25451. http://ieeexplore.ieee.org/document/8649632
[8]	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. doi: 10.1109/TITS.2018.2877572
[9]	CHATI Y S, HAMSA B. Modeling of aircraft takeoff weight using Gaussian processes[J]. Air Traffic Control Quarterly, 2018, 26(2): 70-79. http://smartsearch.nstl.gov.cn/paper_detail.html?id=978ceda4fa7d58e7fe5d6a640c0a8ab4
[10]	邢志伟, 朱慧, 李彪, 等. 基于贝叶斯网络的航班离港时间动态估计[J]. 计算机科学, 2019, 46(10): 329-335. doi: 10.11896/jsjkx.181102039 XING Z W, ZHU H, LI B, et al. Dynamic estimation of flight departure time based on Bayesian network[J]. Computer Science, 2019, 46(10): 329-335(in Chinese). doi: 10.11896/jsjkx.181102039
[11]	陈欣, 袁建, 戴靓. 基于空间计量模型的机场网络溢出效应研究[J]. 交通运输系统工程与信息, 2019, 19(4): 211-217. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201904030.htm CHEN X, YUAN J, DAI L. Airport network spillover effect with spatial econometric models[J]. Journal of Transportation Systems Engineering and Information Technology, 2019, 19(4): 211-217(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201904030.htm
[12]	沈琳, 于劲松, 唐荻音, 等. 图模型与学习算法结合的贝叶斯网络自动建模[J]. 北京航空航天大学学报, 2016, 42(7): 1486-1493. doi: 10.13700/j.bh.1001-5965.2015.0445 SHEN L, YU J S, TANG D Y, et al. Automatic learning of Bayesian network structure using graph model and learning algorithm[J]. Journal of Beijing University of Aeronautics and Astronautics, 2016, 42(7): 1486-1493(in Chinese). doi: 10.13700/j.bh.1001-5965.2015.0445
[13]	KO Y, KIM J, RODRIGUE-ZAS S L. Markov chain Monte Carlo simulation of a Bayesian mixture model for gene network inference[J]. Genes & Genomics, 2019, 41(5): 547-555. doi: 10.1007/s13258-019-00789-8
[14]	CONTALDI C, VAFAEE F, NELSON P C. Bayesian network hybrid learning using an elite-guided genetic algorithm[J]. Artificial Intelligence Review, 2018, 29(3): 1-28. doi: 10.1007/s10462-018-9615-5
[15]	邢志伟, 何川, 罗谦, 等. 基于双层k近邻算法航站楼短时客流量预测[J]. 北京航空航天大学学报, 2019, 45(1): 26-34. doi: 10.13700/j.bh.1001-5965.2018.0259 XING Z W, HE C, LUO Q, et al. Terminal building short-term passenger flow forecast based on two-tier k-nearest neighbor algorithm[J]. Journal of Beijing University of Aeronautics and Astronautics, 2019, 45(1): 26-34(in Chinese). doi: 10.13700/j.bh.1001-5965.2018.0259
[16]	CAI P L, WANG Y P, LU G Q, et al. A spatiotemporal correlative k-nearest neighbor model for short-term traffic multistep forecasting[J]. Transportation Research Part C: Emerging Technologies, 2016, 6(2): 21-34. http://www.sciencedirect.com/science/article/pii/S0968090X15003812
[17]	PROKHORCHUK A, DAUWELS J, JAILLET P. Estimating travel time distributions by Bayesian network inference[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(5): 1867-1876. doi: 10.1109/TITS.2019.2899906
[18]	CHEN G, GE Z. Hierarchical Bayesian network modeling framework for large-scale process monitoring and decision making[J]. IEEE Transactions on Control Systems Technology, 2020, 28(2): 671-679. doi: 10.1109/TCST.2018.2882562
[19]	MEGHAN C B. Safety of flight prediction for small unmanned aerial vehicles using dynamic Bayesian networks[D]. Blacksburg: Virginia Polytechnic Institute and State University, 2018.
[20]	XU B, SHOU Y, LUO J, et al. Neural learning control of strict-feedback systems using disturbance observer[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019, 30(5): 1296-1307. doi: 10.1109/TNNLS.2018.2862907
[21]	谢海红, 戴许昊, 齐远, 等. 短时交通流预测的改进K近邻算法[J]. 交通运输工程学报, 2014, 14(3): 87-94. doi: 10.3969/j.issn.1671-1637.2014.03.017 XIE H H, DAI X H, QI Y, et al. Improved K-nearest neighbor algorithm for short-term traffic forecasting[J]. Journal of Traffic and Transportation Engineering, 2014, 14(3): 87-94(in Chinese). doi: 10.3969/j.issn.1671-1637.2014.03.017
[22]	TIAN Z D, LI S J, WANG Y H, et al. A prediction method based on wavelet transform and multiple model fusion for chaotic time series[J]. Chaos, Solitons & Fractals, 2017, 98: 158-172. http://www.sciencedirect.com/science/article/pii/S0960077917300747
[23]	ROBINSON E, BALLAKRISHNAN H, ABRAMSON M, et al. Optimized stochastic coordinated planning of asynchronous air and space assets[J]. Journal of Aerospace Information Systems, 2017, 14(1): 10-25. doi: 10.2514/1.I010415
[24]	CARLOS S C, SALAZAR H, MORENO R, et al. Stochastic planning of electricity and gas networks: An asynchronous column generation approach[J]. Applied Energy, 2019, 233(1): 1065-1077. http://www.sciencedirect.com/science/article/pii/S0306261918314594
[25]	邢志伟, 李彪, 朱慧, 等. 基于深度神经网络的航班保障时间预测研究[J]. 系统仿真学报, 2020, 32(4): 678-686. https://www.cnki.com.cn/Article/CJFDTOTAL-XTFZ202004017.htm XING Z W, LI B, ZHU H, et al. Research on flight ground service time prediction based on deep neural network[J]. Journal of System Simulation, 2020, 32(4): 678-686(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-XTFZ202004017.htm