Figure 3 - uploaded by Karim Zeghal
Content may be subject to copyright.
Similar publications
Construction projects are complex at every stage; however, the design phase requires primary attention since it is at this phase that the full project can be influenced to a greater extent and at lower cost. In the design phase of construction projects, several specialists from different disciplines participate, particularly in complex projects suc...
Проаналізовано можливості впровадження комплексних геоінформаційних систем для просторового планування аеропортових комплексів на основі дослідження активності аеропортів України, їх пасажиропотоку за останнє десятиріччя. Пасажиропотік є одним з вагомих факторів та передумовою впровадження в аеропортах України геоінформаційних систем, які використо...
For a typically 2D distributed crowd of viewers all trying to get a line-of-sight (LOS) to the same object, the close-packed distribution favors only the few closest viewers who inadvertently occlude the line-of-sight (LOS) for the rest of the group stuck behind them. In this paper we study optimal arrangements of the viewers which guarantee everyo...
Terminal Airspace System Capacity Assessment for Nigeria’s Murtala Mohammed International Airport
Citations
... Step 3.1): Truncate the grid with the number of aircraft is less than , in this paper = 70, and set the corresponding remaining flight time for this gird as 0. This parameter could ensure that the grid contains enough information to calculate the remaining flight time and reduce the cells boundary aliasing effect [32]. ...
Abstract Predicting the arrival aircraft's flight time plays a critical role in effectively optimizing and scheduling spatial‐temporal resources in the terminal airspace. This paper focuses on a data‐driven method for predicting the arrival flight time. First, based on the existing research, a feature set is constructed from four aspects: initial state, arrival pressure, sequencing pressure, and wind information, which are believed to affect arrival flight time significantly. Second, eight widely used models are developed to predict flight time, including linear regression models, nonlinear regression models, and tree‐based ensemble models. Furthermore, the stacking technique is adopted to improve the prediction performance. Finally, take Guangzhou Baiyun International Airport as a study case to verify the proposed method's effectiveness. The results indicate that the arrival pressure (describing the arrival traffic demand) and the sequencing pressure (sketching the arrival traffic distribution) could effectively improve the prediction accuracy. The mean absolute percentage error of the predicted flight time via ATAGA and IGONO can be increased by 1%. Besides, the proposed method of extracting wind data could also improve the prediction performance. The mean absolute error of the predicted flight time via GYA can be reduced by 4.85 s.
... The choice between these options may have to be a local decision, based on local structural constraints and arrival management performance. Arrival throughput/pressure metrics were developed in [7] and [8] and could be used to infer that choice. Figure 12 and Figure 13 from [8] illustrate how such metrics can provide a mapping with arrival management functional layers. ...
... Finally, we investigated the evolution of spacing deviations ( Figure 12). This is measured per leader/trailer pairs of aircraft in the landing sequence, as proposed in [12]: the distance spacing deviation at time t is defined as the difference between the minimum distance to final fix from the position of trailer at time t, and the minimum distance from the position of leader at time t -s, where s is the observed time spacing on final. ...
大型繁忙机场场面布局复杂，场面进离港航空器数量叠加造成机场长期处于高负荷
运转状态， 使得航空器由于滑行时间过长而导致的延误时有发生。同时， 集成了空管、
机场、航空公司三方数据的机场协同管理系统（A-CDM）的广泛使用为研究机场场面运
行效率及预测航空器关键时间节点提供了数据基础。 作为评价场面运行效率的关键指标
之一， 滑行时间预测的准确性不仅为优化航班推出时刻，提高离场时隙的使用效率具有
重要作用，还可以为航空公司准确计算油量、航空器减少地面排放提供理论参考。 基于
以上原因，本文建立深度学习模型预测不确定性条件下的离场航空器滑行时间，具体过
程如下：
首先， 对研究所需的数据进行预处理及分析影响滑行时间的因素。 根据本研究所使
用的多源异构数据进行融合处理，利用数据标准化算法消除不同数据量纲的差异来提高
数据质量。为解决数据不平衡导致的模型鲁棒性降低的问题，使用数据重采样技术平衡
各类别数据的数量。同时，对影响航空器滑行时间的因素及影响程度进行分析，根据因
素的数据特征进一步将其分为静态确定因素（机型，跑道运行模式，滑行距离等） 及动
态不确定因素（机场场面流量、 天气）。
其次，对动态不确定性因素（机场场面流量） 进行预测。 根据数据的时-空属性，利
用滑动时间窗法将数据进行平滑处理， 保证了后续预测的连续性及稳定性。建立长短期
记忆网络-深度神经网络（D-LSTM） 联合模型，预测机场场面实际流量。 使用 D-LSTM
模型对香港机场场面流量进行预测验证。结果显示，与其他机器学习模型相比， D-LSTM
模型预测的准确率为 88.0%，可有效地捕捉场面流量的趋势性及周期性特征。
最后， 建立深度学习模型预测离场航空器滑行时间。根据现阶段航空器滑行时间的
定义及统计方法分别建立两个模型以预测离场航空器滑行时间，分别为： 基于历史统计
数据（未对动态不确定因素进行预测）的航空器滑行时间预测 Wide-Deep 模型；以及
将机场场面流量变为不确定因素下的动态 Wide-Deep 模型。 结果显示， 以上两种深度学
习模型预测精度均明显优于其他机器学习算法，可用于大型机场多种运行条件下离场航
空器滑行时间预测。
