摘要
随着地面延误程序的实施,空中交通压力逐渐向地面转移,持续增长的地面运行压力对机场场面管制措施提出了更高更科学的要求。预测机场场面拥堵状态变化规律,设定拥堵状态等级是科学制定机场场面管制措施的重要基础之一。通过对场面拥堵状态分析确定场面拥堵影响因素,并设定场面拥堵状态等级,基于遗传算法优化的长短时记忆网络(genetic algorithm-long short term memory networks,GA-LSTM)算法对跑道头排队架次、主滑行道延误时间、机动区延误时间进行预测并与LSTM算法进行比较,最后,使用模糊C均值聚类算法(fuzzy C-means,FCM)确定预测的拥堵状态数据聚类中心,对拥堵状态进行分类以确定场面拥堵状态等级。研究表明,对场面跑道头排队架次、主滑行道延误时间、机动区延误时间预测的均方根误差分别为1.18架次、1.85 s、2.11 s,该预测结果能够为战略级层面管制决策提供依据。本文所提出的方法对大型机场系统均具有可操作性,可提前预知拥堵可能产生的区域及时段,为管制员提供决策支持,提高空中交通系统的运行效率。
With the implementation of ground delay procedures,the pressure of air traffic is gradually transferred to the ground,and the continuous increase of ground operation pressure has put forward higher and more scientific requirements for airport field control measures.Predicting the change rule of airport surface congestion status and setting the level of congestion status is one of the important bases for scientific formulation of airport surface control measures.By analyzing the congestion status,the factors influencing the congestion was determined and the congestion status level was set,and the genetic algorithm-long short term memory networks(GA-LSTM)algorithm was used to predict the number of runway head queues,main taxiway delays,and maneuvering area delays.Finally,fuzzy C-means(FCM)algorithm was used to determine the predicted congestion data clustering centers and classify the congestion status to determine the field congestion status level.Results show that the root mean square error of the prediction of runway head queues,main taxiway delays and maneuvering area delays are 1.18,1.85 and 2.11 seconds,respectively,and the prediction results can provide a basis for control decisions at the strategic level.The method proposed in this paper is applicable to large airport systems,and can predict the possible areas and time periods of congestion in advance to provide decision support for controllers and improve the operational efficiency of the air traffic system.
作者
徐川
朱新平
瞿菁菁
陈洪浩
XU Chuan;ZHU Xin-ping;QU Jing-jing;CHEN Hong-hao(Air Traffic Control College,Civil Aviation Flight University of China,Guanghan 618300,China)
出处
《科学技术与工程》
北大核心
2022年第35期15825-15831,共7页
Science Technology and Engineering
基金
国家自然科学基金民航联合基金(U1733105)
四川省中央引导地方科技发展专项(2020ZYD094)
四川省科技计划项目(2021YFS0391)
民航飞行技术与飞行安全重点实验室开放基金(FZ2020KF10)。