摘要
考虑离港航班可变滑行时间的可量化影响因素,构建了基于反向传播(back propagation,BP)神经网络的离港航班可变滑出时间预测模型,采用遗传算法(genetic algorithm,GA)优化BP神经网络的权值和阈值,并提出基于可变滑出时间预测结果的航空器推出控制策略。最后,基于中国中南某枢纽机场2周的实际运行数据对预测模型及控制策略进行了验证。结果表明:离港航班的可变滑出时间与机场场面交通流有强相关性,与平均滑出时间中度相关,与滑行距离相关性和转弯个数相关性较弱;基于GA优化后的BP神经网络预测结果误差在±60、±180、±300 s内的准确率分别提升了14%、10%和5%;预测结果的平均绝对误差百分比提升了1.87%,平均绝对误差和均方根误差分别减少了3.58 s和32.45 s。基于可变滑出时间预测的离港推出策略比实际推出时间平均晚68 s。研究成果为提升大型枢纽机场场面运行效率和协同决策能力提供了新的思路。
Considering of the quantifiable influencing factors of taxi-out time,the prediction model of departure flight estimated taxi-out time based on back propagation(BP)was constructed.Genetic algorithm(GA)was used to optimize the weights and thresholds of BP neural network,and an aircraft push-out control strategy based on taxi-out time prediction was proposed.Finally,the prediction model and control strategy were validated by two weeks'actual operation data of a hub airport in the central and south China.The results indicate that estimated taxi-out time has strong correlation with airport traffic flow,moderate correlation with average taxi-out time and weak correlation with taxi distance and number of turns.The prediction accuracy of BP neural network optimized by GA is increased by 14%in±60 s,10%in±180 s and 5%in±300 s.And the mean absolute error percentage of the prediction results increased by 1.87%,the mean absolute error decreased by 3.58 s,and the root mean square error decreased by 32.45 s.The calculated off block time based on taxi-out time prediction is 68 s later than the actual off block time.It provides a new way to improve the operation efficiency and collaborative decision-making ability of large hub airports.
作者
黄龙杨
夏正洪
HUANG Long-yang;XIA Zheng-hong(School of Air Traffic Control, Civil Aviation Flight University of China, Guanghan 618307, China)
出处
《科学技术与工程》
北大核心
2021年第33期14434-14439,共6页
Science Technology and Engineering
基金
四川省科技计划项目(2020YFS0541)
中国民用航空飞行学院重点项目(ZJ2021-05)。
关键词
可变滑出时间
BP神经网络
遗传算法
机场场面运行效率
协同决策
estimated taxi-out time
BP neural network
genetic algorithm
airport surface operation efficiency
collaborative decision making
