摘要
针对离港航班在机场场面滑出时间的动态性、变化性和不确定性,提出一种基于BP神经网络的离港航班滑出时间预测方法。分析滑出时间影响因素及其相关性,讨论强相关、中度相关和弱相关的影响因素在滑出时间预测中的作用,采用我国中南某枢纽机场两周的实际运行数据对预测模型进行验证。实验结果表明,滑出时间与机场场面交通流强相关,与平均滑出时间中度相关,与滑行距离弱相关;考虑强相关和中度相关影响因素的5元组合预测模型的预测结果最佳,误差范围在±300 s的准确率高达96%;引入弱相关的影响因素后,6元组合预测模型的预测准确率反而有所降低。
Based on the dynamics,variability and uncertainty of departure flights’taxi-out time on the ground,a method to predict the taxi-out time for departure flights based on BP neural network was proposed.The influencing factors of variable taxi-out time and their correlation were analyzed.The effects of strong correlation,medium correlation and weak correlation on the prediction of taxi-out time were discussed,and the predicted model was verified by two weeks’actual operation data of a hub airport in the Central and South China.The results indicate that taxi-out time has strong correlation with airport traffic flow,moderate correlation with average taxi-out time and weak correlation with taxi distance.The 5-element combination forecasting model considering strong correlation and moderate correlation factors has the best prediction results,and the accuracy is 96%when the error range is±300 s.After the introduction of weak correlation factors,the accuracy of the 6-element combination forecasting model is reduced.
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
《计算机工程与设计》
北大核心
2022年第4期1039-1044,共6页
Computer Engineering and Design
基金
四川省科技计划基金项目(2020YFS0541)
四川省中央引导地方科技发展专项基金项目(2020ZYD094)
中国民用航空飞行学院重点基金项目(ZJ2021-05)。
关键词
滑出时间
BP神经网络
机场场面运行效率
协同决策
交通流
taxi-out time
BP neural network
airport surface operation efficiency
collaborative decision making
traffic flow
