进场航空器跑道占用时间预测

摘 要：为了准确预估跑道占用时间（runway occupancy time, ROT），提出了一种将灰狼优化算法和随机森林算法结合的预测模型。首先基于ADS-B轨迹，根据纽瓦克自由国际机场的实际运行情况，提取出进场航空器的跑道占用时间；其次分析跑道出口选择、跑道出口角度、气象条件、跑道入口端速度、跑道出口端的速度、机型、航空公司对跑道占用时间的影响；最后利用灰狼算法实现随机森林参数优化，基于优化后的随机森林模型完成对进场航空器跑道占用时间的预测。实验结果表明，相比实验和文献中的其它方法，该方法对跑道占用时间的预测更为准确，预测值与实际误差值在10 s内的占93.6%。研究结果可用于大型机场实际运行航班跑道占用时间预测。

Research on Runway Occupation Time Prediction of Approaching Aircrafts

Abstract: A prediction model that combines Grey Wolf Optimization algorithm and Random Forest algorithm is proposed to accurately estimate runway occupancy time. Firstly, based on the ADS-B trajectory and the actual operation of Newark Liberty International Airport, the runway occupancy time of the incoming aircraft is extracted. Secondly, the effects of runway exit selection, runway exit angle, weather conditions, entry speed, exit speed, aircraft type, and airline on the runway occupancy time are analyzed. Finally, the Grey Wolf algorithm is used to optimize the parameters of the Random Forest model, and the runway occupancy time of the incoming aircraft is predicted based on the optimized Random Forest model. Experimental results show that compared with other methods in experiments and literature, this method predicts runway occupancy time more accurately, with 93.6% of predicted values within 10 seconds of actual error values. The research results can be used for predicting the runway occupancy time of actual operational flights at large airports.