过站航班地面保障过程动态预测

过站航班地面保障过程预测是机场协同决策系统的重要功能。针对目前无法实现过程精细化动态预测且精度较低的问题，提出了一种基于贝叶斯网络的过站航班地面保障过程动态预测方法。建立了地面保障过程贝叶斯网络模型，设计了基于航班属性的初始样本空间生成算法，结合高斯核概率密度估计构建了地面保障过程动态预测方法。某枢纽机场实际数据的仿真结果表明:所提方法在充分考虑航班运行属性的基础上实现了各保障节点的动态预测，其平均绝对误差仅为2.224 1 min，均方根误差相比其他方法低近2 min，能够为机场运行短时战术组织提供客观的决策依据。 

Dynamic prediction of ground support process for transit flight

Prediction of ground support process for transit flights is an important function of airport collaborative decision-making system. Aimed at the problems that the refined dynamic prediction of the process cannot be achieved at present and the accuracy is low, a method for dynamic prediction of the transit ground support process based on the Bayesian network is proposed. A Bayesian network model of ground support process was established. The initial sample space generation algorithm based on flight attributes is designed. Dynamic prediction method of ground support process is constructed in conjunction with Gaussian kernel probability density estimation. According to the simulation results of the actual data of a hub airport, it is shown that the method realizes the dynamic prediction of each support node based on full consideration of flight operation attributes. The average absolute error of each node is only 2.224 1 min, and the root mean square error is about 2 min lower than other methods, which confirm that this method can provide an objective decision-making basis for the short-term tactical organization of airport operations.