基于区域残差和LSTM网络的机场延误预测模型  

Airport delay prediction model based on regional residual and LSTM network

作　　者：屈景怡[1] 叶萌 渠星 QU Jingyi;YE Meng;QU Xing(Tianjin Key Laboratory of Advanced Signal Processing,Civil Aviation University of China,Tianjin 300300,China)

机构地区：[1]中国民航大学天津市智能信号与图像处理重点实验室,天津300300

出　　处：《通信学报》2019年第4期149-159,共11页Journal on Communications

基　　金：国家自然科学基金资助项目(No.U1833105);天津市智能信号与图像处理重点实验室开放基金项目(No.2017ASP-TJ01);中央高校基本科研业务费基金资助项目(No.3122018D006)~~

摘　　要：针对目前民航运输业对机场延误预测高精度的要求,提出一种基于区域残差和长短时记忆(RR-LSTM)网络的机场延误预测模型。首先,将机场的属性信息、气象信息和相关运行航班信息进行融合;然后,利用RR-LSTM网络对融合后的机场数据集进行特征提取;最后,构建Softmax分类器对机场延误分类预测。所提RR-LSTM网络模型既能有效提取机场延误数据的时间相关性,又能避免深层LSTM网络的梯度消失问题。实验结果表明,RR-LSTM网络模型预测准确率可达95.52%,取得了比传统网络模型更好的预测效果。其中,融合机场的气象信息和相关运行航班信息后,预测准确率可提高约11%。Nowadays, the civil aviation industry has a high precision requirement of airport delay prediction, so an airport delay prediction model based on the RR-LSTM network was proposed. Firstly, the airport information, meteorological information and related flight information were integrated. Then, the RR-LSTM network was used to extract the features of the fused airport data set. Finally, the Softmax classifier was adopted to classify and predict the airport delay. The proposed RR-LSTM network model can not only extract the time correlation of airport delay data effectively, but also avoid the gradient disappearance problem of deep LSTM network. The experimental results indicate that the RR-LSTM network model has a prediction accuracy of 95.52%, which achieves better prediction results than the traditional network model. The prediction accuracy can be improved about 11% by fusing the weather information and the flight information of the airport.

关 键 词：区域残差网络 长短时记忆网络 机场延误预测 特征提取 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]