基于双通道卷积神经网络的航班延误预测模型

Flight delay prediction model based on dual-channel convolutional neural network

针对航班延误预测数据量大、特征提取困难而传统算法处理能力有限的问题,提出一种基于双通道卷积神经网络(DCNN)的航班延误预测模型。首先,该模型将航班数据和气象数据进行融合,应用DCNN进行自动特征提取,采用批归一化(BN)和Padding策略优化,提升到港延误等级的分类预测性能;然后,在卷积神经网络(CNN)基础上加入直通通道,以保证特征矩阵的无损传输,增强深度网络的畅通性;同时引入卷积衰减因子对卷积通道的特征矩阵进行稀疏性限制,控制不同网络深度的特征叠加比例,维持模型的稳定性。实验结果表明,所提模型与传统模型相比,具有更强的数据处理能力。通过数据融合,航班延误预测准确率可提高1个百分点;加深网络深度后,该模型能保证梯度的稳定,从而训练更深的网络,使准确率提升至92.1%。该基于DCNN算法的模型特征提取充分,预测性能优于对比模型,可更好地服务于民航决策。

Nowadays, flight delay prediction has a large amount of data and the feature extraction is difficult. Traditional models can not solve these problems effectively, so a flight delay prediction model based on Dual-Channel Convolutional Neural Network （DCNN） was proposed. Firstly, flight data and meteorological data were fused in the model. Then, a DCNN was used to extract features automatically, and Batch Normalization （BN） and Padding strategy were used to improve the classification prediction performance of arrival delay level. Secondly, to guarantee the lossless transmission of feature matrix and enhance the patency of deep network, a straight channel was used in the Convolutional Neural Network （CNN）. Meanwhile, convolution attenuation factor was introduced to control the sparseness of feature matrix, it also was used to control the proportion of feature matrix from different depth and guarantee the stability of the model. The experimental results indicate that the proposed model has a stronger data processing capability than the traditional model, and through fusion of meteorological data, the accuracy of the proposed model is improved 1 percentage point. When the networks are deepened, the model can guarantee the stability of gradients and train the deeper network, thus improves the accuracy to 92.1%. The proposed model based on DCNN algorithm has sufficient feature extraction and better prediction performance than the contrast model, it can better serve the civil aviation decision-making.