Aiming at the current high delay rate of the civil aviation transportation industry, and the fact that the high-precision delay prediction problem can hardly be solved by traditional algorithms, a randomly connected Clique Network (CliqueNet) based flight delay prediction model was proposed. Firstly, the flight data and related weather data were fused by the model. Then, making full use of the improved network model to extract features from the fused dataset. Finally, the softmax classifier was used to predict the flight departure delay of all levels with high precision. The main features of the model include random connection of clique feature layers and the introduction of Channel-wise and Spatial Attention Residual (CSAR) block to the transition layer. The former transmits the feature information in a more effective connection; and the latter double-calibrates the feature information on the channel and spatial dimensions to improve accuracy. Experimental results show that the prediction accuracy of the fused data is improved by 0.5% and 1.3% respectively with the introduction of random connection and CSAR block, and the final accuracy of the new model reaches 93.40%.

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.

In the view of the problem that the portability and expansibility current flight delay platform in China can not adapt to the status of large data storage brought by rapid development of Chinese civil aviation, a flight delay big data platform with cross platform, high availability and high expansion was designed. The platform used a big data tool LeafLet as a visual carrier, displayed the flight trajectory in the map interface, and loaded trajectory data to HBase database. Message-Digest Algorithm (MD5) algorithm was used to redesign and optimize the rowkey of flight data table to solve its "hot spot" problem brought by incremental flight time. Considering the shortcomings of multi-level query of HBase filter, a query algorithm based on SolrCloud was proposed, which utilized SolrCloud to realize hierarchical storage of row and index fields, so as to realize HBase two-level fast indexing. Finally, based on historical flight data and flight plan data of HBase, a massive flight information data warehouse based on Hive was constructed. The experimental results show that the expensibility of large data platform for flight delays and the construction of flight information data warehouse can meet the demand of civil aviation for unified storage of data, and the response speed of the multi-condition query is improved by hundreds of times compared with the cluster without second index, and this advantage becomes more and more obvious as the flight data amount grows.