Traffic flow is used as an essential indicator to measure the performance of the road network and a pivotal basis for road classification. However, the combined prediction model of traffic flow based on seasonal characteristics has been given little attention at present. Because the seasonal autoregressive integrated moving average model (SARIMA) has superior linear fitting characteristics, it is often used to process seasonal time series. In contrast, the non-autoregressive dynamic neural network (NAR) has a vital memory function and nonlinear interpretation capabilities. They are suitable for constructing combined forecasting models. The traffic flow time series of a highway in southwest China is taken as the research object in this paper. Combining the SARIMA (0,1,2) (0,1,2)₁₂ model and the NAR model with 15 hidden layer neurons and fourth-order delay, two combined models are constructed: the linear and nonlinear component combination method is realized by the SARIMA-NAR combination model 1, and the MSE weight combination method is used by the SARIMA-NAR combination model 2. We calculated that the prediction accuracy of SARIMA-NAR combined model 1 is as high as 0.92, and the prediction accuracy of SARIMA-NAR combined model 2 is 0.90. In addition, the traffic flow forecast under the influence of the epidemic is also discussed. Through a comprehensive comparison of multiple indicators, the results show that the SARIMA-NAR combined model 1 has better road traffic flow fitting and prediction effects and is suitable for the greater volatility of traffic flow during the epidemic. This model improves the effectiveness and reliability of traffic flow forecasting, and the forecasting process is more convenient and efficient.

The implementation of railway intelligent construction is the need of national strategic development and the demand of society. Based on the idea of system engineering, this paper proposes a three-dimensional railway intelligent construction system architecture composed of a full life cycle, management level and technical support. Based on this architecture, a “three-step” implementation path is proposed. Then, it analyzes the technology support framework required in the architecture based on Building Information Modeling (BIM), incorporating Global Positioning System (GPS) and Geographic Information System (GIS), algorithmic prediction and machine learning technology, Internet of Things (IoT) and artificial intelligence technology, big data and cloud computing technology, and the application of railway intelligent construction system architecture is analyzed by taking a railway tunnel project in Zhejiang Province of China as an example. Finally, it discusses the problems that may be encountered in the implementation of railway intelligent construction and puts forward relevant suggestions. The results show that railway intelligent construction is an essential way. At present, China’s railway intelligent construction is still in the primary stage. The design organization should do a good job in the top-level design and accumulate sufficient data for the later stage. All parties in the middle stage of construction should do a good job in the induction and integration of information and accumulate sufficient experience. In this way, we can integrate into the advanced stage and give full play to the advantages of software and hardware integrated applications such as BIM, IoT, big data, cloud computing and intelligent devices so as to truly realize the intellectualization and modernization of railway construction.