For a long time, the accurate prediction of passenger flow can provide early warning information for various industries such as the public service industry, tourism industry, and industrial business, thus opportunely arranging passengers and providing homologous services to relieve the overloading of places and the accidents caused by overcrowding of people. In recent years, by using the wireless sensor network to sense the passenger data in advance, the technique of machine learning and neural networks has been utilized to assist the short‐term passenger flow prediction. In this study, building on convolutional neural network (CNN) and long short‐term memory network (LSTM), a complete ensemble empirical mode decomposition with adaptive noise algorithm (CEEMDAN) and attention‐based CNN‐LSTM network to extract both temporal and spatial characteristics of passenger flow data, is proposed. Moreover, the problem of the inaccuracy of the noise part is properly solved by adding the CEEMDAN algorithm to the input layer. With the proposed network structure, the CNN‐LSTM network is replaced with the Conv‐LSTM network to reduce the information loss and get a further performance improvement. The result shows that 39% performance improvement can be achieved than the case with a single LSTM network, and 28% performance improvement can be achieved than the CNN‐LSTM network.

No abstract

Water/mud inrush is a serious threat to the safety of tunnel construction. It is very important to set up a certain thickness of aquifuge to prevent water/mud inrush and eliminate the catastrophe causing object when there exists potential risk of water inrush in front of the tunnel face. Taking the water inrush accident of No.1 ventilation inclined shaft at K21+693 in Yingpanshan Tunnel as an example, the cause of water inrush is analysed from angle of the geological and hydrological conditions. Then, a minimum aquifuge thickness of the tunnel face valuing 8.6m is obtained based on the thin elastic plate theory model. In order to explore the mechanism of water/mud inrush near the water-bearing fault, the numerical models of the aquifuge with a thickness of 10m/5m/1m were established based on the material point method. The results show that it is reasonable to take 10m as the construction safety thickness, and the water/mud inrush mechanism varies with the aquifuge thickness. The overall extrusion failure occurs when the aquifuge is thicker, and the middle fracture failure occurs when the thickness is thinner. The material point method has advantages in studying large deformation problems including water/mud inrush. The results provide references for strengthening aquifer, eliminating catastrophe causing object and ensuring construction safety.