Due to the lack of living space and the increase in population, there has been a construction boom in the underground space to improve the quality of human life. Tunnel engineering plays a vital role in the development of underground space. In addition to traditional methods, some intelligent methods such as artificial neural networks (ANNs) have been applied to various problems in the tunnel domain in recent years. This paper systematically reviews the application of ANNs from different aspects of tunnel engineering. It reveals that the backpropagation algorithm (BPA) and Levenberg-Marquardt algorithm (LMA) are the most widely used. Due to the limitations of some original models, some scholars use optimization algorithms such as particle swarm optimization (PSO) and genetic algorithm (GA) to optimize the original ANNs to obtain better prediction results. A comparison between the ANN-based methods and methods like statistical methods is conducted. Finally, the following conclusions can be drawn: (1) The recommended ratio of the training set and test set is 3:1; (2) The advantage of optimized ANNs is not apparent when the optimization algorithm varies. Additionally, the performance of ANNs is always better than that of statistical methods.

In order to research the theory for the variety of transverse forces of the adjacent shield tunnels caused by foundation pits excavation, the effect mechanism of foundation pit excavation on the adjacent shield tunnel was analyzed. The sidewall unloading model of the foundation pit, considering the deformation of the retaining structures, was introduced to calculate the additional stress of soil caused by foundation pit excavation. On this basis, the additional confining pressure variation model of the adjacent shield tunnel was established, considering the influence of the longitudinal deformation. Take the deep foundation pit project by the side of the shield tunnel of Hangzhou Metro Line 2 as a case study, the variation in confining pressure distribution of the adjacent shield tunnel caused by foundation pit excavation was analyzed, and a simplified finite element model was established to calculate the internal force of the segment ring structure. Moreover, the influence factors were analyzed, such as the deformation of the foundation pit retaining structure, the clearance between the foundation pit and the adjacent tunnel, and the buried depth of the tunnel. The present study suggests that the foundation pit excavation reduces the confining pressure of the adjacent shield tunnel, increases the absolute value of bending moment and shear force, and decreases the axial force at the top and bottom of the tunnel’s segment ring. With the increase in the deformation of the foundation pit’s retaining structure, the absolute value of the additional confining pressure on the adjacent tunnel increases, and the response of the bending moment to the foundation pit excavation unloading is more obvious than the variation in the confining pressure. When the buried depth of the adjacent shield tunnel is deeper than the excavation depth of the foundation pit, the influence of the excavation on the tunnel will be obviously weakened. With the decrease in the distance between the pit and tunnel, the influence of the excavation on the tunnel will be enhanced.

The use of artificial freezing can change the mechanical properties of marine clay. In the construction of cross passages in metro tunnels in which the artificial ground freezing (AGF) method is applied, freeze–thaw circulation and cyclic loading could weaken the engineering properties of the clay, thus resulting in differential settlement. In this paper, the authors studied the dynamic properties of frozen–thawed soils under cyclic loading, with the help of dynamic triaxial testing. According to the dynamic triaxial test results and the images from scanning electron microscopy (SEM), the authors explained the weakening effect of both the freeze–thaw cycle and dynamic loading on soft soil. After freezing, the number of large pores increased. In addition, after cyclic loading, the pore structure of the soil showed a tendency towards compaction, which led to the large pores breaking into small ones. Subsequently, the potential reasons for the change of macroscopic dynamic characteristics were explained from a micro-scale point of view.

The vertical tunneling method is an emerging technique to build sewage inlets or outlets in constructed horizontal tunnels. The jacking force used to drive the standpipes upward is an essential factor during the construction process. This study aims to predict the jacking forces during the vertical tunneling construction process through two intelligence systems, namely, artificial neural networks (ANNs) and hybrid genetic algorithm optimized ANNs (GA-ANNs). In this paper, the Beihai hydraulic tunnel constructed by the vertical tunneling method in China is introduced, and the direct shear tests have been conducted. A database composed of 546 datasets with ten inputs and one output was prepared. The effective parameters are classified into three categories, including tunnel geometry factors, the geological factor, and jacking operation factors. These factors are considered as input parameters. The tunnel geometry factors include the jacking distance, the thickness of overlaying soil, and the height of overlaying water; the geological factor refers to the geological conditions; and the jacking operation factors consist of the dead weight of standpipes, effective overburden soil pressure, effective lateral soil pressure, average jacking speed, construction hours, and soil weakening measure. The output parameter, on the other hand, refers to the jacking force. Performance indices, including the coefficient of determination (R²), root mean square error (RMSE), and the absolute value of relative error (RE), are computed to compare the performance of the ANN models and the GA-ANN models. Comparison results show that the GA-ANN models perform better than the ANN model, especially on the RMSE values. Finally, parametric sensitivity analysis between the input parameters and output parameter is conducted, reaching the result that the height of overlaying water, the average jacking speed, and the geological condition are the most effective input parameters on the jacking force in this study.

This paper is based on the case of the earth pressure balance (EPB) shield tunnelling project of the new Metro Line 2 undercrossing the existing Metro Line 1 in the soft soil urban area of Hangzhou. Because the EPB shield must break through a plain concrete wall before undercrossing the existing tunnels, the pipe roof prereinforcement was adopted to stabilize the soil between the existing tunnels and the new shield tunnel. The deformation characteristics of the existing tunnels in the process of double shield undercrossing were discussed. According to the variation of shield position, the settlement development could be divided into three stages: shield approaching subsidence, shield crossing heave, and shield leaving subsidence. The horizontal displacement shows a back and forth variation characteristic consistent with the direction of shield tunnelling. At the junction of tunnel and station, the shield undercrossing caused considerable differential settlement between the existing tunnel and the station. The construction of pipe roof prereinforcement will lead to the presettlement of the existing tunnels. The settlement of the existing tunnels caused by the attitude deviation of pipe roof and grouting disturbance should be reduced in reasonable ranges. In addition, the maximum longitudinal settlement of the existing tunnel during the shield second undercrossing was also discussed. It was considered that the influence of wall breaking is greater than the sequence of shield undercrossing. The driving parameters of shield tunnelling should be optimized before the second crossing.

The jacking force is one of the important parameters affecting the construction process in the vertical tunnelling method. To study the dynamic changing process of jacking force with the jacked distance and the influencing factors of the maximum jacking force, both the indoor model test and numerical simulation were conducted. In the model test, we investigated the influence of the height of the soil and water content. The results indicated that the higher the overburden height was, the greater the jacking force. Moreover, the water content enhanced the compressibility of the soil and had little effect on the maximum jacking force. Additionally, the coupled Eulerian–Lagrangian (CEL) approach was used to simulate the vertical jacking construction. In the numerical simulation, we investigated two construction factors (jacking speed and the standpipe outer diameter) and four soil parameters (cohesion, internal friction angle, elastic modulus, and Poisson’s ratio). Before that, the CEL simulation results were compared with test data to prove the rationality of the CEL approach, and the two were in good agreement. The results showed that among the six influence parameters, according to the influence degree on the maximum jacking force from large to low, the outer diameter of the standpipe, internal friction angle, cohesion, elastic modulus, jacking speed, and Poisson’s ratio were ranked. In addition, the jacking speed of numerical analysis was suggested to be 0.2 m/s. The research results in this paper can provide a reference for the construction of the vertical tunnelling method.