Accurate prediction of ground surface settlement (GSS) adjacent to an excavation is important to prevent potential damage to the surrounding environment. Previous studies have extensively delved into this topic but all under the limitations of either imprecise theories or insufficient data. In the present study, we proposed a physics-constrained neural network (PhyNN) for predicting excavation-induced GSS to fully integrate the theory of elasticity with observations and make full use of the strong fitting ability of neural networks (NNs). This model incorporates an analytical solution as an additional regularization term in the loss function to guide the training of NN. Moreover, we introduced three trainable parameters into the analytical solution so that it can be adaptively modified during the training process. The performance of the proposed PhyNN model is verified using data from a case study project. Results show that our PhyNN model achieves higher prediction accuracy, better generalization ability, and robustness than the purely data-driven NN model when confronted with data containing noise and outliers. Remarkably, by incorporating physical constraints, the admissible solution space of PhyNN is significantly narrowed, leading to a substantial reduction in the need for the amount of training data. The proposed PhyNN can be utilized as a general framework for integrating physical constraints into data-driven machine-learning models. (c) 2025 Institute of Rock and Soil Mechanics, Chinese Academy of Sciences. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/ 4.0/).

This study presents a series of centrifuge model tests that were conducted to investigate the grouting mechanism and its effect during rectangular pipe jacking in soft soil. A new jacking grouting device was developed to simulate the entire grouting process in the centrifuge model tests. The influence of grouting on the friction at the lining-soil interface and vertical displacement of the tunnel lining was analysed. In addition, the impact of the grouting slurry's viscosity and fluid loss on ground surface settlement and the friction at the pipe-soil interface was also examined. The results indicate that grouting plays a significant role in mitigating the friction and vertical displacement of the tunnel lining caused by excavation. Furthermore, the study shows that reducing the viscosity of the grouting slurry can reduce the friction coefficient at the pipe-soil interface, thus facilitating the advancement of pipe jacking. The use of a low fluid loss grouting slurry is also recommended to improve control over ground surface settlement. These findings are crucial for enhancing the efficiency and safety of rectangular pipe jacking in soft soil.

Ground surface settlement is the most significant restriction when constructing shallow metro station tunnels in urban areas. The umbrella arch method (UAM) is generally applied as a tunnel support method. However, UAM becomes inadequate in some soil conditions, such as loose sand or soft clay. Innovative support systems are required to safely build shallow metro station tunnels in urban areas. The objective of this research is to investigate alternative tunnel support systems and appropriate soil models to safely construct shallow twin-tube metro station tunnels. The continuous pipe arch system (CPAS), which consists of horizontal and continuous pipes along the metro station tunnels, was modeled in three dimensions (3D) using the finite element (FE) program Plaxis3D for various pipe diameters. The ground surface settlement results of the 3D models were compared with the in situ settlement measurements to validate the geotechnical parameters of the soils used in the models. It was observed that the hardening soil (HS) model was more accurate than the Mohr-Coulomb (MC) soil model. As a result of the 3D FE model analysis, maximum ground surface settlements were obtained below 50 mm when the pipe diameters of CPAS were larger than an internal diameter (ID) of 1200 mm at a cover depth of 10 m in sandy clay soil. It is revealed that CPAS with pipe diameters between ID 1200 mm and ID 2000 mm can be utilized as a tunnel support system in urban areas to construct shallow twin-tube metro station tunnels with low damage risk.

Though a comprehensive in situ measurement project, the performance of a deep pit-in-pit excavation constructed by the top-down method in seasonal frozen soil area in Shenyang was extensively examined. The measured excavation responses included the displacement of capping beam and retaining pile, settlement of ground surface, and deformation of metro lines. Based on the analyses of field data, some major findings were obtained: 1) the deformations of retaining structures fluctuated along with the increase of temperature, 2) the deformation variation of retaining structures after the occurrence of thawing of seasonal frozen soil was greater than that in winter, although the excavation depth was smaller than before, 3) the influence area of ground settlement was much smaller because of the features of seasonal frozen sandy soil, 4) the displacement of metro line showed a significant spatial effect, and the tunnel lining had an obviously hogging displacement pattern, and 5) earth pressure redistribution occurred due to the combined effects of freezing-thawing of seasonal frozen soil and excavation, leading to the deformation of metro line. The influence area of ground settlement was obviously smaller than that of Shanghai soft clay or other cases reported in literatures because of special geological conditions of Shenyang. However, the deformation of metro lines was significantly lager after the thawing of the frozen soil, the stress in deep soil was redistributed, and the metro lines were forced to deform to meet a new state of equilibrium.

Excavation with Tunnel Boring Machine (TBM) in urban environments can have risks, such as ground surface settlement. The empty space between the cutterhead and the segment should be filled with suitable grout during the excavation. Nowadays, using grout behind the segment and other fillers fill the empty space behind the segment and reduce the amount of ground surface settlement. Undoubtedly, using a grout with appropriate mechanical behavior can be a suitable substitute for excavated soil in mechanized tunneling. In this research, the mechanical behavior of the grout behind the segment during injection into the space between the soil and the segment and its mixture with the soil is studied. Also, the effect of mechanical properties of grout mixed with soil on the ground surface settlement is investigated using numerical modeling. The components of twocomponent grout of this study comprises Sufian type 2 cement with 28-day strength of 44 MPa and density of 3050 kg/m3, Salafchegan bentonite with density of 2132 kg/m3 and precipitator of liquid sodium silicate with density of the solution 1500 kg/m3. The results of the laboratory studies indicated that mixing the grout and soil increases the mechanical properties of grout significantly. Increasing the soil in the mixture of soil and grout up to 40% increases the uniaxial compressive strength up to 300%, the elasticity of modulus up to 156% and the cohesion of the mixture up to 100%. On the other hand, based on the results of numerical modeling, the proper injection pressure can significantly reduce the ground surface settlement. Increasing the injection pressure from 0 to 120 kPa has a 17% influence on the reduction of ground surface settlement.