Tunnel Depth Research Articles

Study on Soil Vibration Propagation Characteristics Caused by Subway near Foundation Pit

Abstract Based on the Shanghai Metro Line 12, a three-dimensional finite element calculation model is established to study the influence of adjacent foundation pits on subway train vibration propagation. A comparative analysis is conducted on the vibration response and propagation characteristics of the subway during single and bidirectional metro operation under free field and adjacent foundation pit conditions. The effects of subway train speed and tunnel depth on vibration propagation are discussed in detail. It is indicated that as the train speed increases, the ground vibration increases, and the increasing trend of vertical acceleration gradually slows down. The deeper the tunnel is buried, the smaller the ground vibration response. The variation of tunnel burial depth has no effect on the attenuation law of vertical vibration.

Modifiable and non-modifiable risk factors affecting surgical failure after revision ACL reconstruction: a cohort study

BackgroundResearch on factors influencing the outcomes of revision anterior cruciate ligament (ACL) reconstruction is relatively scarce and mostly relies even on reports from a single group. Understanding the factors contributing to the failure of revision ACL reconstruction can provide valuable information for achieving better clinical outcomes and assist in patient counseling before surgery. Therefore, this study aimed to analyze the factors contributing to surgical failure after revision ACL reconstruction.MethodsThe medical records of consecutive patients who underwent single-bundle revision ACL reconstruction using the transportal technique between 2010 and 2020 and had a minimum follow-up of 2 years were retrospectively reviewed. Eligible patients were classified into two groups on the basis of the presence of surgical failure during the follow-up period (group NF, patients who did not experience surgical failure; group F, patients who experienced surgical failure). In this study, surgical failure after revision ACL reconstruction was defined as meeting any of the following conditions during follow-up: the presence of graft re-tear confirmed by magnetic resonance imaging (MRI), anterior–posterior laxity graded ≥ 2, or rotational laxity graded ≥ 2. A comparative analysis was conducted on demographic data, as well as peri-, intra-, and postoperative data between the groups. Additionally, a regression analysis was performed to investigate factors influencing surgical failure after revision ACL reconstruction.ResultsA total of 58 patients were included (group NF, 40 patients; group F, 18 patients). In between-group comparisons of demographic, peri-, and intra-operative data, group F exhibited a higher frequency of multiple revision surgeries (P = 0.001), increased preoperative osteoarthritis grade (P = 0.001), and shallower femoral tunnel depth (P = 0.002) compared with group NF. At the final follow-up, group F demonstrated relatively poor clinical outcomes, both subjectively and objectively. Multivariate regression analysis revealed that all variables that showed differences in the preceding comparisons were independent factors affecting surgical failure after revision ACL reconstruction.ConclusionsSurgical failure after revision ACL reconstruction can occur in a substantial number of patients, influenced by non-modifiable factors, such as cases corresponding to multiple revision surgery and preoperative osteoarthritis grade, and modifiable factors, such as femoral tunnel depth.

Numerical Investigation with Failure Characteristic Analysis and Support Effect Evaluation of Deep-Turning Roadways

In recent years, tunnel-boring machines (TBMs) have been widely applied in deep coal mining. Turning is an inevitable challenge in TBM tunneling, and a TBM turning roadway exhibits greater instability than a straight roadway, as engineering experience has indicated. This study aimed to explore the failure mechanism and evaluate the support performance of a deep-turning roadway. Several numerical models were established to investigate the deformation of the roadway, the stress distribution, and the failure zone of the surrounding rocks under different tunneling conditions. The results show that the tunneling depth influences the failure pattern of the turning roadway: deep tunneling with high in situ stress can cause asymmetric failure of the turning roadway, while shallow tunneling with low in situ stress does not. Moreover, the change in turning radius, namely the change in roadway geometry, does not influence the stability of the turning roadway. In addition, the support actions for both the straight and turning roadways do not differ significantly, and the amount of controlled deformation of the surrounding rocks is proportional to their natural deformation.

Application of Ground Penetrating Radar in Rapid and Non destructive Detection of Urban Tunnels

Abstract Due to the rapid advancement of modern transportation, tunnels have emerged as an important component of transportation infrastructure. A large number of pipelines and tunnels makes the urban underground environment extremely complex. Detecting underground tunnels and pipelines can provide guidance for urban construction. Ground penetrating radar (GPR) possesses attributes such as swift detection speed, no loss, convenient and flexible operation, thereby playing a crucial role in numerous domains. The aim of this research is to verify the feasibility of detecting tunnels with depths on the order of 10 meters, by evaluating tunnel dimensions and depth parameters through a combined approach of simulation and experimental measurements. In this investigation, gprMax was utilized to model and simulate the underground tunnel to establish the correlation between echo data and target position. Additionally, this research employed an 80MHz GPR system to detecting a undergound tunnel and acquiring data which facilitated successful determination of the depth of the underground tunnel based on empirical evidence

Numerical analysis of relative density effects on shallow TBM tunnel excavation: Ground behavior and principal strains at surface in greenfield conditions

Tunnel construction in urban areas may result in ground deformations that pose a risk to existing buildings and infrastructure; thus, accurate prediction of these induced ground deformations during the design phase is crucial. The paper focuses on the effects of sandy soil relative density on the ground deformations induced by tunnels excavated with Tunnel Boring Machines (TBMs). The study utilizes the Finite Element Method (FEM) and the NorSand model to simulate the behavior of a sandy ground. The validity of the FEM modeling approach is established by comparing predictions with results from six centrifuge tunnel tests from the literature. The centrifuge tests were performed on sand at different relative densities, tunnel diameters, and tunnel depths. The parameters for the NorSand model were determined based on laboratory tests. Only the state parameter was modified to achieve the desired relative density in the numerical simulations. The effects of relative density observed in centrifuge tests (Franza et al., 2019) have been numerically reproduced with no further adjustments of the model parameters. The rich outputs from the numerical models enabled an in-depth investigation of tunnel behavior, yielding new insights into how tunnels respond under varying relative densities, depths, and diameters. A comprehensive analysis of the induced ground deformations caused by shallow tunnels in sandy ground and the potential to damage buildings is included.

Numerical Simulation of a Shed-Tunnel Structure’s Dynamic Response to Repeated Rockfall Impacts Using the Finite Element–Smoothed Particle Hydrodynamics Method

In practical engineering, a shed-tunnel structure often encounters repeated impacts from rockfall during its whole service life; therefore, this research focuses on exploring the dynamic response characteristics of shed-tunnel structures under repeated impacts from rockfall with a numerical method. First of all, based on a model test of a shed tunnel under rockfall impacts as a reference, an FEM (finite element method)-SPH (Smoothed Particle Hydrodynamics) coupled numerical calculation model is established based on the ANSYS/LS-DYNA finite element code. Numerical simulation of the dynamic response of the shed-tunnel structure under rockfall impacts is realized, and the rationality of the model is verified. Then, with this model and the full restart technology of the LS-DYNA code, the effects of four factors, e.g., rockfall mass, rockfall impact velocity, rockfall impact angle and rockfall shape, on the impact force and impact depth of the buffer layer, the maximum plastic strain and axial force of the rebar, the shed roof’s vertical displacement and plastic strain of the shed tunnel are studied. The results show that the impact force, impact depth, roof displacement and plastic strain of the shed tunnel are positively correlated with the rockfall mass, velocity and angle under multiple rockfall impacts. The impact force, roof displacement and plastic strain of the shed-tunnel structure generated by the impact of rockfall consisting of cuboids are all greater than those under spherical rockfall, and the impact depth generated by the impact of spherical rockfall is greater than that of rockfall consisting of cuboids. For rockfall consisting of cuboids, the impact depth, roof displacement and plastic strain are negatively correlated with the contact area. Under repeated rockfall impacts, the peak impact force usually increases first and then tends to be stable.

A novel FDEM-GSA method with applications in deformation and damage analysis of surrounding rock in deep-buried tunnels

In underground hydraulic tunnel engineering, particularly deep-buried projects, the deformations and stability of the surrounding rock are critical to the construction process. Due to the complex depositional environment of such tunnels, multiple factors influence the stability of the surrounding rock during construction. This paper proposes a novel hybrid method combining Finite-Discrete Element Method (FDEM) with Global Sensitivity Analysis (GSA) and machine learning. The FDEM model is used to establish an approximate relationship between input and output parameters, and its accuracy is validated through comparison with monitoring data. On the basis of data simulated by the FDEM model, a meta-model is developed by Particle Swarm Optimization-Extreme Gradient Boosting (PSO-XGBoost). 10,000 data sets are generated using the meta-model for Sobol sensitivity analysis. The proposed analysis framework is applied to study the deep-buried water diversion tunnel in the Central Yunnan Water Diversion Project (CYWDP). The results indicate that in deep-buried tunnel environments, as the tunnel depth increases, the dominant factor influencing the deformation of the surrounding rock transitions from tunnel depth to the mechanical properties of the rock itself. These findings provide valuable insights for optimizing construction plans in similar tunnel projects and offer a new perspective on sensitivity analysis frameworks based on numerical computations.

Effect of burial depth of a new tunnel on the seismic response of an existing tunnel

Effect of burial depth of a new tunnel on the seismic response of an existing tunnel

Analytical solution of overlying pressure for shallowly buried underwater box tunnel: A case study of box jacking in Suzhou, China

Accurately predicting the overlying pressure is crucial for determining an appropriate cover depth of underwater box tunnels to avoid the uplifting failure. Based on the project of box jacking crossing the Beijing-Hangzhou Grand Canal in Suzhou, the characteristics of overlying pressure variation during tunneling are investigated. The monitoring results reveal that the fluctuation of overlying pressure is weakened during the rapid tunneling process. A modified analytical model for vertical earth pressure is conceived, in which the active and passive limit states for multi-layered soils are both considered. The probable range of overlying pressure obtained by the proposed model is suitable to cover the actual values. The anti-floating behavior of underwater box tunnels for two different working conditions is discussed by calculating the minimum cover depth. Using the calibrated analytical models, a parametric study is conducted to explore the influence of injection pressure, hardened slurry unit weight, soil internal friction angle, soil cohesion, and tunnel geometry. It is found that the injection pressure during the construction process is crucial for determining the necessary cover depth, and the change of box tunnel height makes it easier to trigger the variation of minimum cover depth.

Transverse seismic analysis method of underground interchange prefabricated utility tunnel

The rapid development of underground utility tunnels has led to the formation of a large number of interchange utility tunnels. Due to significant differences in the lateral resisting stiffness in orthogonal directions, coupled with the close relationship between soil deformation and the depth of the utility tunnel, the seismic response mechanism of the interchange utility tunnel is complex. This paper proposes a method for transverse seismic analysis of the underground interchange utility tunnel based on the response displacement method. A load-structure analysis model of a certain underground cross-type interchange utility tunnel is first established. Then, the different conditions corresponding to maximum relative deformation between layers of the interchange node are discussed, and the proposed method is validated via the time-history analysis method. Based on the proposed analysis method in this paper, seismic response analysis is performed on the interchange utility tunnel considering the condition of vertical incidence of three different input seismic waves. Discussions are conducted in terms of internal forces, inter-story displacement angles, and damage responses under seismic excitations in different principal axis directions. The results show that under major earthquakes, the maximum inter-story displacement angle of the interchange node exceeds the standard limit by up to approximately 184 %, while the tensile damage can reach up to 0.985, significantly surpassing the tensile damage limit. Accordingly, the interchange node is the weakest part of the interchange utility tunnel. There exists deformation inconsistency between the interchange node and standard segments due to significant stiffness differences, with the influence range of the interchange node on internal forces, inter-story displacement angles, joint deformations and damage of the utility tunnel is approximately 7, 6, 8, and 6 prefabricated standard segments, respectively. Since the maximum relative deformation between layers of the interchange node does not occur simultaneously, for double-layered and multi-layered interchange utility tunnels, it is necessary to comprehensively consider the maximum inter-story displacement angle between each layer to determine their most unfavorable condition. The analytical method and related research conclusions presented in this paper can provide references for the transverse seismic design of interchange utility tunnels.

Mathematical modelling for strata deformation caused by rectangular pipe jacking construction in composite layered ground

In this study, analytical solutions of vertical deformation of ground surface and horizontal displacement of strata are derived combining the Mindlin solution and the mirror method due to rectangular pipe jacking tunneling in composite strata, which considers the combined effect of five factors of additional excavation pressure, friction of rectangular pipe jacking and soils, segment-soil friction, grouting filling and strata loss, respectively. The theoretical calculation results were verified against the measured data in two project cases. Moreover, effect factors of rectangular jacking pipe cross-sectional dimensions, embedment of tunnel axial depth, elasticity modulus on the interlayer and the Poisson's ratio of the interlayer on strata deformation is investigated. The results imply that the theoretical calculation values obtained using this method are more closely correlated with the observed values compared to those computed using the single stratum model. The primary cause of terrene upheaval in front of the working surface is the increased excavation pressure on the working face and the horizontal displacement of the deep soils and the surface subsidence behind the excavation face is resulting from the soil loss as the main influencing factor. The varying cross-section size of pipe jacking is able to impact on the vertical deformation of the soil, but it has a limited impact on the lateral displacement of the strata. The affection of the buried depth of the tunnel axis on strata deformation is more notable in the rectangular pipe jacking construction. As the axial tunnel depth growth, the ground surface maximum subsidence value gradually decreases, while the crest value of horizontal distortion mildly increases. When the rise of the interlayered modulus of elasticity, the maximum earth surface subsidence enlarged gradually while the subsidence trough slight diminution. Moreover, the greatest horizontal displacement exhibits a relatively minor fluctuation, but there is a trend of upward movement in the position. The influence of Poisson's ratio of the interlayer on the strata deformation is comparatively weak.

Numerical analysis of seismic response of a circular tunnel-rectangular underpass system in liquefiable soil

Earthquake-induced liquefaction can lead to uplift displacements of underground structures. While the behaviour of a single underground structure has been extensively studied, the coupled response of a shallow buried circular tunnel adjacent to an underpass with a rectangular section in liquefiable ground remains unclear. In this study, the finite difference method based on the fully coupled effective stress is employed to analyse the seismic response of two adjacent underground structures. Firstly, comprehensive parameters of Hostun sand for P2Psand constitutive model was calibrated. The accuracy of the numerical method is verified through a centrifuge test. Subsequently, comparisons are made between the seismic response of the tunnel-soil-underpass interaction and other cases: free field, tunnel, and underpass. The tunnel-soil-underpass interaction in liquefiable ground is analysed, with a special emphasis on the development of excess pore pressure, acceleration response of the soil, displacement and deformation of the structures. A section deformation coefficient was proposed to depict the tunnel deformation. Finally, horizontal spacing, buried depth of tunnel and underpass are discussed to clarify the interaction of two structures. The optimal relative position of two structures is suggested, providing valuable insights for the spatial design of underground structures in liquefiable ground.

Study on Deformation of New Tunnels Overcrossing Existing Tunnels Underneath Operating Railways

With the increasing utilization of urban underground space, new tunnels frequently intersect with existing tunnels and operational railways. However, sometimes the excavation and unloading of new tunnels can cause deformation of adjacent existing tunnels and railways, significantly affecting their normal operation. We used finite element software to predict the influence of new tunnel construction on overcrossing existing tunnels and down-traversing operational railways by a dynamic tunneling model based on a connection channel project of the east and west squares of a railway station. This article is not only control the distance between the two tunnels, but the new tunnel and the existing tunnel, as well as the new tunnel and the operation of the railway, the positional relationship between the three, the deformation laws of existing tunnels and operational railways during the construction of new tunnels with different buried depths are analyzed. The results show that the deformation curves of existing tunnels and operational railways present a normal distribution. The maximum deformation position is at the intersection with the new tunnel upon completion of the new tunnel excavation construction. Moreover, an increase in the buried depth of the new tunnel increases the deformation of the operational railway and the existing tunnel. The influence of the depth change of the new tunnel on the settlement of the operational railway is greater than that of the existing tunnel.

The Behavior of the Tunnel Reinforced with Geogrid in Soft Soil Under the Effect of Axial Load

The soft soil's poor tensile strength requires reinforcing to increase bearing capacity, improve stability, and reduce settlements. This study assessed the efficacy of using geogrid layers to enhance and secure the soil surrounding tunnels. enabling the tunnel to endure pressure, particularly during excavation. The utilization of geogrids in soil reinforcement has experienced a substantial rise as a result of their consistent dimensions and exceptional tensile strength. To quantify the exerted force transferred to the tunnel, during this study utilized various testing tools, including a soil container, a steel loading frame, data loggers, a 0.5-ton load cell, and a miniature pressure cell. The vertical loads are applied by utilizing a hydraulic jack. A series of eleven tests were conducted on the tunnel at two depths of 1.5D and 2.5D, where D is the tunnel's diameter. The different models of geogrid layers showed that using two layers of geogrid at the first dimension, 0.5B and 1B from the base, led to a significant increase in tunnel stability. Two layers of reinforcement were used in both directions, giving the soil a high bearing capacity for the loads applied to the tunnel. This resulted in an improvement, a 1.65 in 1.5D and a 1.82 in 2.5D. The pressure above the pipe decreased by approximately 7.1kPa at the first tunnel depth and about 3.5kpa at the second depth. In conclusion, the study found the geogrid improves the stability of the tunnel by equally distributing loads and minimizing stress concentrations, hence decreasing the chances of collapses or deformations. Doi: 10.28991/CEJ-2024-010-08-04 Full Text: PDF

Anatomic femoral tunnel and satisfactory clinical outcomes achieved with the modified transtibial technique in anterior cruciate ligament reconstruction: A systematic review and meta-analysis

BackgroundAnatomic anterior cruciate ligament (ACL) reconstruction is considered the gold standard treatment for ACL injuries because it aims to restore the knee's normal anatomy and stability, while also protecting long-term knee health. Long-term clinical and radiological outcomes after ACL reconstruction using the modified TT technique are unclear. ObjectiveTo assess the clinical and radiological outcomes following ACL reconstruction using modified transtibial (TT) techniques at a minimum 12-month follow-up. DesignA systematic review with meta-analysis. MethodsPubMed, EMBASE, Web of Science, the Cochrane Library, and MEDLINE databases were searched from the inception to December 1, 2022. PICO search strategy was used to identify studies applying modified TT techniques on patients with ACL reconstruction and a minimum follow-up of 12 months. Eligible studies were identified independently by two reviewers. We extracted data on patient demographics, surgical characteristics, patient reported outcomes including subjective evaluations and clinical outcomes. Radiological data including femoral and tibial tunnel position, femoral and tibial tunnel length, and femoral tunnel angle were also extracted. The tunnel position was evaluated using the quadrant method based on three-dimensional computed tomography (3D CT) images. The standardized mean difference (SMD) and 95 % confidence interval (CI) were calculated for clinical and radiological outcomes. ResultsSixteen studies involving 628 patients were finally included. The SMD of Lysholm (90.39; 95 % CI 83.41–97.38), IKDC (86.07; 95 % CI 79.84–92.31), and Tegner (6.15; 95 % CI 3.96–8.33) scores were considered satisfactory. The depth of the femoral tunnel showed a pooled SMD of 30.08 % (95 % CI 28.25–31.91 %), and the height showed a pooled SMD of 37.72 % (95 % CI 35.75–39.70 %). The pooled SMD for the femoral tunnel angle in the coronal plane was 48.27°(95 % CI 43.14–53.40°), and the pooled SMD for the femoral tunnel length was 33.98 mm (95 % CI 29.03–38.93 mm). ConclusionsThis investigation has shown that modified TT technique can create an anatomic femoral tunnel and maintain optimal tunnel length and angulation. Most patients had satisfactory subjective outcomes and physical examinations after ACL reconstruction using modified TT technique. This information may assist in guiding expectations of clinicians and patients following ACL reconstruction with modified TT technique.

Mechanism of slag discharge failures in earth pressure balance shield screw conveyor: A theoretical model-based investigation

The screw conveyor gushing may cause a sudden drop in pressure in the earth chamber, leading to excessive settlement of the surface and nearby buildings or structures, and even catastrophic accidents such as tunnel collapse. This paper presents a comprehensive investigation into slagging failures associated with earth pressure balance shield screw conveyors, categorizing them into rheological failure and permeability failure. Further, a permeability failure theoretical model and a Bingham fluid-based rheological failure model are developed. The above models can describe the conditions and mechanism of screw conveyor spurt taking into account shield parameters, formation characteristics, chamber pressure, and conditioned soil properties. In addition, a sensitivity analysis is conducted on the critical permeability coefficient and critical shear strength of the discharged soil, with a focus on a specific case project. The results underscore the significant impact of the screw conveyor pitch, water head at the entrance, and chamber pressure on the critical permeability coefficient and shear strength. Building on these findings, this paper proposes an anti-surge control index and strategy for shield screw conveyors, taking into account the ratio of shield covering soil thickness to shield diameter. It is recommended that when the shield soil covering layer thickness exceeds twice the shield diameter, real-time modification of the soil parameters, based on the shield tunneling depth, especially the shear strength, is essential for anti-surge control. This study provides engineers with valuable insights into conditioned soil and implements effective surge management strategies for screw conveyors.

Investigation on the failure mechanism for surrounding rock in small interval tunnels using finite element limit analysis method

This paper presents a case study to evaluate the failure mechanism of surrounding rock in mountain tunnels caused by small interval parallelism and the reinforcement effect of intermediate rock columns. The characteristics and reasons of surrounding rock collapse were analyzed through field investigation, taking Yaoxi Tunnel as a case study. The critical collapse and blowout pressure results obtained by the finite element difference method (FEDM) software FLAC and the finite element limit analysis method (FELAM) software OPTUM were compared based on Mollon’s theoretical solution. The critical support pressure errors for collapse are 18.803% and 8.129%, indicating that OPTUM has a slight advantage in accuracy for solving tunnel collapse. Therefore, the models of small interval tunnels were established by OPTUM to investigate the collapse failure mechanism and progressive failure process of surrounding rock. The effects of tunnel depth ratio (H/D), spacing ratio (S/D), and surrounding rock parameters (γ, φ, c) on critical support pressure, failure mode, and surrounding rock settlement laws were studied through simulation models. It shows that the gradual decrease in mechanical parameters of rock is the main cause of the increase in critical support pressure. The design parameters (H/D, S/D) have a mutagenic effect on the pressure arch of the double tunnel surrounding rock. As the distance between the two holes increases, the joint pressure point in the intermediate rock column gradually rises. Finally, the effectiveness of the reinforcement measures for the intermediate rock column was verified through on-site monitoring. The research results of this study have reference price for similar projects.

A Study on the Maximum Scour Depth of River-Crossing Tunnels

A Study on the Maximum Scour Depth of River-Crossing Tunnels

Analysis of Shield Tunneling Parameters and Research on Prediction Model of Tunneling Excavation Speed in Volcanic Ash Strata of Jakarta–Bandung High-Speed Railway Project

Insufficient investigations have been conducted on the analysis of shield tunneling parameters and the prediction of the tunneling excavation speed in formations composed of volcanic ash strata. To address this issue, we employ a comprehensive approach utilizing literature research, mathematical statistics, and other methodologies, centered on the analysis of the No. 1 Tunnel of the Jakarta–Bandung High-Speed Railway. Our focus is on examining the evolution patterns and inter-relationships of shield tunneling parameters within volcanic ash strata. Subsequently, we propose an optimized strategy for these tunneling parameters. By employing six machine-learning algorithms to construct prediction models, we compare and analyze their performance in predicting the tunneling excavation speed. The results indicate a positive correlation between slurry pressure and tunnel depth in volcanic ash strata, suggesting that the grouting pressure should exceed the slurry pressure by approximately 0.22 MPa. In the composite stratum of “volcanic ash debris + round gravel”, the cutter torque exhibits a strong negative correlation with the total thrust (−0.77). Due to tool wear and ground resistance, the excavation speed and cutter speed are weakly negatively correlated. Compared to other strata, shield tunneling in volcanic ash strata exhibits larger grouting pressure fluctuations, slower tunneling excavation speed, greater total thrust, higher cutter torque, and lower cutter speed. Regarding shield tunneling excavation speed prediction, the ranking of the algorithm performance is RF > DNN > ANN > BPNN > MNR > SVM, with RF achieving a decision coefficient of 0.829. The RF model is well-suited for predicting the shield structure tunneling excavation speed.

Optimized machine learning models for predicting crown convergence of plateau mountain tunnels

The precise prediction of tunnel convergence holds significant importance in ensuring the safety and efficiency of tunnel construction. This study involves the construction of seven machine learning (ML) models that are deemed reliable for predicting crown convergence (CC) of plateau mountain tunnels. These models include K-nearest neighbour (KNN), support vector regression (SVR), decision tree (DT), random forest (RF), extreme gradient boosting (XGBoost), categorical boosting (CatBoost), and automated machine learning model (Auto-ML). The Bayesian optimization (BO) technique and the Tree-based pipeline optimization tool (TPOT) were employed to optimize the hyperparameters of non-automated machine learning models and the automated machine learning model, separately. A total of 2,734 samples of crown convergence monitoring data were collected for training and testing the models. The evaluation metrics employed to assess the performance of the models’ predictions included the determination coefficient (R2), mean absolute percentage error (MAPE), mean absolute error (MAE), and root mean square error (RMSE). The XGBoost model demonstrated the best prediction performance with the R2, MAPE, MAE, and RMSE of 0.9887, 0.1271, 0.7759, and 1.1845 on test set. The XGBoost, CatBoost, and Auto-ML models were utilized to predict the crown convergence monitoring curves of four sections of Huzhubeishan Tunnel in Qinghai Province, China. Notably, the predicted curves exhibited a significant level of concordance with the actual monitoring curves. The results of Shapley Additive Explanations (SHAP) suggested that time, tunnel depth ratio and groundwater table were more important than other input variables. The XGBoost model showed the best robustness of prediction performance across varying dataset sizes for seven distinct machine learning models.