TBM Tunneling Research Articles

Study on Warning Method for Fault Rockburst in Deep TBM Tunnels

Study on Warning Method for Fault Rockburst in Deep TBM Tunnels

Research on optimization strategy of TBM tunneling parameters based on stratum perception and simulation tunneling experiment

Real-time perception of surrounding rock stratum and optimization decision of tunneling parameters are of great significance for TBM safe and efficient tunneling. Taking a diversion tunnel in Xinjiang as the engineering background, 948 groups of tunneling data of surrounding rocks at all grades were collected. Aiming at the problem of unbalanced tunneling data of different grades of surrounding rock, the quaternion classification problem of surrounding rock grade is converted into the binary classification problem, and the surrounding rock stratum perception model is established based on EasyEnsemble algorithm. On this basis, a flow frame for optimization of all grades surrounding rock tunneling parameters is proposed, and the differences between the optimization results of exhaustive method, simulated annealing algorithm and ant colony optimization algorithm are compared. The results show that the prediction error of ant colony optimization model is less than 5 %, and the running time is only 1/12 ∼ 1/6 of the exhaustive method. Then, based on the self-developed model test equipment, a similar materials test block of surrounding rock stratum is configured, and a scale cutter head is used for simulation tunneling experiment. The experiment shows that the ant colony optimization model optimization result is the best combination of tunneling parameters, which shows that the proposed optimization flow frame of tunneling parameters has good applicability. Finally, the AdaBoost model was trained with unbalanced samples of various grades of surrounding rock, and the prediction results were statistically analyzed. The results showed that the AUC value of EasyEnsemble model increased by 11.33 % on average, the F-measure increased by 18.12 % on average, and the G-measure increased by 14.00 % on average compared with the AdaBoost model, indicating that data balance has a significant effect on improving the perception accuracy of surrounding rock stratum.

Analysis of the influence of karst cave parameters on surface settlement in TBM tunnelling

In order to study the sensitivity of multiple karst cave factors on surface settlement during Tunnel Boring Machine(referred to TBM hereinafter) tunnelling, a three-dimensional numerical model is built by taking a subway project as an example and combining MIDAS GTS NX finite element software. Secondly, the influence of the radius, height, angle, vertical net distance, and horizontal distance of the karst cave on the maximum surface settlement is studied and sorted under the two working conditions of treatment and untreated using the grey correlation analysis method. Additionally, a multi-factor numerical model of the untreated karst cave is established. Finally, based on the preceding research, a multi-factor prediction model for the maximum surface settlement is proposed and tested. The results reveal that when the karst cave is not treated, the radius and height of the karst cave have a significant effect on the maximum surface settlement. After the cave treatment, the influence of the cave parameters on the maximum settlement of the surface is greatly reduced. The calculating modelcreated in this study offers excellent prediction accuracy and good adaptability.

Analysis of TBM tunneling performance based on mass fractal dimension of rock chips

The size of the rock chips and its particle size distribution can fully reflect the rock-breaking efficiency of the TBM, but the index that can comprehensively characterize the particle size distribution of rock chips has not yet been found to quantitatively evaluate the TBM tunneling efficiency. Based on the fractal theory, this study uses the mass fractal dimension to quantitatively analyze the particle size distribution of rock chips, and explores its relationship with TBM tunneling performance index. Field sieving tests were carried out on rock chips from two tunnel projects. According to the sieving test results, the mass fractal dimension of the rock chips is calculated as well as the correlation between it and common TBM performance evaluation indexes, average tunneling thrust is discussed. The research results show that the mass distribution of TBM rock chips has significant fractal and self-similar characteristics, the higher the content of large-size rock chips, the lower the content of small-size rock chips, the smaller the fractal dimension value. Simultaneously, under the same surrounding rock conditions, the mass fractal dimension of rock chips is positively correlated with the logarithm of specific energy and negatively correlated with the logarithm of coarseness index, which indicates that the smaller the fractal dimension, the higher the efficiency of rock breaking. It is demonstrated that the interval of TBM thrust force corresponding to smaller specific energy, larger coarseness index and smaller fractal dimension is the same, which can be determined as the optimal thrust interval.

A Novel Identification Approach Using RFECV–Optuna–XGBoost for Assessing Surrounding Rock Grade of Tunnel Boring Machine Based on Tunneling Parameters

In order to solve the problem of the poor adaptability of the TBM digging process to changes in geological conditions, a new TBM digging model is proposed. An ensemble learning prediction model based on XGBoost, combined with Optuna for hyperparameter optimization, enables the real-time identification of surrounding rock grades. Firstly, an original dataset was established based on the TBM tunneling parameters under different surrounding rock grades based on the KS tunnel. Subsequently, the RF–RFECV was employed for feature selection and six features were selected as the optimal feature subset according to the importance measure of random forest features and used to construct the XGBoost identification model. Furthermore, the Optuna framework was utilized to optimize the hyperparameters of XGBoost and validated by applying the established TBM dataset of the KS Tunnel. In order to verify the applicability and efficiency of the proposed model in surrounding rock grade identification, the prediction results of five commonly used machine learning models, Optuna–XGBoost, Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Decision Tree (DT), XGBoost, and PSO–XGBoost, were compared and analyzed. The main conclusions are as follows: the feature selection method based on RF–RFECV improved the accuracy by 8.26%. Among the optimal feature subset, T was the most essential feature for the model’s input, while PR was the least important. The Optuna–XGBoost model proposed in this paper had higher accuracy (0.9833), precision (0.9803), recall (0.9813), and F1 score (0.9807) than other models and could be used as an effective means for the lithological identification of surrounding rock grade.

Study on the Interaction Mechanism of Segments in the Stratum of TBM Tunnels Undercrossing Existing Buildings

Study on the Interaction Mechanism of Segments in the Stratum of TBM Tunnels Undercrossing Existing Buildings

Experimental study on the influences of cutter geometry and material on scraper wear during shield TBM tunnelling in abrasive sandy ground

When shield TBM tunnelling in abrasive sandy ground, the rational design of cutter parameters is critical to reduce tool wear and improve tunnelling efficiency. However, the influence mechanism of cutter parameters on scraper wear remains unclear due to the lack of a reliable test method. Geometry and material optimisation are often based on subjective experience, which is unfavourable for improving scraper geological adaptability. In the present study, the newly developed WHU-SAT soil abrasion test was used to evaluate the variation in scraper wear with cutter geometry, material and hardness. The influence mechanism of cutter parameters on scraper wear has been revealed according to the scratch characteristics of the scraper surface. Cutter geometry and material parameters have been optimised to reduce scraper wear. The results indicate that the variation in scraper wear with cutter geometry is related to the cutting resistance, frictional resistance and stress distribution. An appropriate increase in the front angle (or back angle) reduces the cutting resistance (or frictional resistance), while an excessive increase in the front angle (or back angle) reduces the edge angle and causes stress concentration. The optimal front angle, back angle and edge angle for quartz sand samples are α = 25°, β = 10° and γ = 55°, respectively. The wear resistance of the modelled scrapers made of different metal materials is related to the chemical elements and microstructure. The wear resistances of the modelled scrapers made of 45#, 06Cr19Ni10, 42CrMo4 and 40CrNiMoA are 0.569, 0.661, 0.691 and 0.728 times those made of WC-Co, respectively. When the alloy hardness is less than 47 HRC (or greater than 58 HRC), scraper wear decreases slowly with increasing alloy hardness as the scratch depth of the particle asperity on the metal surface stabilizes at a high (or low) level. However, when the alloy hardness is between 47 HRC and 58 HRC, scraper wear decreases rapidly with increasing alloy hardness as the scratch depth transitions from high to low levels. The sensitive hardness interval and recommended hardness interval for quartz sand are [47, 58] and [58, 62], respectively. The present study provides a reference for optimising scraper parameters and improving cutterhead adaptability in abrasive sandy ground tunnelling.

Big data-driven TBM tunnel intelligent construction system with automated-compliance-checking (ACC) optimization

TBM tunneling in subsea areas with adverse geological conditions presents potential risks due to non-compliant tunneling strategies resulting from manual adjustments and untimely communications. This study proposes an innovative subsea TBM tunnel intelligent construction system, featuring automated-compliance-checking (ACC) optimization, to assess feasibility through a case study. The key ingredient of the system is an integrated data-driven model framework comprising of a geological identification model based on fuzzy set theory and Dempster-Shafer (D-S) fusion theory and a machine learning-based TBM construction strategy ACC optimization model. In addition, a real-time data services scheme is established to manage TBM engineering big data, ensuring its effective utilization. Implemented in the PRDWRA project's F27 fault zone, the system identified greater stratum complexity than previously known, with potential dual faults. Post-ACC optimization, it achieved a 13.6 % increase in advance rate, maintained consistent slurry pressure, and reduced the deviation between optimized and expected values by 57.1 %. Finally, drawing upon statistical data sourced from project stakeholders, the system's deployment yielded a 9 % cycle time reduction, and a 27 % cost saving, with 17 % from reduced construction times and 9 % from lower accident rates. These results confirm the strategy's compliance with construction codes, significantly reducing risk and improving tunneling efficiency. The results confirm that the operational strategy adheres to construction code requirements, substantially reducing construction risks and effectively enhancing tunneling efficiency.

Sequential Prediction of the TBM Tunnelling Attitude Based on Long-Short Term Memory with Mechanical Movement Principle

TBM tunnelling attitude controlling is a significant issue for guaranteeing the tunnel fitting the expected tunnel axis, with directly influence the tunnel quality. The key to solve the problem is to establish the relationship between the tunnelling attitude and the controlling parameters and to predict the tunnelling attitude accordingly. For this, this paper introduced a TBM tunnelling attitude predicting method. In detail, using Long-Short Term Memory (LSTM), the initial tunnelling attitude and the controlling parameters of each later ring are taken as input, while the tunnelling attitude of each later rings are regarded as the output, and the relationship between the input and output is established. Meanwhile, for avoid the over-fitting and error accumulation risk of LSTM, the theoretical relationship between the input and output is also built based on the TBM mechanical movement principle, and it is also involved into the LSTM-based relationship as constraints. The proposed method is verified by the field data collected from the 6th Section of the Qingdao Metro Project, and the results reveal that the proposed LSTM-based method is accurate and acceptable.

Study on mechanical properties of composite support structures in TBM tunnel under squeezing soft rock conditions

As more and more TBM tunnels are constructed under complex conditions such as high stress and fault fracture zones, large deformation disasters of squeezing soft surrounding rocks occur frequently. However, TBM method shows poor adaptability to major engineering challenges. Equipment damage, track deviation and support structures failure are widely observed. It is important to propose an effective support scheme and to fully clarifying the mechanical properties of the support structures in TBM tunnel. In this case, this paper aims to conduct laboratory and numerical tests considering steel–concrete interface bond-slip behavior so as to verify the effectiveness of the proposed support scheme. Thus, the quantitative relationship between arch type, arch spacing, longitudinal connection strength, concrete strength, steel fiber content, and tunnel surrounding rock deformation can be obtained. The research results show that the support scheme proposed in this paper shows good applicability for deformation control of TBM tunnels under squeezing soft rock conditions, which provides a reference for TBM tunnel support under squeezing soft rock conditions.

Support Optimization of Open TBM Tunneling in Luohe Formation Sandstone by CT Test and Numerical Simulation

As underground engineering extends into the western and deeper regions of China, more and more Luohe Formation sandstone layers will be encountered, which have weak cementation and high water content. It is a significant challenge to apply the open TBM, and the support system is crucial in determining whether TBM can excavate quickly and safely. Therefore, in order to optimize the support scheme, this paper analyzes the pore structure and porosity through CT scanning, the results indicate that the volume percentage of pores ≥34 μm is 2.3% and 1.5%, respectively, the large pore apertures are predominant, the surrounding rock has strong permeability, and there is a high risk of rock burst and roof collapse accidents, hence requiring reinforced support measures. On this basis, numerical simulations were conducted to evaluate the support effectiveness. The results show that replacing the “bolt + mesh” with a “bolt + cable + mesh + steel belt”, and replacing the top three bolts with 7.3 m anchor cables, can better control the deformation and provide sufficient thrust force for the TBM, ensuring excavation speed. After the implementation of this scheme at the Kekegai coal mine in Shaanxi, China, the TBM excavation speed increased by 70%, from the previous 10 m/day to 17 m/d, significantly reducing the project duration and construction costs.

Digital Twin-Driven Framework for TBM Performance Prediction, Visualization, and Monitoring through Machine Learning

The rapid development in underground infrastructure is encouraging faster and more modern ways, such as TBM tunneling, to meet the needs of the world. However, tunneling activities generate complex and heterogeneous data, which makes it difficult to visualize the performance of a project. Advancements in information technology, such as digital twins and machine learning, provide platforms for digital demonstration, visualization, and system performance monitoring of such data. Therefore, this study proposes a digital twin-driven framework for TBM performance prediction through machine learning, visualization, and monitoring. This novel approach integrates machine learning and real-time performance data to predict, visualize, and monitor the status of the tunnel construction progress. A digital twin virtual model of TBM was constructed based on TBM design parameters, the input parameter, boring energy, RPM, torque, thrust force, speed, gripper pressure, total revolution, and Q-value provided to SVR and ANN models to predict the TBM AR and PR, and TBM daily progress was visualized continuously. The predictive performance indices R2 (0.97) and RMSE (0.011) were estimated for AR prediction, showing the accuracy of the proposed model. To demonstrate the proposed framework, this study shows the its effectiveness. By implementing this framework, stakeholders can minimize the risk associated with the cost and schedule of a tunneling project by simultaneously visualizing and monitoring the performance of TBMs through digital twin and machine learning algorithms.

Influence of Pea-Gravel Layer on Segment Ring Support Performance in Shield TBM Tunnels: A Discrete-Continuous Coupling Simulation and Model Test

Influence of Pea-Gravel Layer on Segment Ring Support Performance in Shield TBM Tunnels: A Discrete-Continuous Coupling Simulation and Model Test

A Theoretical Method and Model for TBM Tunnelling Trajectory Adjustment

TBM tunnelling trajectory adjustment is a significant issue in guaranteeing a tunnel project. This paper proposes a theoretical method of trajectory adjustment aimed at synchronously reducing bias angle and distance. The proposed method can be divided into three steps. First, the need for manual intervention in the tunnelling trajectory is determined based on the current bias angle and distance. Next, if manual intervention is required, a theoretical relationship is established using the current bias angle and distance as an input and the rotated angle of the TBM main beam as an output. Finally, a series of constraints according to the normal working conditions of the TBM are incorporated into the method. These constraints ensure that the method remains within the acceptable range of TBM operation. Using mechanical parameters such as the cutterhead diameter and cutter spacing of the TBM used in the sixth section of the Qingdao Metro Project, a model suitable for the project is established, and the model is modified by the tunnelling trajectory data collected in the field. This method provides a reference for TBM drivers to use to correct the tunnelling trajectory while considering the specific conditions of the project.

Case study of thermal interaction at urban scale

Due to the rise of awareness regarding the problem of climate change and greenhouse gas emissions, the European Union has increased its involvement in climate change mitigation policies. For this reason, investing in renewable energy sources has become urgent and mandatory.
 Geothermal energy represents a large source of environmentally friendly energy with a low carbon footprint [1] and, thus, shows a high potential to help supply the thermal demands of buildings in urban areas which are usually characterized by a high-density population. However, especially in the shallow depths of urban areas, it is difficult to find natural undisturbed underground thermal conditions because of anthropic interventions. Moreover, these areas are being increasingly used for energy purposes, for example implementing shallow geothermal systems, as a proficient technology to provide clean thermal energy and supply thermal demands of buildings in both winter and summer seasons [2].
 This abstract will focus on thermal interactions in urban areas with reference to the case of the city of Turin where, within the project of Metro Line 2 (ML2) currently at its outlined design stage, the thermal activation of both Cut&Cover and TBM tunnels and of metropolitan stations is envisaged, with the creation of an urban energy geostructure. This infrastructure will extend, in a first stage, in the central districts of the city for about 10 km with 1 depot, 13 stations and 14 shafts and will represent an essential milestone for the city transportation system, reaching decentralized areas and revolutionizing the surface space [3].
 The subsurface in the central area of the city is characterized by sand and gravel deposits overlying, at approximately 40 m depth, clay layers, resulting in a very productive aquifer. Consequently, the geothermal and industrial use of water is of extreme importance [4] and more than 30 geothermal open loop systems are present, based on the public authorities databases. Together with a smaller number of geothermal closed loop systems, they exchange heat according to the user's seasonal cooling and heating demands, exploiting the subsurface resource. Moreover, anthropic entities such as underground car parks, urban tunnels and building basements exchange heat fluxes with the ground as well, affecting indirectly the aquifer and subsoil both hydraulically and thermally.
 With the construction of the ML2 and the thermal activation of its structures, the actual conditions may be affected. It is indeed of interest to understand and evaluate the interaction between the ML2 and the other existing systems. To this extent, a 3D Finite Element numerical model with thermo-hydraulic coupling of the city area crossed by the first two ML2 lots was built by using the FEFLOW software [4]. Thanks to the interoperability of the numerical code and the Geographic Information System (GIS), it was possible to include in the model all the relevant information collected about hydrogeology, existing and planned geothermal systems and anthropic structures. Adequate material properties and boundary conditions were imposed (Figure 1(a)) on the basis of the data collected during the geognostic and hydrogeological survey campaigns of the outlined design. To reproduce the current thermally and hydraulically disturbed subsurface environment, the model was run to simulate a 5 years lifespan where all the existing systems are active and validated against available monitoring data. Subsequently the thermal activation of the ML2 was introduced and its effect on the subsurface was predicted for a period of 4 years.
 Finally, through GIS processing, the results allowed to extrapolate thermal maps of the study area (Figure 1(b)). The modelling showed that the thermal alteration due to the ML2 is limited to the corresponding depths of its structures and downstream of the infrastructure. The central district of the city, where the largest number of existing geothermal systems are present, is the area that is shown to be most influenced and where the thermal plume of existing open loop systems may locally affect the thermal exploitation from the ML2 structures. It is also shown that open loop systems in the city impact massively the ground temperature more than the energy geostructures of the ML2 do.

Evolution law and mechanism of time-delayed spalling in a deep TBM tunnel: A case study

Time-delayed spalling is proposed to describe the time-dependent splitting failure near the tunnel periphery, which occurs in several days or several months after excavation. This kind of failure has been frequently encountered in a deep TBM tunnel, endangering workers' security and delaying the construction schedule. In this paper, two typical time-delayed spalling cases were systematically introduced, including geological and supporting conditions. Based on field observation, microseismic monitoring and laboratory creep tests, the characteristics and mechanism of time-delayed spalling were investigated. Results showed that time-delayed spalling is a stress-induced time-dependent failure in the vicinity of tunnel surface and appears as flake or plate-like splitting fracture subparallel to the free surface. Although the failure region where time-delayed spalling happened is intact, discontinuities are scattered in the peripheral region. Time-delayed spalling is sensitive to boundary conditions and timely support is an essential method for preventing time-dependent spalling. This research is helpful to the tunnel excavation under similar geological conditions and provides foundations for the prevention of time-delayed spalling.

Analysis of the Disc Cutter Cutting Load and Performance during TBM Tunneling in Soft-Hard Varied Strata through Laboratory Cutting Test

Abstract Tunnel boring machine (TBM) disc cutters are specially designed for breaking hard rocks and always exhibit unsatisfactory performance during the soft-hard varied stratum tunneling process. To figure out the load and cutting performance of the disc cutter and avoid unsatisfying excavation face crushing effects, a soft-hard varied strata excavation face model was made and rotary cutting tests with full-scale disc cutters were conducted. The load and cutting performance of the disc cutter under different TBM operating conditions were monitored and analyzed based on the test. It was found that the variation of the disc cutter load did not meet the CSM model completely, and the tangential force of the disc cutters in the heterogeneous areas was only about 30–40 % of that in the uniform areas of the excavation face model. An ideal criterion for the excavation face to be crushed successfully was established and the unknown parameters in it were obtained by fitting the test data. The gradation information and fractal dimension of crushing debris were obtained by the sieved-and-weighed method, which can provide indicators for the crushing effect of the disc cutters. Three different disc cutter poor performance modes in the heterogeneous strata cutting process were analyzed: (1) rotating starting failure of the disc cutters caused by tangential load insufficiency, (2) excavation face crushing failure caused by low crack extending capacities of the materials being cut and improper operating parameters (too small cutting depths or too large disc cutter spacing), and (3) adverse excavation face crushing forms (large or powdery debris). These analyses can help with the performance evaluation of disc cutters and the tunneling parameter adoption of the TBM in soft-hard varied strata tunneling engineering.

A LightGBM-based strategy to predict tunnel rockmass class from TBM construction data for building control

Identification of rockmass class before construction is crucial to the safe and high-efficiency building of underground tunnels and has been a challenge for long water diversion tunnels. This paper is devoted to developing the LightGBM-based strategy for on-site rockmass class prediction in long tunnels from TBM construction data. The LightGBM-based strategy optimizes the input features and hyperparameters automatically by combining the tree-structured Parzen estimator (TPE), the light gradient boosting machine (LightGBM), and Shapley Additive exPlanations (SHAP) and establishes rockmass prediction models with data of various structures in 7505 TBM tunneling cycles in the Yinsong tunnel of 17.488 km long. The LightGBM-based strategy has an accuracy of 92% on the testing set, outperforms the random forest and support vector machines on the Yinsong tunnel data, and shows good generalization ability in the TBM7 tunnel in Xingjiang. The work contributes to the intelligent and efficient construction of long TBM tunnels.

Behavior of damaged TBM tunnel under MJS and Micro-disturbance grouting treatment: a case study

Behavior of damaged TBM tunnel under MJS and Micro-disturbance grouting treatment: a case study

Optimization of Rockburst Risk Control Measures for Deeply Buried TBM Tunnels: A Case Study

Choosing reasonable control measures for different intensity rockburst risks not only effectively prevents and mitigates rockburst risks but also reduces time and engineering investment costs. Due to the limitations of the tunnel boring machine’s structure and working conditions, tunnels excavated by TBMs are highly susceptible to rockbursts. What is even worse is that there are very few measures to control the rockburst risk in these tunnels. Implementing reasonable control measures from the limited mitigation measures to control and mitigate rockburst in TBM tunnels is an urgent problem that warrants a solution. In this paper, a large number of on-site rockburst risk control cases and a large amount of MS monitoring data (the total mileage of MS monitoring is approximately 7 km, lasting for 482 days) are used to derive a reasonable scheme to control the rockburst risk of different intensities in twin TBM tunnels. First, the rockburst early warning effect of the two headrace tunnels of the Neelum–Jhelum hydropower station based on microseismic monitoring is analyzed. Second, based on highly accurate rockburst warning results, 94 rockburst risk control cases are applied to analyze the control effect of different control measures at different intensities of rockburst risk. Then, by combining factors such as the time cost and expense cost of different control measures, more reasonable control measures for different intensity rockburst risks are proposed: for slight rockburst risk, normal excavation is preferred; for moderate rockburst risk, horizontal destress boreholes are preferred; and for intense rockburst risk, a combination of measures of shortening daily advance and horizontal destress boreholes is preferred. The research results can provide a reference for other TBM excavation projects to carry out rockburst risk prevention and mitigation.