Tunnel Boring Machine Excavation Research Articles

Analyses of Pre‐Excavation Grouting for TBM Tunnelling

AbstractPre‐excavation grouting (PEG) is essential for mitigating groundwater inflow to unlined tunnel structures. Prevention of initial water inflow proved best practice to balance groundwater conditions throughout the utilisation of a tunnel. The grouted rock mass acts as a circumferential sealing barrier instead of a secondary lining to minimise groundwater inflow to an acceptable level over the structure's lifetime. The construction of unlined tunnels relies on existing favourable in‐situ rock mass conditions with an overall low hydraulic head, mainly to keep the effort of grouting inferior and avoid an unbalanced proportion of pre‐excavation grouting during the tunnel construction works.From the operational perspective of tunnelling works, pre‐excavation grouting delineates the continuous excavation process of a TBM and represents a discontinuative work process. In addition, grouting includes an exploration process ahead of the cutterhead to predict the ground conditions to align the sealing demand of the rock mass. Generally, pre‐excavation grouting foresees the drilling of mainly open boreholes with a considerable length of 20 m to 25 m ahead of the tunnel boring machine (TBM). Establishing a continuous grouted zone around the tunnel demands an overlapping of the grouting rings ranging from 2 m to 10 m. The overlapping decreases the excavation length of the TBM adequately. The repetitive grouting process interfering with the excavation consists of various processes such as exploration including water loss measuring (WLM), the drilling and grouting of boreholes and the hardening time.TBM tunnelling depends on the systematic and continuous implementation of construction procedures. Therefore, based on current static pre‐excavation grouting, an agile combined grouting and excavation approach is presented, incorporating a reliable pre‐excavation grouting, a systematic TBM excavation and a specific balance of long‐term sealing and high utilisation rates for TBM excavation.

On the Effect of Shield Friction in Hard Rock TBM Excavation

During hard rock tunnel boring machine (TBM) excavation, shields behind the cutterhead are usually in direct contact with the tunnel wall and therefore subjected to friction forces that occur within this interface. The effect of shield friction in hard rock TBM tunneling has received little attention so far and literature on this topic is scarce and conflicting. To investigate the friction coefficient for the planning of TBM excavations, specialized shear tests were conducted where steel specimens were sheared against lithologically different rock specimens under representative normal forces and shearing speeds. The tests were executed with and without the use of bentonite lubrication. The results show that there is a significant difference between different lithologies and also that using bentonite does not lower the friction coefficient as expected. To elaborate on the effect of shield friction during construction, a framework for interpretation of TBM operational data based on experience from construction sites is provided. Whereas thorough interpretation of the data enables one to draw conclusions about the shield friction, it still remains difficult to assess the real effect of shield friction due to the limited possibilities to observe the ongoing phenomena. This study therefore provides the basis for theoretical and practical assessments of the effect of shield friction for the planning and construction phase of a tunnel. This becomes increasingly important in the light of new contractual developments that aim at differentiating “standard” from “special” advance in an objective and reproducible way.

Rockburst and microseismic activity in a lagging tunnel as the spacing between twin TBM excavated tunnels changes: A case from the Neelum-Jhelum hydropower project

A reasonable spacing between tunnels is very important in deeply buried tunnels, as it may mitigate the risk of rockburst occurrence. This spacing is particularly important for tunnels excavated using a tunnel boring machine (TBM), as the methods available for controlling rockburst occurrence are inflexible and limited using these machines (compared to tunnels excavated using the drilling and blasting (D&B) method). In this paper, a rare example was studied in situ in which the spacing between twin tunnels was changed to mitigate the rockburst risk during TBM excavation. First, the characteristics of the rockburst and microseismic activity were investigated in three sections of the lagging tunnel before, during, and after the spacing between the tunnels was changed (we concentrated on the lagging TBM696 tunnel, which is part of the Neelum-Jhelum hydropower project). We observed a significant occurrence of rockburst and microseismic activity in the lagging tunnel at the original spacing of the twin tunnels in both the sandstone and siltstone lithologies, and thus a consideration of enlarging the spacing between the twin tunnels is reasonable. A more detailed investigation was then conducted to explore the effects of tunnel spacing on rockburst occurrence and microseismicity. The rockburst frequency and microseismic radiated energy due to excavation unloading generally decrease as the spacing between the twin tunnels increases (substantially at first and then more slowly as separation increases). In particular, the microseismic radiated energy exhibits a power-decreasing type in both the sandstone and siltstone. Increasing the spacing beyond a certain point, therefore, exerts a very limited effect on the microseismic radiated energy and occurrence of rockbursts (increments of 16–21 m and 15–20 m in sandstone and siltstone, respectively). Consequently, in practice, a very reasonable approach would be to enlarge the spacing of twin tunnels by 22.48 m. Thus, microseismic monitoring is a useful technique for assessing the rockburst risk and deriving a reasonable value for tunnel spacing. This study can be used as a guideline to derive reasonable tunnel spacings when using not only TBMs but also D&B.

A new method for wear estimation of TBM disc cutter based on energy analysis

The accurate estimation of disc cutter wear has always been a long-term topic affecting the excavation efficiency and construction cost of tunnel boring machines (TBMs), especially in the project of high-strength and high-abrasiveness stratum. In fact, disc cutter wear is one of the comprehensive results of rock-machine interaction during TBM excavation. Therefore, the change of internal energy of rock-machine system describes the wear information of disc cutter. In this study, a new method for estimation disc cutter wear based on energy conversion mechanism is proposed. Firstly, the basic relationship of energy conversion during TBM excavation is analyzed in detail, and an energy equation considering the influence of geological conditions, TBM technical specifications and rock-machine interactions at three levels is established. Based on this context, according to the working characteristics and abrasion mechanism of disc cutter, the conversion mechanism between the disc cutter wear energy and wear capacity is investigated, and the definite relationship between the energy conversion coefficient and the properties of intact rock is obtained. Furthermore, to illustrate the applicability of this method, a case study of the Shenzhen Metro Project in China is introduced and analyzed in detail. The results show that the proposed method can predict 85 % of the average wear of each disc cutter on the cutterhead. Finally, the prediction method provided in this study is compared with Gehring, NTNU and CSM models to validate the rationality and reliability of this method. Evidently, this method can provide an accurate and reliable estimate of the general wear capacity and life of disc cutters on the cutterhead, and it is also a very practical tool for TBM engineers to make decision and optimize the cutter replacement scheme.

Correlation Analysis of Machine Performance Parameters and Rock Mass Properties during Tunnel Boring Machine Excavation Process: A Case Study in Yin-song Headrace Tunnel, China

Abstract A rock breaking process during the tunnel boring machine (TBM) excavation sequence involves a complicated interaction between the disc cutters and the tunnel face, and the excavation process is influenced both by the rock mass properties and the TBM performance. Hence, in achieving a highly efficient TBM excavation, a mutual feedback analysis of rock mass properties and machine parameters is important. In this study, a correlation analysis of rock mass properties and TBM parameters is conducted based on the field data obtained from the Yin-song headrace tunnel in Jilin Province, China. Firstly, the correlation between the rock mass properties (i.e., uniaxial compression strength and rock quality designation index) and the machine parameters (i.e., thrust force, cutterhead torque, rotational speed, penetration depth, and penetration rate) obtained during the stable operation stage of TBM is extensively investigated. The variation in the TBM penetration rate as a function of rock mass properties and machine operation parameters is studied. A statistical prediction model that defines the effects of rock mass properties on the TBM penetration rate is established by multivariate linear regression analysis. The validity of the prediction model is verified by using the in situ monitoring data obtained from two different chainages of the project. This study can help rationalize the TBM machine parameters in order to obtain a highly efficient TBM excavation and a low life-cycle cost for the machine.

Jamming of the double-shield tunnel boring machine in a deep tunnel in Nyingchi, Tibet Autonomous Region, China

The Duoxiongla tunnel in Nyingchi, Tibet Autonomous Region, China passes through a gneissic formation, with a maximum 830 m thick overburden. The tunnel was excavated by a double-shield tunnel boring machine (TBM) and three shield jamming accidents occurred during the construction, which adversely affected the construction progress. In order to prevent the shield machine from jamming again, numerical simulations were conducted to investigate the shield jamming accidents. In addition, the contact relationship between double-shield and surrounding rocks when the TBM entered squeezing ground and the changes in frictional resistance to be overcome during the excavation process were studied. The effects of injection of lubricants and over-cut on reducing the shield jamming risk were explored. Finally, the jamming criterion was proposed by comprehensively considering the surrounding rock strength, in-situ stress, surrounding rock deformation, and reserved gap. The results show that the sequence of surrounding rocks that come into contact with and squeeze the TBM can be influenced by the gap between shields and surrounding rocks, and the locations where the three shield jamming accidents happened are consistent with the actual advancing lengths of the TBM in the formation with extrusion deformation. The method of injecting lubricants at the contact position between surrounding rocks and shields fails to release the jammed TBM. Over-cut can widen the gap between surrounding rocks and shields, which reduces the risk of shield jamming. The assessment of jamming in the Duoxiongla tunnel based on the established jamming criterion is consistent with the actual engineering excavation conditions and can provide reference for judging shield jamming during TBM excavation in other types of squeezing ground.

Towards optimized TBM cutter changing policies with reinforcement learning

AbstractIn tunnel boring machine (TBM) excavation, cutter maintenance is necessary, but the time for it has to be minimized for efficiency. Although there is extensive literature on TBM cutter wear and predictive maintenance for different industrial applications, there is no optimized policy for cutter changes in TBM tunnelling today. This study aims to investigate the application of reinforcement learning (RL) – a branch of machine learning – for finding optimized policies for cutter changing that maximize the number of working cutters and minimize the maintenance effort. A simulation of a TBM excavation process is developed that focuses on the cutter wear and an agent that controls when cutters must be changed. The simulation uses generated parameters that indicate the cutter life, but the results could be transferred to real sensor data in future excavations once that level of development is reached. The article presents the first results from this RL scenario which can give valuable insights into TBM excavation logistics and presents a challenging multiaction‐selection RL problem.

Multi-objective optimization control for tunnel boring machine performance improvement under uncertainty

The tunnel boring machine (TBM) is an important and common construction method for urban subways, and it requires a detailed and rational control strategy to ensure the safety and efficiency of TBM excavation. Multiple objectives are required for shield tunneling; however, the control of TBM parameters is a complex and difficult problem under frequently encountered unforeseen geological conditions. Hence, a multi-objective optimization framework has been proposed to provide suggested TBM operational parameters for decision making under uncertainty. A Grey Wolf Optimizer-Generalized Regression Neural Network (GWO-GRNN) model has been developed to predict the TBM performance under different TBM operating parameters and geological conditions. Then, the nondominated sorting genetic algorithm (NSGA-II) is introduced to solve the multi-objective optimization problem and obtain the final decision-making solutions. To indicate the applicability of the proposed multi-objective optimization (MOO) framework, the Wuhan San-Yang Road Highway-Rail Tunnel Shield Project was adopted as an example. Results show that the GWO-GRNN model is in good agreement with the experimental measurements to predict the advance speed and ground settlement, with R2 values of 0.97 and 0.91, respectively. Additionally, the results of NSGA-II optimization show that the proposed framework can realize the optimization of multiple objectives under different geological conditions. The results of this research are able to generate the optimal solutions for TBM operators, which can improve decision making when conflicting TBM excavation objectives exist.

Early warning of tunnel collapse based on Adam-optimised long short-term memory network and TBM operation parameters

Collapses are common geohazards during tunnel boring machine (TBM) construction under complex geological conditions. This study proposes a tunnel collapse early warning method based on an adaptive momentum estimation optimised long short-term memory (Adam-LSTM) network and TBM operation parameters. Based on the Songhua River water conveyance project, a sample database containing 7538 TBM excavation cycles, three types of geological information, and 18 tunnel collapse statistics is established. A total of 5440 TBM excavation cycles from stable tunnelling sections are used for model training. The key TBM operation parameters in the first 30 s of the parameter-rising phase are used as inputs to the LSTM cell, and the geology data is considered through fully connected layers outside the LSTM cell. Then, the rock-breaking efficiency index (specific energy, Se) of the stable phase is predicted. Compared with the stable tunnelling section, the prediction accuracy of Se in the collapse section decreases to some degree. In collapse area I (i.e. collapses 15–17), by setting the threshold of the statistical indexes based on 30 consecutive predicted Se, an early warning index system for tunnel collapse is constructed. Collapse area II (i.e. collapses 5–7) and collapse area III (i.e. collapse 18) are used to verify the effectiveness of the proposed method.

Analysis of Stability and Required Offset with Vibration Velocity Considering Conditions of Bedrock and Explosive Charges Using the TBM and NATM Extension Blasting Method

The development of underground spaces in urban centers has attracted significant research attention. Typical excavation methods for underground spaces in urban areas include the New Austrian tunneling method (NATM) and the tunnel boring machine (TBM). The NATM is superior in terms of ease of construction and economic efficiency; however, vibration and noise are often cited as major complaints. In addition to their high initial cost, TBMs require intricate analyses of ground conditions during excavation. To overcome the disadvantages of both methods and reduce construction time, a TBM and NATM parallel excavation method has recently been investigated. In this study, the effects of blasting vibrations on the TBM, TBM backup device, and surrounding ground were examined during an NATM application for rear expansion blasting after pilot tunnel excavation using a TBM. Different rock types and powder factors were simulated, and differences in the vibration velocity according to their variations were predicted using 3D numerical analysis.

An Early-Warning System to Validate the Soil Profile during TBM Tunnelling

Identification of soil condition at the working face of a tunnel boring machine (TBM) is a key factor for the efficiency and safety of TBM tunneling. The paper presents the first application of the Horizontal-to-Vertical Spectral Ratio (HVSR) method on microtremors induced by a TBM during tunnelling. The innovative application is based on the development of an easy-to-use and economical early-warning system, which aims to confirm, or otherwise, the soil profile established in the design phase of tunnels by comparing the soil natural frequencies obtained from the soil profile carried out during the design phase and the soil natural frequencies coming from the HVSR analysis of the microtremors induced by the TBM during tunnelling. Just one or two geophones are necessary to use the proposed procedure. It can be applied to an area up to about 20 m ahead of the TBM excavation front and constitutes a powerful early warning system. Due to the great heterogeneity of the subsoil, dual-mode TBMs are often used, frequently changing from Open-Face (OF) mode for rock formations to Earth Pressure Balance (EPB) mode for cohesive and incoherent soil. Any “additional” information on the soil, which will be dug in the next days or hours is extremely useful for subsoil with great heterogeneity. The new procedure offers a reasonable time interval in which to modify the excavation method. This, in turn, can avoid damage to the TBM and existing structures and infrastructures. It allows us also to have a valuable geotechnical database for future works on the infrastructural networks. The proposed procedure has been successfully applied during the construction of the new underground lines in Catania (Italy).

A Newly Developed State-of-the-Art Full-Scale Excavation Testing Apparatus for Tunnel Boring Machine (TBM)

Construction of urban tunnels using a tunnel boring machine (TBM) is often favored over drilling-and-blasting based excavation method. Often, TBMs are customized and re-used in fields. However, little effort has been made to verify the status quo of the reused TBM prior to its placement, and no apparatus or method is available to examine the excavation performance of whole, assembled TBMs. Therefore, we present a newly developed apparatus which can examine the excavation performance of small cross-section TBMs with the cutterhead diameter of ∼3.5 m at full scale. The equipment was verified with a rock-like concrete specimen, in which the excavation of TBM was examined while varying the thrust and cutterhead rotational speed. The test results reveal the positive impact of thrust on the penetration rate (PR) and penetration depth (Pe), as well as a linear relationship between PR and the cutterhead speed. This proves that the presented full-scale TBM excavation testing method is capable to produce reliable and remarkably consistent results. The presented full-scale excavation testing method can be used to examine the functionality of a TBM of interest and further explore the effect of different ground conditions, such as rock strength, joints, and weathering, and the effect of different cutterhead design, including the number of cutters, cutter shape, and cutter location.

Evaluation of the Adaptability of an EPB TBM to Tunnelling through Highly Variable Composite Strata

The adaptability of an earth pressure balance (EPB) tunnel boring machine (TBM) to complex geological strata needs to be evaluated when a tunnel project is set up. It is helpful for better design and more suitable technical parameters of the machine. Because the factors that influence adaptability are numerous and interrelated, their effects also differ; hence, a quantitative assessment of adaptability is generally difficult. In the present study, a method for quantitatively evaluating the excavation adaptability of an EPB TBM was developed using an analytic hierarchy process (AHP) and fuzzy comprehensive evaluation. The method first involves an initial selection of factors that may influence tunnelling. Based on the expert questionnaire and their influence weights determined by AHP, the 10 evaluation indexes from 25 primary indexes were selected to establish the evaluation index system (EIS) including a target, criteria, and index level. Fuzzy membership functions are then derived one after another based on the effect of each evaluation index on the EBP TBM tunnelling process. A fuzzy mathematical method was finally presented to determine the adaptability of an EPB TBM excavation performance. The proposed method was applied to two special sections of diameter 6.98 m excavated by two EPB TBMs in the Shenzhen Metro Line 11 project. The geological exploration shows that these two tunnel sections pass through typical composite strata in Shenzhen. The determined adaptability grades of the EPB TBMs used for composite strata were confirmed by the actual tunnel excavation. It indicates that the developed method is reasonable and useful to evaluate tunnelling adaptability of EPB TBM.

Discrete-Element Analysis of the Excavation Performance of an EPB Shield TBM under Different Operating Conditions

This study used a discrete-element analysis to predict the excavation performance of a 7.73 m-diameter earth pressure balance (EPB) shield tunnel boring machine (TBM). The simulation mainly predicted several excavation performance indicators for the machine, under different operating conditions. The number of particles in the chamber and the chamber pressure varied, as the operating conditions changed during the simulated TBM excavation. The results showed that the compressive force, torque, and driving power acting on the TBM cutterhead varied with its rotation speed, increasing as the cutterhead rotation speed rose. The overall compressive force acting on all of the disc cutters and their impact wear increased linearly as the cutterhead rotation accelerated. The position of a disc cutter on the cutterhead had a particularly strong influence, with higher compressive forces experienced by the cutters closer to the center. In contrast, the gauge disc cutters at the transition zone of the cutterhead showed more wear than those elsewhere. The muck discharge rate and the driving power of the screw conveyor rose with increasing screw conveyor and cutterhead rotation speeds. Finally, this study suggests optimal operation conditions, based on pressure balance and operational management of the TBM.

Damage zones induced by in situ stress unloading during excavation of diversion tunnels for the Jinping II hydropower project

During the excavation of deep tunnels with high in situ stress, the stress unloading path caused by the rock mass excavation has important influences on the formation of the EDZ (excavation damage zone). In this study, the project background of the Jinping II diversion tunnels was firstly introduced. Then, the influences of stress unloading path induced by blasting excavation and tunnel boring machine (TBM) excavation on the EDZ were analyzed based on the acoustic data. Finally, the effects for different unloading paths of in situ stress induced by different excavation methods on the EDZ were studied by theoretical calculation and numerical simulation. The results show that compared with the quasi-static unloading, the transient unloading amplifies the effects of radial stress unloading and the tangential stress loading in surrounding rock masses. The EDZ depths of the blasting excavation tunnel are about 1.0 m greater than those of the TBM excavation tunnel. Moreover, the depths of the low-velocity band of the blasting excavation tunnel account for more than 50% of the total EDZ depths, while the depths of the low-velocity band of the TBM excavation tunnel account for about 30% of the total EDZ depths. The distribution of the low-velocity band along the excavation contour is closely related to the secondary stress field, indicating that the transient unloading of in situ stress is one of the important causes of the low-velocity band. After considering the post-peak mechanical properties of marble, the EDZ extents induced by different excavation methods can be estimated through numerical simulation.

Study on the symmetric bilinear initiating technique of deep-hole boulder blasting in the TBM tunnel excavation

The excavation of the deep-buried tunnel with tunnel boring machines (TBM) is often affected by boulder, which harm the cutter disc of the TBM. It is sometimes difficult to achieve the ideal blasting effect by the conventional blasting technology. In this study, a novel symmetric bilinear initiating (SBI) technique based on detonation wave collision was proposed to reduce the oversize boulders and improve the construction efficiency. The blasting parameters design and unit consumption of explosive were analyzed by using the empirical formula based on field tests in the Hongyan River Nuclear Power Plant (HRNPP) intake tunnel boulder blasting project. Numerical simulation models of the actual engineering parameters were also developed to reduce the risk of engineering test, and to analyze the detonation wave pressure, shock wave propagation, and crack state distribution. The results showed that the SBI technique obviously affects the detonation pressure distribution and crack state compared to the central point initiating (CPI) technique. Furthermore, different treatment methods of boulder were carried out in the field test. The results of rock sample size of the core-drill and TBM advance rate showed that it is possible to form better blasting effect when using SBI technique, and the results of blasting particle velocity also proved that SBI can improve the energy utilization rate of explosive. This study provides a novel method based on SBI system for the boulder blasting to ensure a safe and efficient TBM excavation.

Geomechanical model test for analysis of surrounding rock behaviours in composite strata

Due to the large differences in physico-mechanical properties of composite strata, jamming, head sinking and other serious consequences occur frequently during tunnel boring machine (TBM) excavation. To analyse the stability of surrounding rocks in composite strata under the disturbance of TBM excavation, a geomechanical model test was carried out based on the Lanzhou water supply project. The evolution patterns and distribution characteristics of the strain, stress, and tunnel deformation and fracturing were analysed. The results showed that during TBM excavation in the horizontal composite formations (with upper soft and lower hard layers and with upper hard and lower soft layers), a significant difference in response to the surrounding rocks can be observed. As the strength ratio of the surrounding rocks decreases, the ratio of the maximum strain of the hard rock mass to that of the relatively soft rock mass gradually decreases. The radial stress of the relatively soft rock mass is smaller than that of the hard rock mass in both types of composite strata, indicating that the weak rock mass in the composite formation results in the difference in the mechanical behaviours of the surrounding rocks. The displacement field of the surrounding rocks obtained by the digital speckle correlation method (DSCM) and the macro-fracture morphology after tunnel excavation visually reflected the deformation difference of the composite rock mass. Finally, some suggestions and measures were provided for TBM excavation in composite strata, such as advance geological forecasting and effective monitoring of weak rock masses.

Estimation of the excavation damage zone in TBM tunnel using large deformation FE analysis

This paper aims to estimate the range of the excavation damaged zone (EDZ) formation caused by the tunnel boring machine (TBM) advancement through dynamic three-dimensional large deformation finite element analysis. Large deformation analysis based on Coupled Eulerian-Lagrangian (CEL) analysis is used to accurately simulate the behavior during TBM excavation. The analysis model is verified based on numerous test results reported in the literature. The range of the formed EDZ will be suggested as a boundary under various conditions – different tunnel diameter, tunnel depth, and rock type. Moreover, evaluation of the integrity of the tunnel structure during excavation has been carried out. Based on the numerical results, the apparent boundary of the EDZ is shown to within the range of 0.7D (D: tunnel diameter) around the excavation surface. Through series of numerical computation, it is clear that for the rock of with higher rock mass rating (RMR) grade (close to 1st grade), the EDZ around the tunnel tends to increase. The size of the EDZ is found to be direct proportional to the tunnel diameter, whereas the depth of the tunnel is inversely proportional to the magnitude of the EDZ. However, the relationship between the formation of the EDZ and the stability of the tunnel was not found to be consistent. In case where the TBM excavation is carried out in hard rock or rock under high confinement (excavation under greater depth), large range of the EDZ may be formed, but less strain occurs along the excavation surface during excavation and is found to be more stable.

Hard-rock TBM jamming subject to adverse geological conditions: Influencing factor, hazard mode and a case study of Gaoligongshan Tunnel

Adverse geological conditions, the major challenge of tunnel construction, affect the excavation rate and even cause the hard-rock tunnel boring machine (TBM) jamming. Firstly, 121 cases of TBM jamming are analyzed in this study (detailed information can be found in Appendix A). The influencing factors of TBM jamming are studied and the hazard modes are classified into six categories. The selection of shield TBM takes up 77.69% of the 121 cases, occurring in 94 cases. In terms of adverse geological conditions, the fractured zone is one of the most commonly met adverse geological conditions for TBM jamming cases. In addition, groundwater often plays an indirect catalytic role in jamming hazards. It is found that collapse of surrounding rocks is the most common hazard mode for TBM jamming, appearing in 52 cases. Secondly, Gaoligongshan Tunnel, one of the longest railway tunnels in China, is presented as a representative case. The possibility, geological conditions and locations of TBM jamming occurring in the Gaoligongshan Tunnel are studied in site, which verifies the results of case statistics and the geological laws proposed above. The specific steps to predict and control TBM jamming in Gaoligongshan Tunnel are proposed. Finally, the lessons learned are summarized, and the countermeasures for TBM jamming are developed regarding three stages of TBM tunnel construction. The results of this study provide a reference for the mechanism of TBM jamming and share certain practical countermeasures to ensure a safe and efficient TBM excavation in adverse geological conditions.

Dynamic Prediction of Rock Mass Classification in the Tunnel Construction Process based on Random Forest Algorithm and TBM in situ Operation Parameters

Accurately predicting the rock mass classification is of great significance to ensure the safe and efficient construction of tunnel boring machines (TBMs). On the basis of the TBM in situ operation data recorded during tunnel construction, a prediction model for rock mass classification using the random forest (RF) algorithm is proposed. Through data preprocessing, 7538 TBM excavation cycles were obtained to form a data set. Each data sample included 195 operation parameters and corresponding information on mileage and rock mass classification. Furthermore, 6784 samples were randomly selected as the training set and the remaining 754 samples as the test set. According to the changing characteristics of operation parameters, each TBM excavation cycle was divided into the empty-push phase, the rising phase, and the stable phase. On the basis of the mean decrease Gini index, seven machine parameters highly correlated with rock mass classification were selected. Then, the variation characteristics (i.e., mean value and linear fitting slope) of the seven operation parameters in the first 30 s of the rising phase were used as the input features of the RF model. Additionally, the hyperparameters in the RF model were analyzed. The quantitative results show that the prediction accuracy is up to 87.27%, indicating that the proposed model is effective for the prediction of rock mass classification.