Earth Pressure Balance Shield Machine Research Articles

Soil conditioning of clay based on interface adhesion mechanism: Microscopic simulation and laboratory experiment

Clogging frequently occurs in the cutter head, excavation chamber or screw conveyor when an earth pressure balance (EPB) shield machine is tunneling in soft or silty clay ground with high clay mineral content. In this paper, montmorillonite, kaolinite, and illite were selected as research objects, and molecular dynamics (MD) simulation and laboratory experiment were adopted. At the microscopic scale, dynamic contact behavior and interfacial mechanical behavior of the interface between clay minerals and water/surfactant solution was simulated and the interfacial adhesion and conditioning mechanism between clay minerals and water/surfactant solution was revealed. Thus, sodium dodecyl benzene sulfonate (SDBS) surfactant was selected as the main composition of the soil conditioner. Then, the adhesion stress before and after soil conditioning and the contact angles between clay minerals and water/surfactant solution were tested and analyzed at the macroscopic scale. The result shows that the contact angle between droplet and clay mineral surface is an important parameter to characterize soil adhesion. The simulation rules of the microscopic contact angle are consistent with the experiment results. Furthermore, the adsorption energy between microscopic substances is dominated by electrostatic force, which can reflect the adhesion stress between macroscopic substances. Soil adhesion stress can be effectively decreased by adding the surfactant to the soil conditioner.

Experimental study on workability and permeability of sandy soils conditioned with thickened foam

Water spewing and muck plugging often occur during earth pressure balance (EPB) shield machines tunnelling in water-rich sandy strata, even though the conventional foam has been employed to condition sandy soils. In this study, a novel thickened foaming agent suitable for EPB shield tunnelling in water-rich sandy strata is developed. In contrast to conventional foam-conditioned sands, the thickened foam-conditioned sand has a low permeability due to the consistent filling of soil pores with the thickened foam, and the initial permeability coefficient decreases by approximately two orders of magnitude. It also exhibits a suitable workability, which is attributed to the enhanced capability of the thickened foam to condition sandy soils. In addition, the effect of concentration on the stability of the foam is explained by the Gibbs-Marangoni effect, and conditioning mechanisms for the thickened foam on sands are discussed from the evolution of foam bubbles.

A study on soil conditioning for cohesive soils with high content of clay minerals: Microscopic simulation and laboratory experiment

An earth pressure balance shield machine (EPB) is prone to blockage when tunneling in strata with high clay mineral content. Engineers often improve soil fluidity and reduce soil adhesion through soil conditioning to ensure the safe and efficient tunneling of shields. This paper selected montmorillonite, kaolinite, and illite as research objects and used molecular dynamics simulation and laboratory experiments. The interfacial mechanical behavior between anionic surfactant (sodium dodecyl benzene sulfonate, SDBS) solution and clay minerals was simulated at the microscopic scale and the improvement mechanism of SDBS solution on clay minerals was revealed. Then, the zeta potential of clay minerals and the stirring torque of the soil under different foam injection ratios (FIR) were tested. Accordingly, the conditioning effect of the SDBS solution at the macroscopic scale can be evaluated. The results show that the electrostatic adsorption and repulsion of ions occur on the surface of clay minerals, which makes it difficult for clay particles to aggregate into clusters. The SO3H- groups of the SDBS surfactant are the key factor to change the hydrophilicity of clay minerals. When different soil samples are improved to the same state, montmorillonite requires the largest FIR due to its microstructure.

Autonomous intelligent control of earth pressure balance shield machine based on deep reinforcement learning

In order to reduce the construction risk caused by human operation error and improve the geological adaptive ability of the shield machine, an autonomous intelligent control method is proposed for shield machine within the framework of interaction–judgment–decision based on Deep Deterministic Policy Gradient (DDPG) deep reinforcement learning in this study. Due to the strong nonlinear relationship between the shield machine's tunneling parameters, this research builds a deep reinforcement learning environment using mechanism model of sealed cabin pressure. DDPG agent model of the shield machine is established to replace the shield machine to interact and train with the geological environment. By minimizing the difference between the target pressure setting value and the sealed cabin pressure value, the dynamic balance between the sealed cabin pressure and the pressure on the excavation surface is realized, and the best strategy is obtained. Through real-time interaction with the geological environment, the method in this paper can dynamically adjust the tunneling parameters, accurately control the sealed cabin pressure, and has a strong geological adaptive ability. By realizing the intelligent decision-making of the tunneling parameters, it greatly improves the independent decision-making ability of the shield machine system, reduces the inaccuracy of human operation, and provides an effective guarantee for the efficient and safe operation of the shield machine. This study applies deep reinforcement learning technology to the control field of earth pressure balance shield machine, promotes AI technology, and provides a new idea for the development of AI construction technology in engineering field.

Intelligent real-time prediction of multi-region thrust of EPB shield machine based on SSA-LSTM

During the tunneling process of shield machine, the accurate determination of tunneling parameters is the guarantee of safe operation of shield machine. Through the real-time construction data analysis and mining of shield machine, the tunneling parameters at the next moment are obtained in real-time. Based on this, this paper proposes an intelligent real-time prediction method for multi-region thrust of EPB shield machine based on Sparrow Search algorithm-Long and Short-term Memory (SSA-LSTM). By correlation analysis of the construction big data, the data features with a great correlation of shield machine thrust are obtained. And it is used as the input of LSTM prediction model to explore the nonlinear relationship between inputs and output. SSA is used to optimize LSTM prediction model to establish a more accurate nonlinear relationship, and then the multi-region thrust of shield machine at the next moment is accurately obtained. The simulation results show that SSA-LSTM model can accurately predict the thrust of each region of shield machine at the next moment, and the prediction performance is better than other models. The method provides a reference basis for shield machine to implement accurate thrust regulation and provides a guarantee for effective control of Earth pressure balance (EPB) in sealed cabin to ensure construction safety, which has engineering application value.

Upper bound analysis of longitudinally inclined EPB shield tunnel face stability in dense sand strata

Earth pressure balance (EPB) shield machine frequently drives along a route with a longitudinal inclination angle (δ) during tunnel construction. The tunnel face stability is a crucial issue for controlling the safety of tunneling. In this paper, the finite difference method (FDM) is used to investigate the face stability of longitudinally inclined shield tunnel in dense sand strata. Based on the numerical results of soil failure pattern in front of tunnel face, a novel two-dimensional (2D) failure mechanism is conceived following the upper bound theorem. It is assumed that the failure zone consists of an upper loosen zone, an arc-shaped shear band, and a triangular rigid body, which can calculate the active limit face support pressure pu. A scale factor for pu is introduced to quantify the three-dimensional (3D) behavior from the 2D calculation, with respect to different analysis approaches, e.g., numerical simulation, limit analysis, and limit equilibrium method. By incorporating the measure of scale factor, the calculation accuracy of the proposed 2D failure mechanism can be improved to provide reasonable prediction for longitudinally inclined tunnel.

A coupled deep learning approach for shield moving performance prediction of underground tunnel construction

Recently, deep learning methods have attracted great attentions for geotechnical engineering, especially for the safety construction of underground tunnels. In this regard, the control and regulation of operational parameters are vital for safety and intelligent tunnel construction. In this study, hybrid data-driven models on the basic of optimization approaches [particle swarm optimization (PSO), multilayer hierarchical heterogeneous PSO] and deep learning methods (long short-term memory and gated recurrent unit neural network) were developed. The optimization approaches were utilized to obtain the optimal parameters of deep learning methods. Apart from that, geological data sets were extended to match the scale of operational data sets using Kriging method, which considered the effects of local geology comprehensively. The developed hybrid models (DHMs) were utilized to estimate the speed of earth pressure balance (EPB) shield machine for a tunnel project in China. Results indicate that errors in estimated results by DHMs are acceptable in geotechnical engineering. Besides, the DHMs exist potentials to cope with time-series data sets from underground tunnel project. After that, Pearson correlation coefficient was used to evaluate the relative importance of influential factors on target variable. Results show that penetration has significant correlation relationship with excavation speed. The geological and operational parameters are equally important for the prediction performance of DHMs. The developed DHMs can provide a reference for regulating shield moving performance and attaining safety construction of underground tunnels.

Prediction of geology condition for slurry pressure balanced shield tunnel with super-large diameter by machine learning algorithms

Real-time and precise prediction of geological conditions is extremely beneficial to the safe and efficient construction of slurry pressure balanced shield machines (SPBMs), especially for super-large diameter tunnels. Machine learning algorithms provide an effective way to predict geological conditions and have been successful in hard-rock tunnel boring machine (hard-rock TBM) tunnels or earth pressure balance shield machine (EPBM) tunnels. However, the effectiveness of machine learning in predicting geological conditions for super-large diameter SPBM tunnels is still unknown. This study systematically demonstrated the application of machine learning algorithms to the prediction of geological conditions in super-large diameter SPBM tunnels based on field data from the Heyan Road crossing river tunnel. The relationship between SPBM parameters and geological conditions was first evaluated, and subsequently, an adaptive model was proposed to determine the number of input variables. The performance of three algorithms, random forest (RF), AdaBoost, and support vector machine (SVM), in rock mass classification, and seven algorithms, multi-objective random forest (MORF), single-target-RF, regressor chain-RF, single-target-AdaBoost, regressor chain-AdaBoost, single-target-SVM, and regressor chain-SVM, in formation percentage prediction, were compared. The results showed that machine learning algorithms can effectively predict the geological conditions in super-large diameter SPBM tunnels. Specifically, RF had the best performance in rock classification compared with AdaBoost and SVM. MORF outperforms the other six algorithms in terms of formation percentage prediction. Additionally, sensitivity analysis indicates that the newly proposed parameters, including slurry system parameters and cutter type, have a clear positive effect on the performance of geological condition prediction.

Research on Strata Deformation Induced by EPB Tunneling in Round Gravel Stratum and Its Control Technology

Recently, many studies have been conducted on the stratum deformation induced by earth pressure balance (EPB) shield tunneling in soft soil and sand. Movement laws vary largely among different strata. However, at present, relevant research mainly focuses on soft soil and sand, whereas little attention has been paid to the movement law of round gravel stratum with higher instability. In this study, a field monitoring test was carried out on the EPB shield machine when it passes through the round gravel stratum. Based on the analysis of monitoring results under different chamber earth pressures, thrust force, the torque of the cutter, grouting pressure, and grouting volume, the relationships between shield tunneling parameters and their influence on the disturbance of the surrounding soil mass were investigated. It was found that the surface deformation shape of the monitoring section of the south and north lines conforms to the Gaussian curve. The vertical deformation of the stratum at the tunnel axis is the largest. The maximum value is observed when the cutter head reaches the monitoring section. The horizontal deformation reaches a maximum value at the stage of the shield tail pass section. The strata deformation is not only related to the strata properties but also has a strong positive correlation with the shield tunneling parameters. The chamber earth pressure is the main factor affecting the stratum deformation before the arrival of the cutter head, and the grouting volume is the main factor affecting the strata deformation during the stage of the shield tail pass section.

DEM-continuum mechanics coupling simulation of cutting reinforced concrete pile by shield machine

Based on the discrete element method (DEM) - continuum mechanics coupling method, a numerical simulation analysis is carried out to model cutting some existing bridge piles that have invaded Beijing Metro Line 12. Firstly, the macroscopic parameters of the reinforced concrete pile and the soil stratum where the shield tunneling machine traversed are calibrated using uniaxial compression and Brazilian test through a series of numerical tests. In this paper, the procedure of building up a DEM-continuum mechanics coupling model is presented, then the model is applied to simulate the process of cutting the pile foundation using the earth pressure balanced (EPB) shield machine. The influences of different advancing parameters on the displacement of the pile bottom, the thrust force, and the torque of the EPB shield machine are investigated. The simulation-calculated results, such as thrust force and torque of the shield machine, are in good agreement with the theoretical method in previous studies and the corresponding monitored data in the field. Finally, a method based on the thrust of a single cutter is proposed to improve the theoretical model so that it can consider the effects of cutting bridge piles.

Soil disturbance induced by EPB shield tunnelling in multilayered ground with soft sand lying on hard rock: A model test and DEM study

A large scale model test and numerical simulation using three dimensional discrete element method (3D DEM) were carried out in parallel to study the soil disturbance induced by earth pressure balanced (EPB) shield tunnelling in multilayered ground with soft sand lying on hard rock. The model test used a miniature EPB shield machine which could fully reproduce the real tunnel construction of excavation and support. The DEM model simulating the model test was developed to capture the microscopic mechanisms of ground deformation. The surface and subsurface settlement were closely recorded in model test and compared with those of homogeneous ground to clarify the influence of underlying rock on the movement of overlying sand. The volume ratio of rock to sand in excavated muck was closely recorded in DEM simulation to quantitatively analyse the over excavation of soft sand. Results show that both the surface and subsurface settlement trough in multilayered ground are narrower than those in homogeneous ground, while the subsurface settlement in multilayered ground is larger than that in homogeneous ground. The width parameter of settlement trough decreases nonlinearly along the gravitational direction. The over excavation of overlying soft sand is influenced by the ratio of hard rock to tunnel cross section and the rotating speed of shield cutterhead.

Prediction of shield machine posture using the GRU algorithm with adaptive boosting: A case study of Chengdu Subway project

Shield machine deviation from the design tunnel axis (DTA) causes dislocation and damage of the segments and may lead to poor tunnel quality, which is a primary concern in tunnel construction. Therefore, it is necessary to predict the shield machine posture dynamically and assist the operator in adjusting the tunneling parameters in advance. Based on the tunneling data of five earth pressure balance (EPB) shield machines, a novel method for predicting shield machine posture, mainly composed of adaptive boosting (AdaBoost) and gated recurrent unit (GRU) algorithms, is proposed in this paper. In parallel, a data preprocessing algorithm is developed for the original tunneling parameters, including three phases: data extraction, data compilation, and data normalization. The hyperparameters of the model were determined using the grid search and cross-validation technology. The actual deviation case test shows that once the model predicts that the shield machine posture will deviate significantly from DTA, it can issue a warning in advance and assist the machine operators in optimizing tunneling parameters for a better trajectory. Then, the model prediction results were compared with the benchmark algorithms. The results reveal that the GRU algorithm is conductive to capture the trend of the time sequence, and the AdaBoost algorithm is beneficial for improving the fitting ability of the regression model. Finally, we found some association rules of tunneling parameters that affect the posture of shield machine.

Quantitative Evaluation of the Adaptability of the Shield Machine Based on the Analytic Hierarchy Process (AHP) and Fuzzy Analytic Hierarchy Process (FAHP)

Tunnel engineering based on the shield method is an extremely complex project. During the construction process, many uncertain factors are often faced, which makes it difficult to effectively and quantitatively evaluate the effectiveness of the shield machine. To solve this problem, this paper proposes an adaptability evaluation method for shield machines based on the fuzzy analytic hierarchy process (FAHP) and analytic hierarchy process (AHP). First, the selection and equipment matching of Earth pressure balance shield machines in the shield interval between Tashuiqiao Station and Erxianqiao Station of Chengdu Metro Line 17 are introduced. Then, using APH for screening, the final evaluation indices of the adaptability of the shield machines in this project are determined. Next, referring to the existing research results and fuzzy mathematics method, the membership function of the evaluation indices and adaptability evaluation model of the shield machine are constructed. Finally, the rationality and accuracy of the fuzzy comprehensive evaluation model of shield adaptability are verified through onsite shield construction, and the evaluation results are consistent with the actual situation.

Multi-Step Combined Control Technology for Karst and Fissure Water Inrush Disaster During Shield Tunneling in Spring Areas

Shield tunneling in highly fractured karst water-rich conditions easily results in water inrush disaster or even causes the roof of the karst caves to collapse. Severe water inrush disasters have occurred during the EPB (earth pressure balance) shield machine of the Jinan Metro Line R1 advanced through a karst and fissure groundwater-rich limestone ground in the spring area. To cope with the extreme water inrush risk, a multi-step combined control technology was put forward. First, a detailed geological exploration was carried out by ahead geophysical prospecting using high-density resistivity method, geological radar, etc., and geological borehole drilling was conducted from the ground surface before excavation. As a result, the distribution orientation, size, fissure development degree, and water inflow channel within the surrounding rock of the karst caves were detected. Second, multi-step grouting was performed to reinforce the surrounding rock, including pre-grouting treatment and filling rock blocks to the big karst caves from the ground surface, multiple grouting with a small amount of inert slurry each time inside the tunnel, and secondary circumferential hoop grouting at the shield tail. Third, the tunneling process was optimized, including optimizing the tunneling parameters, making full use of the air-pressurized tunneling technology of the EPB to press bentonite into the fractures around the excavation cabin to seal the fissure water, and using the drainage system of EPB and muck improvement technology to reduce the water inrush disaster. Meanwhile, shield protection slurry technology is applied to cutter inspection and replacement in the pressurized chamber under dynamic water flow environment of the spring terrain. The practice shows that the water inrush on the tunnel face is obviously alleviated after the shield machine advanced into the grouting area. According to statistics, the water inflow on the tunnel face decreases from about 4 m3/h before treatment to less than 0.3 m3/h after the abovementioned control, and the water seepage between the segmental linings reduces to almost zero. The average advance rate increased from 3 m/day without stopping or even zero when the shield machine needs to shut down 2–3 days for drainage to about 6 m/day. In addition, the treatments prevented the shield machine from jamming and the head descending disaster. This study provided a reliable control method for shield tunneling through the karst and fissure water-rich area and played an essential role in protecting the spring water.

Prediction of Shield Machine Attitude Based on Various Artificial Intelligence Technologies

The shield machine attitude (SMA) is the most important parameter in the process of tunnel construction. To prevent the shield machine from deviating from the design axis (DTA) of the tunnel, it is of great significance to accurately predict the dynamic characteristics of SMA. We establish eight SMA prediction models based on the data of five earth pressure balance (EPB) shield machines. The algorithms adopted in the models are four machine learning (ML) algorithms (KNN, SVR, RF, AdaBoost) and four deep learning (DL) algorithms (BPNN, CNN, LSTM, GRU). This paper obtains the hyperparameters of the models by utilizing grid search and K-fold cross-validation techniques and uses EVS and RMSE to verify and evaluate the prediction performances of the models. The prediction results reveal that the two best algorithms are the LSTM and GRU with EVS > 0.98 and RMSE < 1.5. Then, integrating ML algorithms and DL algorithms, we design a warning predictor for SMA. Through the historical 5-cycle data, the predictor can give a warning in advance if the SMA deviates significantly from DTA. This study indicates that AI technologies have considerable promise in the field of SMA dynamic prediction.

Time-series prediction of shield movement performance during tunneling based on hybrid model

This study presents a hybrid model based on the particle swarm optimization (PSO) algorithm and a long short-term memory (LSTM) neural network. PSO can determine the hyperparameters for the LSTM neural network. Using this approach, a framework for automatic data collection and application of the developed model during tunnel excavation was explored. The proposed model includes three stages: (i) data collection and pre-processing, (ii) hybrid prediction model establishment, and (iii) model performance validation. Pearson correlation coefficient is adopted to analyze the relationships between the influential factors and predicted object, which aids in feature selection for the developed model. A total of 1500 data sets, from a tunnel construction case in Shenzhen, China, were collected for training and testing the hybrid model. The results showed that the hybrid model with all the influential factors yielded the best performance. Thus, the developed model can provide a guideline for coping with measured data from an automatic monitoring system in earth pressure balance shield machines.

A Data-Driven Method for Predicting the Cutterhead Torque of EPB Shield Machine

The prediction of cutterhead torque of earth pressure balance (EPB) shield machine is mainly studied. First, the idea of shield tunneling stage division is proposed. The process of shield tunneling from start to stop (or pause) is divided into start-up and stationary driving stages. Using the change point detection method based on linear regression, the separation points between start-up stage and stationary driving stage are identified from the original construction data, and the datasets of the two stages are extracted, respectively. Then, for the start-up stage, the linear regression method is suggested for the cutterhead torque prediction, since there is a strong linear correlation between the key parameters such as the cutterhead torque and the thrust force. Meanwhile, for the stationary driving stage, considering the fact that the key parameters vary smoothly and show obvious inertia, the long short-term memory (LSTM) network method can be used to establish the relationship model between cutterhead torque and other key parameters, such as the thrust force. Through the test experiments of construction data in Zhengzhou, Luoyang, and Dalian shield projects, the results show that the proposed segmented modeling method possesses good adaptability and the cutterhead torque prediction model has high prediction accuracy.

Study on Penetration Damage Caused by Leakage of Earth Pressure Balance Shield Machine Tail Skin in Water-rich Silty Fine Sand Stratum

In order to study the principle of stratum seepage damage caused by shield tail leakage during the EPB shield tunneling in water-rich silty fine sand stratum, a targeted-designed device is used. The results of this research are as follows: (1) The soil loss after leakage could be divided into three stages: initial, rapid growth, and destruction. Besides, the proportions of water leakage and sand leakage in these stages are significantly different; (2) The process of stratum seepage damage caused by tail skin leakage is divided into two stages: the first stage is the formation of subsurface cavities, and the second stage is the instability and destruction of subsurface cavities; (3) When the leakage point is under the tunnel, two flow areas were formed toward the leakage point. When the leakage point is above the tunnel, one flow area is formed at the crown area of the tunnel. Based on the test results, in the actual project, the seepage damage stage and the development of subsurface cavities can be judged based on the amount of water and soil leakage to provide a certain basis for construction risk control and emergency disposal.

Study of Grease Escape of Tail Skin Sealing System with Earth Pressure Balance Shield Machine

In this paper, the grease escape test of shield tail sealing system is carried out, and the variation law of grease escape pressure and escape rate is studied with shield tail clearance, grease cone penetration and grease pressure as variables. The results show: (1) The smaller the shield tail gap, the greater the grease escape pressure, and the grease escape pressure has a non-linear relationship with the shield tail gap. The higher the grease cone penetration, the lower the grease escape pressure under the same shield tail gap. (2) When the grease pressure is greater than the escape pressure, the escape rate of sealing grease increases with the increase of grease pressure under the same shield tail clearance. (3) In the range where the grease pressure is greater than the grease escape pressure and less than the grease resistance pressure, the grease escape rate is linearly related to the grease pressure under different working conditions. (4) There are two escape modes of grease: non-uniform escape and uniform escape.

Prediction of the Amount of Soil Discharged by an Earth Pressure Balanced Shield Machine Based on Feature Engineering

Prediction of the Amount of Soil Discharged by an Earth Pressure Balanced Shield Machine Based on Feature Engineering