Search

• VAE-CNN architecture manages TBM data dynamics for sinkhole event monitoring. • Offline modeling trains the proposed method with sinkhole absence data. • Online monitoring validates the proposed method to detect sinkhole occurrences. • SVI counts isolate critical variables that mostly affect ground stability. • The proposed VAE-CNN achieved a 100% detection rate and 0.9% false alarm rate. This study introduces a real-time unsupervised monitoring framework for monitoring sinkhole formation events during earth pressure balance (EPB) shield tunneling operations. A feature extractor (FE) is constructed by coupling variational Autoencoders structure with convolutional neural network layers (VAE-CNN) to manage the complexity of EPB operational data, including non-linearity and temporal dependencies. The monitoring framework consists of two main phases: offline modeling and online monitoring. In the offline modeling phase, an FE model is trained using data-intensive techniques to define a subspace characterizing the behavior of multivariate data without sinkhole formations. The squared prediction error (SPE) statistics and the control limits are computed for detection. During the online monitoring phase, unseen EPB data is propagated to generate SPE values and determine sinkhole events based on whether these values surpass the control limit. Sensor validity index violation counts were used to isolate the most influential variables, while the results demonstrated the superiority of the proposed VAE-CNN method, achieving a 100% detection rate and a 0.9% false alarm rate. The influential variables identified include cutter resolutions per minute, jack speed, screw pressure, torque, and cutter seal components. The monitoring system shows great potential for early warnings during EPB operations to mitigate sinkhole formation risks. [ABSTRACT FROM AUTHOR]

It is easy to cause safety accidents due to the low precision and poor effect of earth pressure balance (EPB) control during shield machine tunneling process at present. So a data-driven optimization control method for earth pressure balance in sealed cabin of shield machine is proposed. Firstly, the earth pressure prediction model of four pressure monitoring points in the sealed cabin is established by using least squares support vector machine (LSSVM) method, and the penalty coefficient C and kernel parameters σ are optimized by particle swarm optimization (PSO). Then, an optimization function is established with the minimum sum of multi-point earth pressure prediction errors as the target. The optimal solution is obtained by using the fruit fly optimization algorithm (FOA) to solve the optimal screw conveyor speed, so as to realize the balance control of the earth pressure in sealed cabin. Finally, the simulation experiments are carried out based on field construction data. The results show that the method has great performance such as higher accuracy of calculation and better control effect, which can control the excavation face of shield machine more steady. [ABSTRACT FROM AUTHOR]

Mass Rapid Transit Jakarta (MRTJ) phase 1 tunnel construction using the earth pressure balance method has been completed and surface settlement and lateral displacement data according to elevation and inclinometer readings has been collected to evaluate the effect of tunnel's construction on surrounding infrastructure. Soil stratification along the research area, defined according to boring logs and soil parameters for the hardening soil model (HSM) and the soft soil model (SSM), was determined by optimization of stress-strain curve fitting between CU triaxial test, consolidation test and soil test models in the Plaxis 3D software. Evaluation of the result of surface settlement measurements using an automatic digital level combined with geodetic GPS for elevation and position control points showed that the displacement behavior was affected by vehicle load and stiffness of the pavement. Lateral displacement measurements using inclinometers give a more accurate result since they are placed on the soil and external influences are smaller than surface settlement measurement. The result of 3D finite element modeling showed that surface settlement and lateral displacement during TBM construction can be predicted using HSM with 2% contraction. SSM and the closed-form solutions of Loganathan and Poulos are unable to provide a good result compared to the actual displacement from measurements. [ABSTRACT FROM AUTHOR]

During shield machine tunneling, the earth pressure in the sealed cabin must be kept balanced to ensure construction safety. As there is a strong nonlinear coupling relationship among the tunneling parameters, it is difficult to control the balance between the amount of soil entered and the amount discharged in the sealed cabin. So, the control effect of excavation face stability is poor. For this purpose, a coordinated optimization control method of shield machine based on dynamic fuzzy neural network (D-FNN) direct inverse control is proposed. The cutter head torque, advance speed, thrust, screw conveyor speed and earth pressure difference in the sealed cabin are selected as inputs, and the D-FNN control model of the control parameters is established, whose output are screw conveyor speed and advance speed at the next moment. The error reduction rate method is introduced to trim and identify the network structure to optimize the control model. On this basis, an optimal control system for earth pressure balance (EPB) of shield machine is established based on the direct inverse control method. The simulation results show that the method can optimize the control parameters coordinately according to the changes of the construction environment, effectively reduce the earth pressure fluctuations during shield tunneling, and can better control the stability of the excavation surface. [ABSTRACT FROM AUTHOR]

Earth pressure balance tunnel boring machines (EPB TBMs) were successfully used for tunnel excavation in loose grounds. Determining the minimal support pressure in the tunnel face is one of the most critical steps in tunneling by the earth pressure balance method. This study aimed to investigate the tunnel face stability of the Dez–Ghomrood water transfer tunnel analytically and numerically. During the water transfer tunnel project from Dez to Ghomrood, a very weak rock mass similar to an alluvial zone was encountered. Considering the depth of the tunnel and also the layering of the ground, calculating the proper support pressure of the tunnel face was significantly complex. The analytical method was based on the slope of layers relative to the tunnel face and the limit equilibrium of forces. Numerical analyses were conducted based on three-dimensional finite-element simulations using the PLAXIS 3D tunnel. The results demonstrate that the formation of soil arching yields to the curvilinear distribution of the weight of upper levels, therefore, pressure reduction at the tunnel face. The geomechanics parameters of the ground, shield geometry, and ground convergence in the excavated section are the determining factors in calculating the support pressure of the tunnel face. The slope of ground layers should also be considered in the tunnel face failure mechanism and in support pressure. The operational support pressure is compared to the analysis results, and the good accuracy of the method is confirmed. [ABSTRACT FROM AUTHOR]

• A precise DEM model of shield tunneling incorporating cutter-soil interactions was introduced. • Using particle velocity as a predictive indicator for excavation face instability. • Ground subsidence is time-delayed. • Determining the limits of support pressure. Shield construction plays a crucial role in the development of underground infrastructure. However, as a complex engineering process, it can lead to excavation face instability and surface subsidence. This paper presents a detailed investigation into the mechanisms influencing excavation face instability and surface subsidence of sand cobble stratum during shield construction using the discrete element method (DEM). Through a combination of numerical simulations and experimental analyses, the impact of various parameters, including support pressure, and cutters on the stability of the excavation face were explored. The results reveal that the presence of cutters significantly enhances particle fluidity but weakens the stability of the excavation face, necessitating a higher ultimate support pressure. Furthermore, the study highlights the distinct behavior of surface subsidence compared to excavation face instability. Surface subsidence exhibits a delayed manifestation, even when soil overflows into the shield machine. This finding underscores the importance of diligent monitoring and control of cabin pressure during shield construction. The findings provide valuable insights into the intricate dynamics of shield construction and offer practical recommendations for minimizing excavation face instability and surface subsidence. [ABSTRACT FROM AUTHOR]

Background: Earth pressure balance shield machines are widely used in underground engineering. To prevent ground deformation even disastrous accidents, the earth pressure in soil chamber must be kept balance to that on excavation face during shield tunneling. Therefore, in this paper an advanced control strategy that a least squares support vector machine model-based predictive control scheme for earth pressure balance is developed. Methods: A prediction model is established to predict the earth pressure in chamber during the tunneling process by means of least squares support vector machine technology. On this basis, an optimization function is given which aims at minimizing the difference between the predicted earth pressure and the desired one. To obtain the optimal control actions, an improved ant colony system algorithm is used as rolling optimization for earth pressure balance control in real time. Results: Based on the field data the simulation experiments are performed. The results demonstrate that the method proposed is very effective to control earth pressure balance, and it has good stability. Conclusion: The screw conveyor speed and advance speed are the major factors affecting the earth pressure in chamber. The excavation face could be controlled balance better by adjusting the screw conveyor speed and advance speed. [ABSTRACT FROM AUTHOR]

Knowing the as-encountered geology during mechanized TBM tunneling is important for machine operation and contractual dispute resolution. However, ground condition estimated before excavation can be locally highly inaccurate. One solution is to characterize the ground directly from tunnel boring machine (TBM) data with data-driven models, assuming there exists unique relationships between TBM behavior and the changing ground. Only supervised-learning models trained exclusively with TBM data obtained near boreholes, where the true geology is known, have been used. Due to borehole sparsity, such training data is limited in quantity, especially at the beginning of excavation, undermining the model performance and delaying its deployment during tunneling. This paper proposes a semi-supervised learning model capable of using TBM data both with and without borehole information, relying on the principle of "guilt by association". Using the Seattle Northgate Link Extension tunneling project for case study, the proposed model is shown to outperform popular SL models – multilayer perceptron, multinomial logistic regression, random forest and sparse autoencoder neural networks – both in fitting the borehole data, as well as in inferring the heterogeneous ground profile with many irregular geological interbeddings and shifts of geological transitions identified. The proposed SSL model performs significantly better than SL models when given limited boreholes for training, making it more effective for use during tunneling. [ABSTRACT FROM AUTHOR]

During the process of shield excavation, the pressure unbalance of excavation surface may easily cause the collapse or blow-out of ground surface, which may lead to disastrous accidents. Since the change of chamber earth pressure is closely related to the pressure of excavation surface, the accurate prediction and control of chamber earth pressure is one of key technologies for avoiding the pressure unbalance of excavation surface effectively. In order to establish the prediction model of chamber earth pressure, the relationships between earth pressure and excavating parameters, especially the influence of cutter torque on earth pressure, were analyzed in detail. On this basis, the new input and output parameters of earth pressure model were determined. Then, according to the data of pressure sensors on the clapboard, a prediction model of earth pressure was established based on the least squares support vector machine (LSSVM). And based on the prediction model, by minimizing the deviation between four predicted earth pressures and setting values, the particle swarm optimization (PSO) was adopted to optimize the control parameters, therefore, the online balance control of earth pressure was realized. Finally, in order to verify the validity and accuracy of prediction model, some simulation experiments and comparative analyses were carried out by using on-site construction data. The proposed method provides a technical support for the accurate prediction and control of chamber earth pressure and the safety in excavating process. [ABSTRACT FROM AUTHOR]

This paper combined data-driven modeling and optimal control for performance enhancement of earth pressure balance tunnel boring machine (EPBM). Two coupled processes, EPBM advance rate (AR) and cutterhead rotation torque, are modeled using support vector regression (SVR). An optimal control framework was formulated to maximize the AR, solved with particle swarm algorithm. Using the Seattle N125 project as case study, it is found the SVR model can predict EPBM AR with R 2 = 0.90, normalized root mean square error (nRMSE) = 0.30 and mean absolute percentage error (MAPE) = 31.2%, and R 2 = 0.65, nRMSE = 0.59 and MAPE = 6.7% for torque prediction. Compared to human operator, EPBM with optimal control can increase AR by 0.6–23.3 mm ∕min on average, accompanied by an average torque reduction of 83.1 kN - m. It is found higher cutterhead rotation and lower chamber pressure always contribute to faster tunneling, but the optimal total thrust force to apply depends on the chamber pressure. • Modeled EPBM tunneling advance rate and cutterhead rotation torque using data-driven method with physical guidance • Visualized and interpreted the influence of each EPBM operation to advance rate and torque. • Established a general optimal control formulation for EPBM tunneling performance enhancement. • Used the Seattle N125 tunneling project as a case study to demonstrate the expected improvement with optimal EPBM control. [ABSTRACT FROM AUTHOR]

To ensure security during the excavation process of an earth pressure balance shield, this paper presents an optimal control method that accounts for the tunnel face's stability. The tunnel face is controlled by an optimal screw conveyor speed derived from the particle swarm optimization algorithm for a designed stable normal vector angle range on the distribution surface of the chamber pressure field. These normal vector angles can be computed online by measuring the changes to the earth pressure in the shield's chamber using a BP neural network model of the chamber pressure field distribution. An experimental example that uses excavation data from an actual EPB shield is given to illustrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Highlights: [•] The discrete element model of cutterhead system tunneling is presented. [•] The performance indicator of the cutterhead system is defined and measured in the DEM model. [•] The model can be used to forecast the system performance and optimize the system structure. [Copyright &y& Elsevier]

In order to control the earth pressure balance more accurately and efficiently, a new modeling method for control the earth pressure in pressure chamber was proposed. Based on the in-site construction data eliminating the noise by using the wavelet threshold denoising method, an earth pressure field model of the pressure chamber was established by using least square method; on this basis, by analysing the relationship between tunneling control parameters and the earth pressure in chamber and the impact factor of the earth pressure states change, the EPB control model was established which takes the equivalent earth pressure as control target. The fuzzy adaptive PID controller was designed and the EPB control system was constructed. Finally, the simulations were given to illustrate the effectiveness of the earth pressure control model, which lay a foundation for the shield EPB control. [ABSTRACT FROM AUTHOR]

Abstract: To avoid ground deformation in the process of earth pressure balance (EPB) shield tunneling, it is necessary to keep the earth pressure balance on excavation face. However, at present the earth pressure control depends mainly on operation experiences which is hysteretic and could result in slow response to the change of earth pressure. To solve these problem, a predictive control strategy for earth pressure balance during excavation is proposed in this paper, where an earth pressure prediction model taking advance speed and screw conveyor speed as the control parameters is established by means of least squares support vector machine (LS-SVM). Further, by minimizing the difference between the predicted earth pressure and the desired one, an optimization model of the control parameters is established, and solved by the particle swarm optimization (PSO) algorithm. Therefore, an optimal EPB control scheme for shield tunneling automatically is presented here. The simulation results demonstrate that the method presented in this paper is very effective to control earth pressure balance. [Copyright &y& Elsevier]

• According to the slump value and its water contents, the natural sandy pebble soil in Beijing area can be divided into three groups of dry, lower water content, high water content. • The flow plasticity of sandy pebble soil is highly sensitive to water content. Therefore, it is necessary to develop the corresponding optimization soil conditioning scheme according to the water content of different soil groups before the shield tunneling. • For the dry sandy pebble soil (W < 5%), the ideal addition ratio of bentonite slurry is 7%, while that of foam is 40–50%. For the low water content sandy pebble soil (5% < W < 9%), the ideal addition ratio of bentonite slurry is 7%, while that of foam is 5% to 15%. For the high water content sandy pebble soil (W > 9%), it is necessary to first add appropriate amount of polymer solution to reduce water, and then inject a certain amount of foam to improve the soil flow plasticity. During the construction of the interconnection tunnel from Tianqiao Station to Yongdingmen Station of Metro Line 8 in Beijing, the Earth Pressure Balance (EPB) shield machine had to excavate in sandy cobble soil. Because the sandy cobble soil has varying moisture content along the tunnel route and shows the characteristics of loose particle structure, large pores and no cohesion between the cobble particles, it is difficult to stabilize the support pressure acting on the cutting face and transport the muck. To effectively and efficiently use the EPB tunnelling in such situations, a series of laboratory tests on conditioning the sandy cobble soil to a reasonable quality were conducted, and the influence of water content and additive amount on the conditioning effectiveness was studied. Based on the test results, the optimal soil conditioning schemes corresponding to the water content of different soil groups were proposed. Finally, the laboratory test results were used to guide the soil conditioning in the field and the measured field data showed that the conditioned material fulfills the required standard for an EPB application. [ABSTRACT FROM AUTHOR]

• Physics-based model for (1) Compressible material flow and (2) Fluid seepage. • Considered muck's void-, and hence pressure-, dependent behavior. • Simplified model capable of running in real-time, suitable for simulator use. • Case study using the North Link Extension tunneling project data for demonstration. This paper presents a simplified excavation chamber pressure model for earth pressure balance shield tunnel boring machine (EPBM) tunneling in granular soils, capable of predicting chamber pressure response during both excavation and standstill periods. Two physical processes, (1) compressible material flow, and (2) chamber fluid seepage, are modeled. The chamber pressure model is physics-based and is built upon chamber muck mass conservation. The model assumes muck behavior to be pressure-dependent and quasi-static. Given recorded EPBM operations, including advance rate, chamber additive injection rates and screw conveyor rotation speed, the model can predict the chamber pressure fluctuation with good accuracy, both during excavation and standstill periods. A case study using tunneling project data is included, where the model's capability to simulate chamber pressure evolution during excavation of a single ring and multiple consecutive rings is demonstrated. [ABSTRACT FROM AUTHOR]

• Numerical models for muck transport in different EPB chamber designs established. • The chamber design has a strong influence on pressure fluctuations. • Larger levels of yield stress and viscosity lead to a larger pressure unbalance. • Smaller muck compressibility and high pressure levels lead to higher fluctuations. • Pressure drop at the screw conveyer entrance may propagate to the tunnel face. Earth Pressure Balance (EPB) shield machines are widely used in mechanized tunneling operations in soft grounds. In contrast to slurry shield machines, the pressure distribution in EPB excavation chambers is not well undersood, as it is influenced by the muck properties and the chamber design. A computational model specifically developed in Dang and Meschke (2018) for the numerical simulation of material transport in EPB pressure chambers is employed to investigate the pressure distribution in two different types of EPB chambers, characterized by a different design of the mixing components, the rotators and the screw conveyor. The numerical model allows for the description of all rotating and fixed components of the EPB chambers including the screw conveyor and considers adequately the compressibility and the consistency of the soil paste. The spatio-temporal pressure distribution is investigated with respect to the influence of chamber design and the properties of the soil paste. Essential characteristics of the pressure distribution, such as the pressure unbalance between the left and right side and pressure fluctuations observed in in situ measurements are captured by the numerical analyses. The key factors influencing the pressure unbalance and pressure fluctuations are identified by parametric studies for two different EPB chamber designs. [ABSTRACT FROM AUTHOR]