Search

Copyright of Construction Machinery & Equipment is the property of Construction Machinery & Equipment Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This dissertation presents a development of an integrated framework of artificial intelligence (AI) systems for earth pressure balance (EPB) tunnel boring machine (TBM) tunneling. The framework is constructed based on the feedback loop control system. The AI systems are developed using machine learning algorithms and structured to follow the human cognitive model, i.e., sensing, perceiving, and decision-making. The development of the systems is conducted in three parts.The first part discusses the characteristics of TBM data and the effects of data preparation on data-driven models. This is achieved by (i) proposing a knowledge-based EPB TBM feature taxonomy and (ii) investigating the effects of data aggregation and feature selection on prediction models. The investigation shows that models developed using different data aggregation levels produce comparable prediction trends and similar feature importance rank in the conditions of sufficient observations and predictors. However, models with a coarser aggregation level may appreciate higher prediction performance due to the lower variance. The investigation also shows that the knowledge-guided TBM feature selection offers benefits over embedded machine learning-based feature selections. The developed model can produce relatively consistent feature importance in different tunneling cases, indicating better generalizability of the model. The second part proposes AI systems that perceive tunneling environments in real-time based on the streams of sensor data during tunneling operation. This is achieved by developing (i) a supervised AI system to interpret the encountered geologic conditions, (ii) an unsupervised AI system to detect the encountered geologic anomalies, and (iii) a supervised AI system that connects TBM data to the ground monitoring data and estimates tunneling-induced ground movements. The proposed geologic interpretation system uses either Random Forests (RF) classification or regression algorithms to infer the geologic transitions along the tunnel alignment. The proposed geologic anomaly detection system combines Principal Component Analysis (PCA) to project the data into a lower dimension space and Local Outlier Factor (LOF) to measure the degree of the anomaly of the projected data points. The proposed tunneling-induced ground movement estimation system uses RF regression to approximate any shape of ground movements solely based on TBM operation data and tunnel spatial geometries without prior assumptions on the ground movement shape, geologic material parameters, and the expected ground loss. The third part proposes AI systems that model tunneling and its decision-making processes. This is achieved by introducing (i) a combination of probabilistic graph modeling and structure learning algorithms as a tool to systematically explore the causal effect interactions contained in TBM operation data and (ii) a multi-output supervised AI system to determine multiple steering control parameters simultaneously and steer the TBM along the tunnel alignment. The study shows that Bayesian Network Structure Learning (BNSL) can potentially be used to model the interactions of human operator decisions, TBM behaviors, and ground conditions in an integrated representation. The study also shows that the multivariate Random Forest (MRF) algorithm can concurrently make multiple decisions on TBM steering control parameters during driving. This dissertation has demonstrated that TBM data contain valuable information that can be extracted to benefit tunneling operations. Due to the complex relationships within the data, the nonlinear and nonparametric machine learning models offer advantages over the conventional linear and parametric models. This development is envisioned to be a building block that advances the development of autonomous TBM technology.

During earth pressure balance (EPB) shield tunnelling in sandy ground, not only foam but also other conditioning agents need to be injected to reduce the permeability of muck and avoid water spewing out of the screw conveyor. Permeability tests were carried out to study the permeability characteristics of conditioned sand under high hydraulic gradients. A low bentonite slurry injection ratio (BIR) enhanced the workability of foam-conditioned sand. As the hydraulic gradient increased, the initial permeability coefficient of conditioned sand increased, and the initial stable period became shorter or disappeared. The BIR had a more significant effect on the permeability of conditioned sand than the foam injection ratio (FIR), and this effect gradually weakened as the hydraulic gradient increased. The initial permeability coefficient of the foam–bentonite slurry-conditioned sand decreased by approximately an order of magnitude compared with that of the foam-conditioned sand. With the addition of bentonite slurry, suitable sand conditioning can accept a higher water content (w) and lower FIR, resulting in suitable ranges of w and FIR that are more flexible. Finally, the mechanism of stabilizing foam under the action of bentonite slurry was discussed by considering the interaction between foam bubbles and fine particles.

Surface settlements caused by twin tunneling are a major interest in underground space engineering. Most prevailing studies have investigated the surface settlements observed over twin tunnels constructed in clay. Yet, less attention is given to the twin tunnels excavated in silty sand, which is the focus of this study. A comprehensive field monitoring scheme was designed in the Hangzhou metro line six project to measure the surface settlements during twin tunneling by adopting earth pressure balance shields. The influence of four shield operational parameters, namely, face pressure, tail grouting pressure, penetration rate, and pitching angle on the surface settlements due to twin tunneling are explored. In general, the total settlement profiles observed over twin tunnels follow an inverted bimodal shape. The post-settlement observed over the 1st tunnel due to the 2nd tunnel excavation is non-trivial when the twin tunnels are spaced closely. Low face pressure and tail grouting pressure can induce excessive peak surface settlements during twin tunneling in silty sand.

Conducting tunneling construction at any depth causes deformations of the earth's surface and, as a result, additional movements of the surrounding buildings, as well as changes in the stress-strain state of the ground mass. When modeling the site of work to assess the impact of the construction of tunnels, it is necessary to take into account the volume loss of soil. The purpose of this work is to determine the technological parameter with further averaging and application in the design of dispersed soils. The article considers the impact on buildings from the construction of a two-track tunnel from the «Kosino» station to the «Yugo-Vostochnaya» station in Plaxis in a two-dimensional and three-dimensional with a design volume loss of soil of 1.5 %. The construction of the tunnels was carried out by a shield with earth pressure balance with a cutting diameter of 10.8 m. The maximum depth of the tunnel from the ground surface is about 27.0 m, the construction site is dominated by dispersed soils. For the considered section of the construction of the distillation tunnel, the calculated volume loss of soil for the two-dimensional problem varies in the range from 0.32 to 0.41 %, for the spatial problem - from 0.52 to 0.78 %. With the same additional draft of the building, there is a percentage increase from 62 to 90 % between the calculated parameters obtained in the schemes in both settings. Taking into account the calculated volume loss of soil at the design stage, obtained from the results of this article, in similar engineering and geological conditions, contributes to the rational distribution of funds, reducing the volume of geotechnical monitoring and measures for the preservation of buildings in compliance with the required standards and safety regulations.

Recent years have witnessed several accidents associated with tunnel face failure in cobble-rich soil in the city of Chengdu, China. Due to its lack of cohesion, cobble-rich soil can be easily disturbed by shield tunneling. Based on the general conditions of the Chengdu Metro Line 1 project, the mechanisms of face failure of tunnels in cobble-rich soil driven with earth pressure balance (EPB) machines are studied. Specifically, we present results of tests carried out using a laboratory reduced-scale model of EPB tunneling operations in cobble-rich soil. The failure kinematics and limit face pressures are presented and analyzed. Then a three-dimensional (3D) discrete-element method (DEM) model, which is able to simulate the main EPB excavation processes is employed to gain further insight into the mechanisms of face failure in cobble-rich soil. Comparisons of these results with the observations based on previous studies are discussed. The results reveal a fundamentally different tunnel-face failure mechanism in cobble-rich soil in contrast with that in clayey or sandy soils. It shows that the ground movement during face failure is sudden in cobble-rich soil, which is different from the progressive mechanism in frictional–cohesive materials. The observed sinkhole at surface takes the shape of an oval, and the failure zone behind tunnel face extends almost as far as that ahead of the face, which is different from the observations in previous studies. The failure zone is found to be wider than that of sandy soils in both the transverse and longitudinal directions.

Metro tunnel construction under high-density urban areas always poses the challenge of ground settlement which should be well predicted so that necessary precautions can be taken. An underground Metro line case study from Iran is used for the investigation. In this paper, an attempt has been made to predict ground settlement using available empirical and analytical methods. Significance of correctly estimating the parameters especially volume loss has been discussed. A numerical model is developed using the finite-difference-based numerical code FLAC3D to simulate tunnel construction using earth pressure balance shield tunnel boring machine (EPBM). The stage by stage construction sequence and EPBM parameters are simulated in this model. The ground settlement behaviour as the tunnel advances is presented as displacement contours and profiles. A critical comparison has been made among all methods used to predict the ground movement for the current case study. It was concluded that empirical and analytical methods are effective only if associated parameters like volume loss can be correctly ascertained. The numerical model was found to be the most reliable and useful tool for ground settlement prediction.

The ground loss caused by earth pressure balance (EPB) shield tunneling is a serious threat to the safety of ground and underground buildings. The amount of soil discharged is a direct factor causing the ground loss, but the feedback of the amount of soil discharged has the problems of human subjectivity and information lag. Based on the theory of soil discharged and shield construction data, a data model for predicting the amount of soil discharged is constructed, and a predictive method of soil discharged based on adaptive adjustment strategy and parameters to achieve optimal regression is proposed. Taking Changzhou shield tunnel construction project as an example, through comparative analysis, the main influencing factors of soil discharge data model are screw-conveyor torque, screw-conveyor revolutions, total thrust, screw-conveyor entrance earth pressure, the revised standard penetration test blow-count, and compression modulus. The results show that the mean absolute error (MAE) of the model is 0.911 m3, and the mean absolute percentage error (MAPE) is 2.78%, which verifies the effectiveness of the prediction of soil discharged by feature engineering

Estimating surface settlement induced by excavation construction is an indispensable task in tunneling, particularly for earth pressure balance (EPB) shield machines. In this study, predictive models for assessing surface settlement caused by EPB tunneling were established based on extreme gradient boosting (XGBoost), artificial neural network, support vector machine, and multivariate adaptive regression spline. Datasets from three tunnel construction projects in Singapore were used, with main input parameters of cover depth, advance rate, earth pressure, mean standard penetration test (SPT) value above crown level, mean tunnel SPT value, mean moisture content, mean soil elastic modulus, and grout pressure. The performances of these soft computing models were evaluated by comparing predicted deformation with measured values. Results demonstrate the acceptable accuracy of the model in predicting ground settlement, while XGBoost demonstrates a slightly higher accuracy. In addition, the ensemble method of XGBoost is more computationally efficient and can be used as a reliable alternative in solving multivariate nonlinear geo-engineering problems.

This paper establishes an intelligent framework for real-time prediction of trajectory deviations in the process of earth pressure balance (EPB) tunnelling. A hybrid model was developed which integrates principal component analysis (PCA) and a gated recurrent unit (GRU). PCA was adopted to mine the interrelated input parameters and reduce the accompanying data noise. A scroll window mode was implemented in the GRU to predict the shield movement in real time. The proposed PCA–GRU model was implemented and validated through a case study of the Guang-Fo intercity railway in Guangzhou, China. Another three machine learning models were also used for comparison. The results revealed that the proposed model predicted the shield moving trajectory with higher precision than other models. The implications for trajectory regulation were discussed using field data. The proposed prediction framework represents a promising solution for real-time prediction of the shield moving trajectory in EPB tunnelling.

When a slurry shield tunnel boring machine (TBM) encounters sticky ground during tunneling, mud cakes often occur on the cutter head due to the high stickiness of soil. The mud cakes caused several negative issues, such as high torque demand, advancement rate reduction, and additional costs. Existing studies have largely focused on Earth pressure balance TBMs; research on formation and mitigation measures of mud cakes in slurry shield TBMs is limited. Therefore, this study proposes the addition of dispersant to the slurry to prevent mud cakes during the tunneling of slurry shield TBMs by reducing stickiness of excavated clay. The basic properties of slurry were measured experimentally, and the effectiveness of dispersant in reducing the potential for mud cakes was investigated through mixing tests and viscosity experiments. A statistical analysis of the data was performed to determine relationships between slurry properties and material behaviors. The results showed that the slurry with dispersant had a lower viscosity and formed filter cakes more quickly, thereby meeting the performance requirements of a supporting fluid for slurry shield TBMs. Further, dispersant effectively reduced the empirical stickiness ratio and suspension viscosity. Therefore, a slurry with an appropriate dispersant content could effectively reduce the potential for mud cake formation.

Deformation of ground during tunnelling projects is one of the complex issues that is required to be monitored carefully to avoid the unexpected damages and human losses. Accurate prediction of ground settlement (GS) is a crucial concern for tunnelling problems, and the adequate predictive model can be a vital tool for tunnel designers to simulate the ground settlement accurately. This study proposes relatively new hybrid artificial intelligence (AI) models to predict the ground settlement of earth pressure balance (EPB) shield tunnelling in the Bangkok MRTA project. The predictive models were various nature-inspired frameworks, such as differential evolution (DE), particle swarm optimization (PSO), genetic algorithm (GA), and ant colony optimizer (ACO) to tune the adaptive neuro-fuzzy inference system (ANFIS). To obtain the accurate and reliable results, the modeling procedure is established based on four different dataset scenarios including (i) preprocessed and normalized (PPN), (ii) preprocessed and nonnormalized (PPNN), (iii) non-preprocessed and normalized (NPN), and (iv) non-preprocessed and nonnormalized (NPNN) datasets. Results indicated that PPN dataset scenario significantly affected the prediction models in terms of their perdition accuracy. Among all the developed hybrid models, ANOFS-PSO model achieved the best predictability performance. In quantitative terms, PPN-ANFIS-PSO model attained the least root mean square error value (RMSE) of 7.98 and a correlation coefficient value (CC) of 0.83. Overall, the attained results confirmed the superiority of the explored hybrid AI models as robust predictive model for ground settlement of earth pressure balance (EPB) shield tunnelling.

The new Istanbul Airport is being constructed over an old coal field area, 35 km away from the city center. The construction of a rail link between the city and the airport entails the excavation of tunnels in the areas of complex geology, creating several problems for tunnel construction. This paper summarizes the effect of different grades of weathering of an interbedded sandstone-mudstone-siltstone sequence and transition zones on the performance of an earth pressure balance tunnel boring machine (EPB-TBM) during this work. The variation of EPB pressure, TBM thrust, torque, penetration, and specific energy values were analyzed in different lithologies and weathering zones and with respect to the attitude of transition zones between different materials. Normalized thrust and torque values considered in respect of penetration rate and EPB pressure showed that the attitude of transition zone on TBM performance is strictly dependent on the position of each geologic formation in the respect to the other, inclined or horizontal. To be specific, in an inclined transition zone, the thrust and torque values were almost double compared to the values obtained in a horizontal transition zone in the same lithology. This was probably due to increased over-break in inclined transition zones, which created loose material that accumulated in front of the cutter head. However, further case studies would be required definitely to confirm this. Mean normalized thrust and torque values were almost half in moderately/highly weathered sandstone compared to fresh/slightly weathered sandstone. The highest mean penetration of 28 mm/rev and mean lowest specific energy of 2.4 kWh/m3 were obtained in transition zone between claystone with silty sand and highly weathered interbedded sandstone-mudstone-siltstone. Due to impact effects, increased disc consumption was experienced where passage was made from low strength due to high strength formations, with up to one disc per 115 m3 of excavated material in the transition zones included in the study. The relatively high production rates were achieved, which attributed to a combination of logging daily the face conditions accompanied by appropriate adjustments of soil conditioning agents (FIR-foam injection ratio and FER foam expansion ratio values) and anti-clogging agents to control the sticking behavior of the spoil. The impact of different ground conditions on EPB-TBM performance in different projects is also discussed in relation to the results obtained in this study. It is believed that this research will help to manage better mechanized tunneling activities in similar conditions.

Soil conditioning is an important stage in shield tunnel construction that can effectively improve muck flow plasticity, reduce cutter head wear and improve tunneling efficiency, especially in sandy and cobbly soils. The aim of this paper is to obtain the optimal ratio of residue modifiers in sandy and cobbly soil and to improve the equipment used in residue-related shield machines. Residual soil in a sandy pebble layer was selected, and particles with sizes over 50 mm were removed to form soil samples. Through laboratory tests, the optimal ratio of the modifier was obtained, and the shield tunneling machine equipment was optimized. The research results for the laboratory tests and equipment optimization were verified and adjusted appropriately through field tunneling tests. The following results were obtained. 1) A 3% foaming agent C was selected for the soil conditioning tests. The final mass ratio of the bentonite mixed solution of water, bentonite, soda ash (Na2CO3), and carboxymethyl cellulose (CMC) was 6:1:0.028:0.035. 2) Improving earth pressure balance (EPB) shield machine equipment can improve the effects of soil conditioning. 3) Compared with the volume of residual soil, the optimal ratio of soil conditioning in sandy and cobbly layer was 13% water, 4–5% bentonite mixed solution and 12–15% foam. In addition, the maximum ratio shall be taken for the strata with poor grain composition. These results can be used to provide excavation guidelines for using an EPB machine under these soil conditions.

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.

Earth pressure balance (EPB) shield tunneling in a silty sand stratum is frequently faced with the wear of rotary cutter disc, clogging, or even collapse of workface due to its noncohesive and discrete properties of silty sand material. Soil conditioning is an effective way to reduce the discrete and friction properties of silty sand and to increase its rheology and fluidity, thus improving the cutting performance of EPB machines. However, soil conditioning materials were generally prepared and injected based on past limited field experiences or lab tests which were far from reality. In this article, a ground suitability test system for simulating shield tunneling in a conditioned ground was specially developed and used in a series of tests to investigate the influences of key factors of soil conditioning on the shield cutting performance. In addition, a field experiment of shield tunneling in silty sand of Wuhan Metro was conducted for verification. The major findings were obtained as follows. (1) The proposed test system performed well in simulating and assessing the cutting performance of EPB shield in conditioned soils, and the test results agreed well with the field test. (2) The soil conditioning materials can significantly reduce the cutting torque of shield tunneling in silty sand by up to 60%–70%. (3) The optimal foam and slurry parameters are suggested in the paper for shield tunneling in silty sand, respectively. (4) The test results reveal that the slurry conditioning is better than the foam in decreasing the cutter torque in silty sand. To achieve the same effect of soil conditioning, the injection ratios of foam and slurry should be 45% and 10%, respectively, to achieve the torque reduction ratio of 60%. These findings can provide a practical reference for engineers to determine the best-fit conditioning materials and construction parameters in the silty sand stratum.

Silty sand is highly permeable and has a large internal friction angle. To ensure the stable and efficient construction of the Earth pressure balance (EPB) shield in silt stratum, it is necessary to reduce the disturbance to the stratum during tunneling and reduce the risk of spewing and blocking during soil discharge. Thus, a new type of dense slurry-EPB shield construction technology is proposed. Using a custom-made test device, the consolidation tests were conducted on sand after mixing it with different amounts of slurry to study the change in the pore pressure in the mixed soil and sand stratum and analyze the stress transmission rule. In addition, slump tests were conducted on the mixed soil to study the change in the fluidity. Based on the laboratory test results, a field investigation was carried out to study the effects of the amount of slurry addition on the pore pressure in the stratum, the driving parameters, and the sand’s flowability during shield tunneling. The results show that when the amount of slurry reaches a certain value, the filter cake effect occurs. The greater the amount of slurry added during the shield tunneling, the smaller the rate of change of the pore pressure in the stratum. When the amount of BC2 slurry added reached 8 m3 per ring, the rate of change was reduced by 57%, and the slump value improved by 93%. The type of filter cake of the DS-EPB shield was only internal filter cake during tunneling, which reduced the disturbance of the excavation face and improved the flowability of the sand. These results are of great significance to the application and promotion of DS-EPB shields in sandy cobble strata.

Background: Nowadays, the construction of urban tunnels for rapid transportation in metropolises is necessary. Since these tunnels are excavated at low depths, they are often associated with different problems and hazards. Some of them can reduce the efficiency of the tunnel boring machines and sometimes will stop the project. Among these problems the clogging can cause problems at the cutter head, in the chamber, and in other sections where the material transference occurs. Objective: The main purpose of this paper is to evaluate and determine the risk of clogging in the tunneling boring machine in Line 6 of the Tehran Metro. It includes stations: Amirkabir, Shohada Square, Emam Hossein Square and Sayyadeh Shirazi. This phenomenon induces an adhesion of the shield with the soil, increasing the necessary shear forces and it can eventually leads to the project interruption. Methods: Due to the fact that the criterion for the behavior of fine soils against moisture is Atterberg Limits, therefore, Atterberg Limits and the water content were utilized. For this purpose, the new method proposed by Hollman and Thewes (2013) was used. In this study, in addition to the Atterberg limits, the amount of free water resulting from the machine and from the underground water inflow was included in the calculations. Results: It was found that the water content should be increased carefully as the soil is very sensitive to this parameter. An increase of 15% of the water content permits to reduce the risk of clogging. If the added free water amount 15%, the probability of clogging becomes high. Whereas, in case where the added free water amount reaches 20%, the risk of clogging decreases significantly. Conclusion: According to the performed assessments, it was found that critical areas for the clogging aspect are both the cutter head and the chamber. The sensitivity of the soil is very important to the free water amount. Therefore, due to the behavior of sticky and plastic of clay soils against increasing water, it is necessary to determine the percentage of allowable water used in mechanized excavation projects.

In this research, three- dimension finite difference method was applied to simulate the tunnel excavation by earth pressure balance (EPB) boring machine of Tehran Metro Line 7 tunnel in Iran. Sensi...

The earth pressure balance tunnel boring machine (TBM) is advanced excavation machinery used to efficiently drill through subsurface ground layers while placing precast concrete tunnel segments. They have become prevalent in tunneling projects because of their adaptability, speed, and safety. Optimal usage of these machines requires information and data about the soil of the worksite that the TBM is drilling through. This paper proposes the utilization of artificial intelligence and machine learning, particularly recurrent neural networks, to predict the operational parameters of the TBM. The proposed model utilizes only performance data from excavation segments before the location of the machine as well as its current operating parameters to predict the as-encountered parameters. The proposed method is evaluated on a dataset collected during a tunneling project in North America. The results demonstrate that the model is effective in predicting operation parameters. To address the potential issue of gathering sufficient data to retrain the model, the possibility of transferring the trained model from one tunnel to another is tested. The results suggest that the model is capable of performing accurately with minimal or even no re-training.

This paper presents a case history of an earth pressure balance shield tunnelling project in Guangzhou, China. It beings with an explanation of the project background and geological conditions on s...

The sliming problem of chamber soil is caused by excessive groundwater seeping into the pressure chamber when an Earth pressure balance shield tunnels through a water-rich weathered rock stratum under semiopen under-pressure mode. As a solution to this problem, a calculation model was established based on field measurements of the discharged soil properties, the seepage water volume, and the seepage path in Jinan Metro, China. Chamber soil sliming is a phenomenon in which chamber soil is in a thin mud state, with no pressure balance in the pressure chamber of the EPB shield and an excessive water content of the chamber soil owing to the continuous seepage of groundwater into the chamber. The chamber pressure is relatively low, which is different from the phenomenon of spewing when the chamber pressure is relatively high. A large amount of water seepage from the stratum around the tunnel excavation surface and shield to the chamber is a significant factor leading to chamber soil sliming during the construction process. It was considered that when the moisture content of the chamber soil, w, is 2wL ≤ w ≤ 3wL, slight chamber soil sliming may occur, whereas when w ≥ 3wL, serious chamber soil sliming may occur. Moreover, some measures to prevent and control the occurrence of chamber soil sliming were discussed. Controlling the advancing time and the permeability coefficient of chamber soil during construction is the most effective measure to avoid the phenomenon of soil sliming.

Earth pressure balance shield (EPBS) tunneling techniques originally developed for fine-grained soil deposits have been adopted in a growing number of tunneling projects where challenging geological conditions, such as those with coarse-grained soils, are encountered. However, successful application of EPBS tunneling with soil conditioning could fully address technical challenges during tunneling in coarse-grained strata, such as tunnel face instability, blocking or clogging, severe wear of cutting tools, and low-effiency tunneling. In this paper, a comprehensive case study is presented that EPBS tunneling was successfully used in Beijing Metro Xijiao line with the aid of soil conditioning, where sandy gravel deposit with unfavorable particle size distribution, poor flowabilty, high permeability, and high abrasiveness was encountered. A series of both laboratory and in situ testing was carried to evaluate foaming agents, develop soil conditioning schemes, and verify their effectiveness of modifying the sandy gravel for EPBS tunneling purpose. The homogeneity, workability, permeability, and abrasivity of foamed soils were tested in the laboratory to develop soil conditioning schemes while the effectiveness of soil conditioning schemes during in situ tunneling was further evaluated with slump test and visual inspection. Parameters, such as foam expansion ratio (FER), half-life period, and foam injection ratio (FIR), which are used to evaluate the behavior of foaming agent and performance of conditioning schemes and tunneling schemes, were also discussed.

At present, many large-scale engineering equipment can obtain massive in-situ data at runtime. In-depth data mining is conducive to the real-time understanding of equipment operation status or recognition of service environment. This paper proposes a geological type recognition system by the analysis of in-situ data recorded during TBM tunneling to address geological information acquisition during TBM construction. Owing to high dimensionality and nonlinear coupling between parameters of TBM in-situ data, the dimensionality reduction feature engineering and machine learning methods are introduced into TBM in-situ data analysis. The chi-square test is used to screen for sensitive features due to the disobedience to common distributions of TBM parameters. Considering complex relationships, ANN, SVM, KNN, and CART algorithms are used to construct a geology recognition classifier. A case study of a subway tunnel project constructed using an earth pressure balance tunnel boring machine (EPB-TBM) in China is used to verify the effectiveness of the proposed geological recognition method. The result shows that the recognition accuracy gradually increases to a stable level with the increase of input features, and the accuracy of all algorithms is higher than 97%. Seven features are considered as the best selection strategy among SVM, KNN, and ANN, while feature selection is an inherent part of the CART method which shows a good recognition performance. This work provides an intelligent path for obtaining geological information for underground excavation TBM projects and a possibility for solving the problem of engineering recognition of more complex geological conditions.

In order to avoid the safety accidents caused by earth pressure imbalance during shield machine tunneling process, the earth pressure between excavation face and that in chamber must be maintained balance, but it is difficult for practical engineering. Therefore, a data-driven multi-variable optimization method based on dual heuristic programming (DHP) is proposed. First, a cost function with respect to the chamber’s earth pressure is given in light of Bellman’s principle. Then, based on back propagation neural networks (BPNN), the action network, model network and critic network are established that compose the DHP controller. The networks’ weights are updated through the gradient descent algorithm. By minimizing the cost function, the action network utilizes the critic network’s error to optimize the control variables, so that the optimal advance speed, cutter head torque, cutter head speed, total thrust and screw conveyor speed are obtained. Finally, the simulation experiments are carried out, and the results indicate that the method can effectively control the earth pressure balance in chamber and has strong anti-interference ability.

This paper proposes an intelligent framework to predict and automatically regulate earth pressure using a deep learning technique during earth pressure balance shield tunneling. A prediction model was proposed by integrating a new cost function (relative mean square error) with a gated recurrent unit (GRU). The moving average smoothing method was also incorporated into the GRU model to reduce the noise of the dataset and improve the accuracy of the proposed model. A real-time dynamic regulation model for adjusting the operational parameters was proposed by integrating the GRU model into a genetic algorithm-based optimizer. By adjusting the operational parameters, the dynamic regulation model regulates the excessive predicted earth pressure within a suggested range. The proposed prediction and regulation models were applied to a metro tunnel construction in Luoyang, China. The results show that the proposed models provide good guidance for automated tunnel construction.