• Tunnel and Underground Space
• /
• v.30 no.5
• /
• pp.496-507
• /
• 2020

A prediction of the performance of EPB TBM is significant for improving the constructability of tunnels. Thus, various attempts to simulate TBM excavation by the numerical method have been made until these days. In this paper, to evaluate the performance of TBM with different operating conditions, a parametric study was carried out using coupled discrete element method (DEM) and finite difference method (FDM) EPB TBM driving model. The analysis was conducted by changing the penetration rate (0.5 and 1.0 mm/sec) and the rotational speed of screw conveyor (5, 15, and 25 rpm) while the rotation velocity of the cutter head kept constant at 2 rpm. The torque, thrust force, chamber pressure, and discharging with different TBM operating conditions were compared. The result of parametric study shows that the optimum driving condition can be determined by the coupled DEM-FDM numerical model.

• Geomechanics and Engineering
• /
• v.39 no.1
• /
• pp.27-41
• /
• 2024

Accurately estimating the performance of tunnel boring machines (TBMs) is crucial for mitigating the substantial financial risks and complexities associated with tunnel construction. Machine learning (ML) techniques have emerged as powerful tools for predicting non-linear time series data. In this research, six advanced meta-heuristic optimization algorithms based on long short-term memory (LSTM) networks were developed to predict TBM penetration rate (TBM-PR). The study utilized 1125 datasets, partitioned into 20% for testing, 70% for training, and 10% for validation, incorporating six key input parameters influencing TBM-PR. The performances of these LSTM-based models were rigorously compared using a suite of statistical evaluation metrics. The results underscored the profound impact of optimization algorithms on prediction accuracy. Among the models tested, the LSTM optimized by the particle swarm optimization (PSO) algorithm emerged as the most robust predictor of TBM-PR. Sensitivity analysis further revealed that the orientation of discontinuities, specifically the alpha angle (α), exerted the greatest influence on the model's predictions. This research is significant in that it addresses critical concerns of TBM manufacturers and operators, offering a reliable predictive tool adaptable to varying geological conditions.

• Geomechanics and Engineering
• /
• v.38 no.6
• /
• pp.633-645
• /
• 2024

Disc cutters, used as excavation tools for rocks in a Tunnel Boring Machine (TBM), naturally undergo wear during the tunneling process, involving crushing and cutting through the ground, leading to various wear types. When disc cutters reach their wear limits, they must be replaced at the appropriate time to ensure efficient excavation. General disc cutter life prediction models are typically used during the design phase to predict the total required quantity and replacement locations for construction. However, disc cutters are replaced more frequently during tunneling than initially planned. Unpredictable disc cutter replacements can easily diminish tunneling efficiency, and abnormal wear is a common cause during tunneling in complex ground conditions. This study aims to overcome the limitations of existing disc cutter life prediction models by utilizing machine data generated during tunneling to predict disc cutter wear patterns and determine the need for replacements in real-time. Artificial intelligence classification algorithms, including K-nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree (DT), and Stacking, are employed to assess the need for disc cutter replacement. Binary classification models are developed to predict which disc cutters require replacement, while multi-class classification models are fine-tuned to identify three categories: no replacement required, replacement due to normal wear, and replacement due to abnormal wear during tunneling. The performance of these models is thoroughly assessed, demonstrating that the proposed approach effectively manages disc cutter wear and replacements in shield TBM tunnel projects.

• Tunnel and Underground Space
• /
• v.22 no.2
• /
• pp.144-156
• /
• 2012

This paper discusses the methods of estimating the punch penetration indices and data analysis punch penetration test to estimate the TBM normal force and penetration rate. In punch penetration test is known as a useful test to estimate penetration rates and normal force of TBMs directly with several slope indices indicated drill-ability and brittleness of rocks. However, the standard methods and indices for punch penetration test are not suggested yet. The main purpose of punch penetration test which is prediction of normal force of TBM disc cutter when cutters excavate rock mass. In this study, the punch penetration tests were performed for 6 representative Korean rock types and variety length and diameter of rock core specimens. Among slope indices were obtained from punch penetration test, PLI and MLI which is suggested in this study show high correlation with cutter force measured by full-scale cutting test. The results show that the predicted normal force of a single disc cutter and the experimental error was 10%. Based on these results, it is concluded that punch penetration test is reliable laboratory test for estimating thrust and penetration rates of TBM.

• Geomechanics and Engineering
• /
• v.37 no.3
• /
• pp.197-211
• /
• 2024

This research studies the effect of geotechnical factors on EPB-TBM performance parameters. The modeling was performed using simple and multivariate linear regression methods, artificial neural networks (ANNs), and Sugeno fuzzy logic (SFL) algorithm. In ANN, 80% of the data were randomly allocated to training and 20% to network testing. Meanwhile, in the SFL algorithm, 75% of the data were used for training and 25% for testing. The coefficient of determination (R²) obtained between the observed and estimated values in this model for the thrust force and cutterhead torque was 0.19 and 0.52, respectively. The results showed that the SFL outperformed the other models in predicting the target parameters. In this method, the R² obtained between observed and predicted values for thrust force and cutterhead torque is 0.73 and 0.63, respectively. The sensitivity analysis results show that the internal friction angle (φ) and standard penetration number (SPT) have the greatest impact on thrust force. Also, earth pressure and overburden thickness have the highest effect on cutterhead torque.

• Tunnel and Underground Space
• /
• v.19 no.5
• /
• pp.440-449
• /
• 2009

LCM test is one of the most powerful and reliable methods of experiment for the cutter head design and the performance prediction of TBM. In many cases, however, the predicted design model can be directly applied to the field design, because this test may have an uppermost limit in preparation and/or transportation of the large size rock samples and the test for the jointed rock mass is not easy. When the proper and reasonable numerical modeling is considered to overcome this limit, the most adequate cutter head design for TBM could be presented without any complicate preconsideration in the field. In this study, the crack propagation patterns dependent on the contact point of disc cutter and the angle of rock joint are analyzed for the rock specimen with a single joint using the UDEC. The authors could derive the appropriate contact points of disc cutters and their space with respect to the joint angle in rock mass thru the numerical analysis.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.1
• /
• pp.39-58
• /
• 2024

Tunnel Boring Machines (TBM) use multiple disc cutters to excavate tunnels through rock. These cutters wear out due to continuous contact and friction with the rock, leading to decreased cutting efficiency and reduced excavation performance. The rock's abrasivity significantly affects cutter wear, with highly abrasive rocks causing more wear and reducing the cutter's lifespan. The Cerchar Abrasivity Index (CAI) is a key indicator for assessing rock abrasivity, essential for predicting disc cutter life and performance. This study aims to develop a new method for effectively estimating CAI using rock strength, petrological characteristics, linear regression, and machine learning. A database including CAI, uniaxial compressive strength, Brazilian tensile strength, and equivalent quartz content was created, with additional derived variables. Variables for multiple linear regression were selected considering statistical significance and multicollinearity, while machine learning model inputs were chosen based on variable importance. Among the machine learning prediction models, the Gradient Boosting model showed the highest predictive performance. Finally, the predictive performance of the multiple linear regression analysis and the Gradient Boosting model derived in this study were compared with the CAI prediction models of previous studies to validate the results of this research.

• Geomechanics and Engineering
• /
• v.18 no.2
• /
• pp.215-224
• /
• 2019

Excavation of long tunnels by shielded TBMs is a safe, fast, and efficient method of tunneling that mitigates many risks related to ground conditions. However, long-distance tunneling in great depth through adverse geological conditions brings about limitations in the application of TBMs. Among various harsh geological conditions, squeezing ground as a consequence of tunnel wall and face convergence could lead to cluttered blocking, shield jamming and in some cases failure in the support system. These issues or a combination of them could seriously hinder the performance of TBMs. The technique of excavation has a strong influence on the tunnel response when it is excavated under squeezing conditions. The Golab water conveyance tunnel was excavated by a double-shield TBM. This tunnel passes mainly through metamorphic weak rocks with up to 650 m overburden. These metamorphic rocks (Shales, Slates, Phyllites and Schists) together with some fault zones are incapable of sustaining high tangential stresses. Prediction of the convergence, estimation of the creeping effects and presenting strategies to overcome the squeezing ground are regarded as challenging tasks for the tunneling engineer. In this paper, the squeezing potential of the rock mass is investigated in specific regions by dint of numerical and analytical methods. Subsequently, several operational solutions which were conducted to counteract the challenges are explained in detail.

• Tunnel and Underground Space
• /
• v.33 no.6
• /
• pp.594-609
• /
• 2023

TBM (Tunnel Boring Machine) method is gaining popularity in urban and underwater tunneling projects due to its ability to ensure excavation face stability and minimize environmental impact. Among the prominent models for predicting disc cutter life, the NTNU model uses the Cutter Life Index(CLI) as a key parameter, but the complexity of testing procedures and rarity of equipment make measurement challenging. In this study, CLI was predicted using multiple linear regression analysis and tree-based machine learning techniques, utilizing rock properties. Through literature review, a database including rock uniaxial compressive strength, Brazilian tensile strength, equivalent quartz content, and Cerchar abrasivity index was built, and derived variables were added. The multiple linear regression analysis selected input variables based on statistical significance and multicollinearity, while the machine learning prediction model chose variables based on their importance. Dividing the data into 80% for training and 20% for testing, a comparative analysis of the predictive performance was conducted, and XGBoost was identified as the optimal model. The validity of the multiple linear regression and XGBoost models derived in this study was confirmed by comparing their predictive performance with prior research.

• Geomechanics and Engineering
• /
• v.29 no.3
• /
• pp.219-228
• /
• 2022

The most widely used parameter to represent rock abrasiveness is the Cerchar abrasivity index (CAI). The CAI value can be applied to predict wear in TBM cutters. It has been extensively demonstrated that the CAI is affected significantly by cementation degree, strength, and amount of abrasive minerals, i.e., the quartz content or equivalent quartz content in rocks. The relationship between the properties of rocks and the CAI is investigated in this study. A database comprising 223 observations that includes rock types, uniaxial compressive strengths, Brazilian tensile strengths, equivalent quartz contents, quartz contents, brittleness indices, and CAIs is constructed. A linear model is developed by selecting independent variables while considering multicollinearity after performing multiple regression analyses. Machine learning-based regression methods including support vector regression, regression tree regression, k-nearest neighbors regression, random forest regression, and artificial neural network regression are used in addition to multiple linear regression. The results of the random forest regression model show that it yields the best prediction performance.