• Proceedings of the Korean Society for Rock Mechanics Conference
• /
• 2006.03a
• /
• pp.217-236
• /
• 2006

In this study, the LCM was applied as the preliminary study for the cutterhead design of TBM and the drilling performance evaluation. The optimum cutting condition is obtained from the LCM tests and the effects of the design factors of IBM cutterhead, such as penetration depth and cutter spacing, on drilling performance are estimated. In this study, hence, to predict the accurate performance of TBM, instead of one-dimensional penetration depth applied in existing studies, three-dimensional cutting volume was quantified and measured. For this, the digital photogrammetry technique was applied to the LCM tests. Also, AUTODYN 2D was applied to investigate the applicability of the numerical analysis technique to simulate the cutting process of rock by the TBM disc cutter.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.17 no.4
• /
• pp.457-471
• /
• 2015

A domestic cutterhead with the diameter of 3.6 m was designed and manufactured in this study. Then, it was attached to an existing earth-pressure balanced shield TBM to excavate a cable tunnel with the length of 1,275 m. Especially, the procedures for TBM cutterhead design and its corresponding performance prediction were also summarized. From field data analyses of the refurbished shield TBM, its maximum advance rate was recorded as 14.4 m/day. Penetration depths of disc cutters were found to be approximately 4 mm/rev, which is equal to the maximum penetration depth designed for the strongest rock strength condition in the target tunnel. Every TBM operating thrust and cutter normal force during TBM driving was much smaller than their corresponding maximum capacities. When cutter acting forces recorded in the field were analyzed, their prediction errors by the CSM model were very high for weak rock conditions. In addition, rock strength showed very close relationships with cutter normal force and penetration depth.

• Tunnel and Underground Space
• /
• v.21 no.6
• /
• pp.508-517
• /
• 2011

The linear cutting test is the most reliable and accurate approach to measuring cutting forces and cutting efficiency using full-size disc cutter in various rock types. The result of linear cutting tests can be used to obtain the key parameters of cutter-head design (i.e. optimum cutter spacing, cutter forces). In Korea, LCM (Linear Cutting Machine) tests have been performed for typical Korean rock types, but these studies focused on the isotropic rocktypes. For prediction of TBM (Tunnel Boring Machine) performances in complex geological conditions including a bedded and schistose rockmass, it is important to consider the effects of anisotropy of rockmass on cutting performances and cutting efficiency. This study discusses a series of LCM tests that were performed for Asan Gneiss having two types of anisotropy angles to assess the effect of the anisotropy angle on rock-cutting performances of TBM. The result shows that the rock-cutting performances and optimum cutting conditions are affected by anisotropy angle and the effect of anisotropy on rock strength should be considered in a prediction of the cutting performances and efficiency of TBM.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.5
• /
• pp.519-532
• /
• 2024

Anomaly detection for the penetration rate of tunnel boring machines (TBMs) is crucial for effective risk management in TBM tunnel projects. However, previous machine learning models for predicting the penetration rate have struggled with imbalanced data between normal and abnormal penetration rates. This study aims to enhance the performance of machine learning-based anomaly detection for the penetration rate by utilizing a data augmentation technique to address this data imbalance. Initially, six input features were selected through correlation analysis. The lowest and highest 10% of the penetration rates were designated as abnormal classes, while the remaining penetration rates were categorized as a normal class. Two prediction models were developed, each trained on an original training set and an oversampled training set constructed using SMOTE (synthetic minority oversampling technique): an XGB (extreme gradient boosting) model and an XGB-SMOTE model. The prediction results showed that the XGB model performed poorly for the abnormal classes, despite performing well for the normal class. In contrast, the XGB-SMOTE model consistently exhibited superior performance across all classes. These findings can be attributed to the data augmentation for the abnormal penetration rates using SMOTE, which enhances the model's ability to learn patterns between geological and operational factors that contribute to abnormal penetration rates. Consequently, this study demonstrates the effectiveness of employing data augmentation to manage imbalanced data in anomaly detection for TBM penetration rates.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.15 no.3
• /
• pp.225-235
• /
• 2013

Cutter forces acting on a disc cutter in TBM are the key parameters for TBM design and its performance prediction. This study aimed to experimentally evaluate cutter forces with different ring shapes in a hard rock. The stiffness of a cutter ring was indirectly estimated from a series of full-scale linear cutting tests. From the experiments, it was verified that the rolling stress acting on a V-shape disc cutter was much higher than on a CCS disc cutter even though the penetration depth by a V-shape disc cutter could be increased in the same cutting condition. Finally, it is suggested that a prediction model considering the shape parameters of a disc cutter should be used for its better prediction.

• Tunnel and Underground Space
• /
• v.10 no.4
• /
• pp.526-532
• /
• 2000

The uniaxial compressive strength of rock mass is known as the major factor in the assessment of drillability and the optimum excavation design in full-face tunnel excavation by TBM. Referring to worldwide cases, TBM has been applied mostly to the rock mass within the strength range of 80~250 MPa. Recently, a water way tunnel has been constructed as a part of Milyang dam project by TBM within the rock masses where the rock type is mainly granite with some granophyre, hornfels and andesite. Their uniaxial compressive strengths in extended area are estimated higher than 260 MPa. In this paper, the relation between the penetration rate and the rock mass properties is analyzed and TBM application to the very hard rocks is discussed. As a result that three suggestions to predict the TBM net penetration rate are analyzed, NTH method seems a better approach than other methods in the extremely hard rocks. NTH prediction matches with the results of actual values with the variations of 2~20%. Hardness measurement by Schmidt hammer and RMR estimation are carried out along the L = 5.3 km entire TBM tunnel alignment. The net penetration rate measured monthly is shown to be reciprocally proportional to Schmidt rebound hardness and RMR where coefficients of correlation, $R^2$are 0.705 and 0.777 respectively. As a result, they are good quantitative indices for the prediction of TBM net penetration rate in the extremely hard rocks. Magnitude of in-situ stress has a certain effect on TBM performance, and it is required to measure the in-situ stresses in TBM excavation design.

• Journal of the Korean Geosynthetics Society
• /
• v.17 no.4
• /
• pp.129-139
• /
• 2018

The Discrete Element Method (DEM) has been widely used in granular material researches. Especially, if material has a large deformation, such as ground, it can be a useful method to analyze. In this study, to simulate ground formations, DEM was used. The main purpose of DEM analysis was to investigate the numerical model which can predict the TBM performance by simulating excavating procedure. The selected EPB TBM has a 7.73 m of diameter and six spokes. And two pre-defined excavation conditions with the different rotation speeds per minute (RPM) of the cutterhead was applied. In the modeled cutterhead, the open ratio of cutterhead was 21.31% and number of cutters (including disc cutter and cutter bit) was 219. From the results, reaction forces and resistant torques at the cutterhead face and cutting tools, were measured and compared. Additionally the muck discharge rate and accumulated muck discharge by the screw auger were evaluated.

• Geomechanics and Engineering
• /
• v.38 no.5
• /
• pp.507-515
• /
• 2024

An accurate estimation of the geotechnical parameters in front of tunnel faces is crucial for the safe construction of underground infrastructure using tunnel boring machines (TBMs). This study was aimed at developing a data-driven model for predicting the rock quality designation (RQD) of the ground formation ahead of tunnel faces. The dataset used for the machine learning (ML) model comprises seven geological and mechanical features and 564 RQD values, obtained from an earth pressure balance (EPB) shield TBM tunneling project beneath the Han River in the Republic of Korea. Four ML algorithms were employed in developing the RQD prediction model: k-nearest neighbor (KNN), support vector regression (SVR), random forest (RF), and extreme gradient boosting (XGB). The grid search and five-fold cross-validation techniques were applied to optimize the prediction performance of the developed model by identifying the optimal hyperparameter combinations. The prediction results revealed that the RF algorithm-based model exhibited superior performance, achieving a root mean square error of 7.38% and coefficient of determination of 0.81. In addition, the Shapley additive explanations (SHAP) approach was adopted to determine the most relevant features, thereby enhancing the interpretability and reliability of the developed model with the RF algorithm. It was concluded that the developed model can successfully predict the RQD of the ground formation ahead of tunnel faces, contributing to safe and efficient tunnel excavation.

• Tunnel and Underground Space
• /
• v.30 no.6
• /
• pp.540-550
• /
• 2020

Machine learning has been actively used in the field of automation due to the development and establishment of AI technology. The important thing in utilizing machine learning is that appropriate algorithms exist depending on data characteristics, and it is needed to analysis the datasets for applying machine learning techniques. In this study, advance rate is predicted using geotechnical and machine data of TBM tunnel section passing through the soil ground below the stream. Although there were no problems of application of statistical technology in the linear regression model, the coefficient of determination was 0.76. While, the ensemble model and support vector machine showed the predicted performance of 0.88 or higher. it is indicating that the model suitable for predicting advance rate of the EPB Shield TBM was the support vector machine in the analyzed dataset. As a result, it is judged that the suitability of the prediction model using data including mechanical data and ground information is high. In addition, research is needed to increase the diversity of ground conditions and the amount of data.

• Geomechanics and Engineering
• /
• v.37 no.3
• /
• pp.223-241
• /
• 2024

Evaluating the performance of Tunnel Boring Machines (TBMs) stands as a pivotal juncture in the domain of hard rock mechanized tunneling, essential for achieving both a dependable construction timeline and utilization rate. In this investigation, three advanced artificial neural networks namely, gated recurrent unit (GRU), back propagation neural network (BPNN), and simple recurrent neural network (SRNN) were crafted to prognosticate TBM-rate of penetration (ROP). Drawing from a dataset comprising 1125 data points amassed during the construction of the Alborze Service Tunnel, the study commenced. Initially, five geomechanical parameters were scrutinized for their impact on TBM-ROP efficiency. Subsequent statistical analyses narrowed down the effective parameters to three, including uniaxial compressive strength (UCS), peak slope index (PSI), and Brazilian tensile strength (BTS). Among the methodologies employed, GRU emerged as the most robust model, demonstrating exceptional predictive prowess for TBM-ROP with staggering accuracy metrics on the testing subset (R² = 0.87, NRMSE = 6.76E-04, MAD = 2.85E-05). The proposed models present viable solutions for analogous ground and TBM tunneling scenarios, particularly beneficial in routes predominantly composed of volcanic and sedimentary rock formations. Leveraging forecasted parameters holds the promise of enhancing both machine efficiency and construction safety within TBM tunneling endeavors.