• Journal of Korean Tunnelling and Underground Space Association
• /
• v.20 no.2
• /
• pp.453-467
• /
• 2018

The excavation performance and the cutting tool wear prediction of shield TBM are very important issues for design and construction in TBM tunneling. For hard-rock TBMs, CSM and NTNU model have been widely used for prediction of disc cutter wear and penetration rate. But in case of soft-ground TBMs, the wear evaluation and the excavation performance have not been studied in details due to the complexity of the ground behavior and therefore few testing methods have been proposed. In this study, a new soil abrasion and penetration tester (SAPT) that simulates EPB TBM excavation process is introduced which overcomes the drawbacks of the previously developed soil abrasivity testers. Parametric tests for penetration rate, foam mixing ratio, foam concentration were conducted to evaluate influential parameters affecting TBM excavation and also ripper wear was measured in laboratory. The results of artificial soil specimen composed of 70% illite and 30% silica sand showed TBM additives such as foam play a key role in terms of excavation and tool wear.

• 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.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2010.09a
• /
• pp.1343-1349
• /
• 2010

This paper presents the behavior of the soil based on the Gap Parameter during the Shield TBM tunnel excavation in sandy soil. This study reproduced the tunnel before and after the excavation according to the diameter of the tunnel, water ratio and depth to execute a Scaled Model Test and analyzed the behavior change of the upper soil. As a result, tunneling after for soil stress decreased was similar in all the Case. In addition, the soil stress decreased was in water ratio increases.

• Journal of the Korean GEO-environmental Society
• /
• v.7 no.2
• /
• pp.67-76
• /
• 2006

For a hydro power plant project, the headrace tunnel having a finished diameter of 3.3 m was constructed in volcanic rocks with well-developed vertical joint and high groundwater table. The intake facility was located 20.3km upstream of the powerhouse and headrace tunnel of 20km in length and penstock of 440m in height connected the intake and the powerhouse. The typical caldera lake, Lake Toba set the geology at the site the caving of the ground caused tension cracks in the vertical direction to be developed and initial stresses at the ground to be released. High groundwater table(the maximum head of 20bar) in the area of well-connected vertical joints delayed the progress of tunnel excavation severely due to the excessive inflow of groundwater. The excavation of tunnel was made using open-shield type TBM and mucking cars on the rail. High volume of water inflowraised the water level inside tunnel to 70cm, 17% of tunnel diameter (3.9m) and hindered the mucking of spoil under water. To improve the productivity, several adjustments such as modification of TBM and mucking cars and increase in the number of submersible pumps were made forthe excavation of severe water inflow zone. Since the ground condition encountered during excavation turned out to be much worse, it was decided to adopt PC segment lining instead of RC lining. Besides, depending on the conditions of the water inflow, rock mass condition and internal water pressure, one of the invert PC segment lining with in-situ RC lining, RC lining and steel lining was applied to meet the site specific condition. With the adoption of PC segment lining, modification of TBM and other improvement, the excavation of the tunnel under severe groundwater condition was successfully completed.