• Geomechanics and Engineering
• /
• v.38 no.5
• /
• pp.517-528
• /
• 2024

For numerous tunnelling projects implemented in urban areas due to limited space, it is crucial to take into account the interaction between the foundation, ground, and tunnel. In predicting the deformation of piled foundations and the ground during twin tunnel excavation, it is essential to consider various factors. Therefore, this study derived a prediction model for pile group settlement using machine learning to analyze the importance of various factors that determine the settlement of piled foundations during twin tunnelling. Laboratory model tests and numerical analysis were utilized as input data for machine learning. The influence of each independent variable on the prediction model was analyzed. Machine learning techniques such as data preprocessing, feature engineering, and hyperparameter tuning were used to improve the performance of the prediction model. Machine learning models, employing Random Forest (RF), eXtreme Gradient Boosting (XGB), and Light Gradient Boosting Machine (LightGBM, LGB) algorithms, demonstrate enhanced performance after hyperparameter tuning, particularly with LGB achieving an R² of 0.9782 and RMSE value of 0.0314. The feature importance in the prediction models was analyzed and P_N was the highest at 65.04% for RF, 64.81% for XGB, and P_CTC (distance between the center of piles) was the highest at 31.32% for LGB. SHAP was utilized for analyzing the impact of each variable. P_N (the number of piles) consistently exerted the most influence on the prediction of pile group settlement across all models. The results from both laboratory model tests and numerical analysis revealed a reduction in ground displacement with varying pillar spacing in twin tunnels. However, upon further investigation through machine learning with additional variables, it was found that the number of piles has the most significant impact on ground displacement. Nevertheless, as this study is based on laboratory model testing, further research considering real field conditions is necessary. This study contributes to a better understanding of the complex interactions inherent in twin tunnelling projects and provides a reliable tool for predicting pile group settlement in such scenarios.

• Geomechanics and Engineering
• /
• v.38 no.5
• /
• pp.467-476
• /
• 2024

This study investigates Tunnel Boring Machine (TBM) performance prediction by employing discrete event simulation technique, which is a potential remedy highlighting its stochastic adaptability to the complex nature of TBM tunnelling activities. The new discrete event simulation model using AnyLogic software was developed and validated by comparing its results with actual performance data for Daegok-Sosa railway project that Earth Pressure Balance (EPB) TBM machine was used in Korea. The results showed the successful implementation of predicting TBM performance. However, it necessitates high-quality database establishment including geological formations, machine specifications, and operation settings. Additionally, this paper introduces a novel methodology for daily performance updates during construction, using automated data processing techniques. This approach enables daily updates and predictions for the ongoing projects, offering valuable insights for construction management. Overall, this study underlines the potential of discrete event simulation in predicting TBM performance, its applicability to other tunneling projects, and the importance of continual database expansion for future model enhancements.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.22 no.5
• /
• pp.575-589
• /
• 2020

In recent years, Shield TBM construction has been continuously increasing in domestic tunnels. The main excavation tool in the shield TBM construction is a disc cutter which naturally wears during the excavation process and significantly degrades the excavation efficiency. Therefore, it is important to know the appropriate time of the disc cutter replacement. In this study, it is proposed a predictive model that can determine yes/no of disc cutter replacement using machine learning algorithm. To do this, the shield TBM machine data which is highly correlated to the disc cutter wears and the disc cutter replacement from the shield TBM field which is already constructed are used as the input data in the model. Also, the algorithms used in the study were the support vector machine, k-nearest neighbor algorithm, and decision tree algorithm are all classification methods used in machine learning. In order to construct an optimal predictive model and to evaluate the performance of the model, the classification performance evaluation index was compared and analyzed.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.21 no.5
• /
• pp.641-656
• /
• 2019

In this study, a machine learning method was proposed to use in predicting optimal replacement period of shield TBM (Tunnel Boring Machine) disc cutter. To do this, a large dataset of ground condition, disc cutter replacement records and TBM excavation-related data, collected from a shield TBM tunnel site in Korea, was built and they were used to construct a disc cutter replacement period prediction model using a machine learning algorithm, SVM (Support Vector Machine) and to assess the performance of the model. The results showed that the performance of RBF (Radial Basis Function) SVM is the best among a total of three SVM classification functions (80% accuracy and 10% error rate on average). When compared between ground types, the more disc cutter replacement data existed, the better prediction results were obtained. From this results, it is expected that machine learning methods become very popularly used in practice in near future as more data is accumulated and the machine learning models continue to be fine-tuned.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.15 no.5
• /
• pp.483-496
• /
• 2013

This paper presents the shield TBM technology in soft ground tunnelling. In order to perform this study, a scale model test was carried out using the developed small scaled shield TBM machine. The various instrumentations were conducted during the simulation of tunnelling. In addition, the ground behavior due to the shield TBM operation parameters was measured during the simulation. Based on the simulation results, the stability of the ground was evaluated and the fundamental shield TBM tunnelling technique in the soft ground was suggested. In conclusion, design's reliability through laboratory small scale model test about Shield-TBM section was obtained, and both the improvement plan for safety during construction and the construction plan for securing airport runway's safety during tunnel passing by Shield-TBM propulsion were suggested.

• Journal of the Korean Geotechnical Society
• /
• v.19 no.5
• /
• pp.273-280
• /
• 2003

This paper describes a study of the effect of shield tunnel construction on the liners of nearby existing perpendicular tunnels. The research programme investigated the influence of tunnel proximity and alignment, liner stiffness on the nature of the interactions between closely spaced tunnels in clay. A total of two sets of carefully controlled 1g physical model tests, including the same test for repeatability, were performed. A cylindrical test tank was developed and used to produce clay samples of Speswhite kaolin. In each of the tests, three model tunnels were installed in order to conduct two interaction experiments in one clay sample. The tunnel liners were installed using a model tunnelling machine that was designed and developed to simulate the construction of a full scale shield tunnel. The first tunnel liner was instrumented to investigate its behaviour due to the installation of each of the new tunnels. The interaction mechanisms observed from the physical model tests are discussed and interpreted.

• Geomechanics and Engineering
• /
• v.14 no.5
• /
• pp.479-489
• /
• 2018

In this paper, a comparative study of the effects of soil modelling on the interaction between tunnelling in soft soil and adjacent piled structure is presented. Several three-dimensional finite element analyses are performed to study the deformation of pile caps and piles as well as tunnel internal forces during the construction of an underground tunnel. The soil is modelled by two material models: the simple, yet approximate Mohr Coulomb (MC) yield criterion; and the complex, but reasonable hardening soil (HS) model with hyperbolic relation between stress and strain. For the former model, two different values of the soil stiffness modulus ($E_{50}$ or $E_{ur}$) as well as two profiles of stiffness variation with depth (constant and linearly increasing) were used in attempts to improve its prediction. As these four attempts did not succeed, a hybrid representation in which the hardening soil is used for soil located at the highly-strained zones while the Mohr Coulomb model is utilized elsewhere was investigated. This hybrid representation, which is a compromise between rigorous and simple solutions yielded results that compare well with those of the hardening soil model. The compared results include pile cap movements, pile deformation, and tunnel internal forces. Problem symmetry is utilized and, therefore, one symmetric half of the soil medium, the tunnel boring machine, the face pressure, the final tunnel lining, the pile caps, and the piles are modelled in several construction phases.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.16 no.6
• /
• pp.507-520
• /
• 2014

In this study, the surface displacement was investigated according to the various depth of cover when the tunnel excavation equipment was used in a clay soil. For this the laboratory scaled model test was carried out using the soil sample similar to the in-situ conditions. We carried out four tests according to tunnel depth(1.5D, 2.0D, 2.5D, 3.0D). The distribution of impact due to tunnelling was quantitatively analyzed in the three-dimension by measuring the surface displacement. In addition, the pattern of surface displacements was figured out.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.2
• /
• pp.217-230
• /
• 2022

The adequate control of TBM face pressure is of vital importance to maintain face stability by preventing face collapse and surface settlement. An EPB shield TBM excavates the ground by applying face pressure with the excavated soil in the pressure chamber. One of the challenges during the EPB shield TBM operation is the control of face pressure due to difficulty in managing the excavated soil. In this study, the face pressure of an EPB shield TBM was predicted using the geological and operational data acquired from a domestic TBM tunnel site. Four machine learning algorithms: KNN (K-Nearest Neighbors), SVM (Support Vector Machine), RF (Random Forest), and XGB (eXtreme Gradient Boosting) were applied to predict the face pressure. The model comparison results showed that the RF model yielded the lowest RMSE (Root Mean Square Error) value of 7.35 kPa. Therefore, the RF model was selected as the optimal machine learning algorithm. In addition, the feature importance of the RF model was analyzed to evaluate appropriately the influence of each feature on the face pressure. The water pressure indicated the highest influence, and the importance of the geological conditions was higher in general than that of the operation features in the considered site.

• 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.