• 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.

• Wind and Structures
• /
• v.27 no.4
• /
• pp.223-234
• /
• 2018

In this study, a simplified three-dimensional calculation model is developed for the dynamic analysis of soil-pile group-supertall building systems excited by wind loads using the substructure method. Wind loads acting on a 300-m building in different wind directions and terrain conditions are obtained from synchronous pressure measurements conducted in a wind tunnel. The effects of soil-structure interaction (SSI) on the first natural frequency, wind-induced static displacement, root mean square (RMS) of displacement, and RMS of acceleration at the top of supertall buildings are analyzed. The findings demonstrate that with decreasing soil shear wave velocity, the first natural frequency decreases and the static displacement, RMS of displacement and RMS of acceleration increase. In addition, as soil material damping decreases, the RMS of displacement and the RMS of acceleration increase.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.3
• /
• pp.355-373
• /
• 2017

Tunnelling in urban areas, it is essential to understand existing structure-tunnel interactive behavior. Serviced structures in the city are supported by pile foundation, since they are certainly effected due to tunnelling. In this research, thus, pile load distribution and ground behavior due to tunnelling below grouped pile were investigated using laboratory model test. Grouped pile foundations were considered as 2, 3 row pile and offsets (between pile tip and tunnel crown: 0.5D, 1.0D and 1.5D for generalization to tunnel diameter, D means tunnel diameter). Soil in the tank for laboratory model test was formed by loose sand (relative density: Dr = 30%) and strain gauges were attached to the pile inner shaft to estimate distribution of axial force. Also, settlements of grouped pile and adjacent ground surface depending on the offsets were measured by LVDT and dial gauge, respectively. Tunnelling-induced deformation of underground was measured by close range photogrammetric technique. Numerical analysis was conducted to analyze and compare with results from laboratory model test and close range photogrammetry. For expression of tunnel excavation, the concept of volume loss was applied in this study, it was 1.5%. As a result from this study, far offset, the smaller reduction of pile axial load and was appeared trend of settlement was similar among them. Particulary, ratio of pile load and settlement reduction were larger when the offset is from 0.5D to 1.0D than from 1.0D to 1.5D.