• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2001년도 봄 학술발표회 논문집
• /
• pp.299-306
• /
• 2001

Crushed Stone Pile(CSP) is one of the ground improvement methods available to loose sand and clayey ground by forming compacted CSP in the weak soil layer. The effects of this method are enhancement of ground bearing capacity, reduction of settlement and prevention of lateral ground movement in cohesive layer, reduction of liquefaction potential in sandy ground. This study performs model tests in 1.0m${\times}$1.0m${\times}$1.0m and 1.5m${\times}$1.5m${\times}$l.2m model tank to observe bearing capacity of CSP treated ground. The area replacement ratio of CSP composite ground varies 20%, 30% and 40% with square grid pattern. After the composite ground was consolidated under pressure of 0.5kg/$\textrm{cm}^2$ and 1.0kg/$\textrm{cm}^2$, load tests were carried out. The results show that ultimate bearing capacity increases with area replacement ratio and the preconsolidation pressure of ground.

• Geomechanics and Engineering
• /
• 제38권5호
• /
• 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.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2005년도 춘계 학술발표회 논문집
• /
• pp.65-70
• /
• 2005

In this study, the large scale model tests were executed to estimate the Load Sharing Ratio(LSR) of raft in a piled footing under various conditions. The conditions such as the subsoil type, pile length, pile spacing, array type and pile installation method etc. were varied in the pile loading tests about the free-standing group piles and a piled footing. As the results of this study, it was found that there were no differences of the load-settlement curves, along with the pile installation method and subsoil type. The piles supported most of the external load until a yielding load of the piled footing, but the raft supported a considerable load after a yielding load. And it was also found that the LSR didn't be affected by the pile installation method and the subsoil type. As the relative density of sands increased, the LSR decreased. As the pile spacing was wider and the pile length increased, there was a tendancy for the LSR to increase.

• 한국지반공학회논문집
• /
• 제21권5호
• /
• pp.197-205
• /
• 2005

이 논문에서는 속채움 재료로 입도조정 쇄석을 사용하고 해저 연약지반에 말뚝을 조성하되 말뚝의 외벽을 토목섬유 (PE Mat)로 팩을 만들어 보강하는 공법을 개발하여 이를 소개하고자 한다. 이 공법은 주로 해저 연약지반 개량에 적용하고자 해상 대구경 팩 말뚝(Marine Large Pack Pile)이라 명하였으며, 그 적용성을 검토하기 위하여 부산 신항만 현장에서 시험시공을 수행하고, 시공된 해저 지반에서 국내에서는 최초로 해상 구조물 기초 보강지반에 대하여 재하시험을 실시하였다. 또한, 실내 모형시험을 실시하여 압밀 특성 및 팩 말뚝의 자립압축강도를 파악하였다. 시험결과, MLPP 공법은 기존의 SCP나 GCP공법에 비하여 침하저감과 응력분담 측면에서 탁월한 효과를 갖는 것으로 나타났다.

• Geomechanics and Engineering
• /
• 제31권2호
• /
• pp.129-147
• /
• 2022

The properties of soil are naturally highly variable and thus, to ensure proper safety and reliability, we need to test a large number of samples across the length and depth. In pile foundations, conducting field tests are highly expensive and the traditional empirical relations too have been proven to be poor in performance. The study proposes a state-of-art Particle Swarm Optimization (PSO) hybridized Artificial Neural Network (ANN), Extreme Learning Machine (ELM) and Adaptive Neuro Fuzzy Inference System (ANFIS); and comparative analysis of metaheuristic models (ANN-PSO, ELM-PSO, ANFIS-PSO) for prediction of bearing capacity of pile foundation trained and tested on dataset of nearly 300 dynamic pile tests from the literature. A novel ensemble model of three hybrid models is constructed to combine and enhance the predictions of the individual models effectively. The authenticity of the dataset is confirmed using descriptive statistics, correlation matrix and sensitivity analysis. Ram weight and diameter of pile are found to be most influential input parameter. The comparative analysis reveals that ANFIS-PSO is the best performing model in testing phase (R² = 0.85, RMSE = 0.01) while ELM-PSO performs best in training phase (R² = 0.88, RMSE = 0.08); while the ensemble provided overall best performance based on the rank score. The performance of ANN-PSO is least satisfactory compared to the other two models. The findings were confirmed using Taylor diagram, error matrix and uncertainty analysis. Based on the results ELM-PSO and ANFIS-PSO is proposed to be used for the prediction of bearing capacity of piles and ensemble learning method of joining the outputs of individual models should be encouraged. The study possesses the potential to assist geotechnical engineers in the design phase of civil engineering projects.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 1994년도 가을 학술발표회 논문집
• /
• pp.87-93
• /
• 1994

Factors which affect the capacity and the soil plug condition of an open-ended pile can be broadly divided into three categories:i.e., pile conditions, soil conditions and penetration methods. It has been found that the relative density and the horizontal stress have much effects on the soil plug behavior than other soil conditions. Also, it has been found that the pile diameter is the most important factor among pile conditions. However, a few investigations have been performed to account for both soil conditions and pile conditions. In this paper, a number of calibration chamber tests have been conducted with three different sized open-ended model piles. The model pile was driven into siliceous sand, with varying soil conditions, to clarify coupled effects of pile diameter and soil conditions on the plug behavior, the capacity, and the load trasfer mechanixm of soil plug. The model piles are composed of two stainless steel pipes so as to measure the plug capacity, the tip resistance, and the outside skin friction. separately.

• 한국지반공학회논문집
• /
• 제34권6호
• /
• pp.5-16
• /
• 2018

본 연구에서는 수평하중을 받는 연직 및 경사말뚝에 대하여 실내 대형 모형실험을 수행하여 무리말뚝의 배열방법과 경사각도에 따른 무리말뚝의 수평지지력 특성을 파악하였다. 또한 말뚝직경(D), 말뚝의 중심간격, 말뚝길이, 지반면 상부 말뚝돌출길이, 상재하중 등을 변화시켜 무리말뚝의 거동에 미치는 영향을 파악하였다. 이러한 실험 결과로부터 수평하중을 받는 $2{\times}2$ 배열 무리말뚝의 경우, 말뚝을 수직으로 시공하는 것보다 양쪽으로 경사지게 시공하는 것이 더 유리한 것으로 나타났다. 그리고 무리말뚝에서 수평지지력에 미치는 요소에 대한 실험 결과, 무리말뚝에 가장 큰 영향을 미치는 요소는 말뚝길이인 것으로 나타났다. 근입깊이비(L/D)가 26.5에서 36.5로 커지면, 수평지지력이 3~4배 이상 증가하는 것으로 나타났다. 그러나 말뚝 중심간격, 말뚝돌출길이 및 상재하중은 무리말뚝의 수평지지력에 큰 영향을 미치는 못하는 것으로 나타났다.

• 한국지반공학회논문집
• /
• 제15권6호
• /
• pp.29-44
• /
• 1999

본 논문은 균질 및 비균질의 사질토 지반에서 항타 시공된 단일 강성말뚝의 수평거동에 대한 모형실험 결과들을 고찰하였다. 본 연구의 목적은 말뚝의 수평거동 특성에 대한 말뚝 시공상태 (Driven & Embedded), 말뚝 근입길이에 대한 하부지반의 두께비 (H/L),그리고 지반의 상대밀도의 영향에 관하여 실험적인 연구를 수행하고 이러한 영향들을 정량화 할 수 있는 실험결과를 얻었다. 모형 실험 결과들에 의하면, 수평거동은 느슨한 균질지반에서 시공방법에 상당히 의존하는 것으로 나타났다. 말뚝시공시 항타방법에 의존할 경우 균질지반에서는 느슨한 지반일수록 그리고 비균질 지반 $(E_{h1}/E_{h2}/=0.18)$에서는 상부층 두께가 클수록 수평변위 감소에 상당한 효과를 얻을 수 있으나, 최대 휨모멘트 감소는 수평변위 감소와 정반대의 결과를 나타냈다. 수평변위 측면에서, 매입말뚝에 대한 항타말뚝의 변위비 $(y_{Driven}y_{Embedded})$는 균질지반의 각 상대 밀도에 대하여 0.65-0.88 $(D_r=90%)$와 0.38-0.65 (D$_{r}$=61.8%)의 범위로 그리고 비균질지반에서 0.6-0.88 의 범위로 나타났다. 또한, 본 연구에서는 $y_D/y_E \;와\; NBM_D/MBM_E$에 대한 항타고와 H/L의 영향들을 모형실험 결과들로부터 실험식으로 제안하였다.

• Geomechanics and Engineering
• /
• 제23권2호
• /
• pp.139-149
• /
• 2020

Piles are widely used in structural foundations of engineering projects. However, the deformation of the soil around the pile caused by driving process has an adverse effect on adjacent existing underground buildings. Many previous studies have addressed related problems in sand and saturated clay. Nevertheless, the failure mechanism of pile driving in unsaturated soil remains scarcely reported, and this issue needs to be studied. In this study, a modeling test system based on particle image velocimetry (PIV) was developed for studying deformation characteristics of pile driving in unsaturated silt with different water contents. Meanwhile, a series of direct shear tests and soil-water characteristic curve (SWCC) tests also were conducted. The test results show that the displacement field shows an apparent squeezing effect under the pile end. The installation pressure and displacement field characteristics are sensitive to the water content. The installation pressure is the largest and the total displacement field is the smallest, for specimens compacted at water content of 11.5%. These observations can be reasonably interpreted according to the relevant unsaturated silt theory derived from SWCC tests and direct shear tests. The variation characteristics of the soil displacement field reflect the macroscopic mechanical properties of the soil around the pile.

• 산업기술연구
• /
• 제15권
• /
• pp.147-152
• /
• 1995

The purpose of this paper is to analyze the bearing capacity, settlement and pile action of pile groups in cohesionless soil, based on a wide range of model test in laboratory. Model test were conducted with changing the variables affecting the behavior of group pile; Number of pile, Diameters, Spacings between piles and Arrangement of piles. Effects of these variables on group efficiency were investigated by analyzing test results. Test results were also compared with the existing analytical method and data obtained in-situ tests.