• Geomechanics and Engineering
• /
• v.31 no.6
• /
• pp.545-556
• /
• 2022

Evaluation and optimization of tunnel wall convergence (TWC) plays a vital role in preventing potential problems during tunnel construction and utilization stage. When convergence occurs at a high rate, it can lead to significant problems such as reducing the advance rate and safety, which in turn increases operating costs. In order to design an effective solution, it is important to accurately predict the degree of TWC; this can reduce the level of concern and have a positive effect on the design. With the development of soft computing methods, the use of deep learning algorithms and neural networks in tunnel construction has expanded in recent years. The current study aims to employ the long-short-term memory (LSTM) deep neural network predictor model to predict the TWC, based on 550 data points of observed parameters developed by collecting required data from different tunnelling projects. Among the data collected during the pre-construction and construction phases of the project, 80% is randomly used to train the model and the rest is used to test the model. Several loss functions including root mean square error (RMSE) and coefficient of determination (R²) were used to assess the performance and precision of the applied method. The results of the proposed models indicate an acceptable and reliable accuracy. In fact, the results show that the predicted values are in good agreement with the observed actual data. The proposed model can be considered for use in similar ground and tunneling conditions. It is important to note that this work has the potential to reduce the tunneling uncertainties significantly and make deep learning a valuable tool for planning tunnels.

• Geomechanics and Engineering
• /
• v.37 no.1
• /
• pp.65-72
• /
• 2024

Water ingress poses a common and intricate geological hazard with profound implications for tunnel construction's speed and safety. The project's success hinges significantly on the precision of estimating water inflow during excavation, a critical factor in early-stage decision-making during conception and design. This article introduces an optimized model employing the gene expression programming (GEP) approach to forecast tunnel water inflow. The GEP model was refined by developing an equation that best aligns with predictive outcomes. The equation's outputs were compared with measured data and assessed against practical scenarios to validate its potential applicability in calculating tunnel water input. The optimized GEP model excelled in forecasting tunnel water inflow, outperforming alternative machine learning algorithms like SVR, GPR, DT, and KNN. This positions the GEP model as a leading choice for accurate and superior predictions. A state-of-the-art machine learning-based graphical user interface (GUI) was innovatively crafted for predicting and visualizing tunnel water inflow. This cutting-edge tool leverages ML algorithms, marking a substantial advancement in tunneling prediction technologies, providing accuracy and accessibility in water inflow projections.

• Proceedings of the Korean Society of Soil and Groundwater Environment Conference
• /
• 2002.04a
• /
• pp.167-172
• /
• 2002

Seoul subway system has been constructed to solve traffic difficulties of Seoul metropolitan, and now is the major public transportation. However, the more line has added in the system the deeper the bottom of the tunnel base. And a huge amount of groundwater along the line has seeping into the tunnel. Several subway stations has pumping system to extract the groundwater to the outside and consequently, groundwater table along the line has declined gradually. Groundwater table has dropped about 40 meters at some areas, There was some study for the proper usage of the abstracted groundwater and the project to use the groundwater has launched already by the local government. However. more serious problem is expected on quality degradation of soil and groundwater as the decline of groundwater table along the subway line. This study suggests that the detailed groundwater environmental study should be made as soon as possible for this. If there is any pollution leaking at the surface area of the groundwater depression, the pollution will be seep into the subway tunnel in some day even though the time will be different with the soil material and hydraulic characteristics of the aquifer. And the polluted area of the soil and groundwater would be enlarged along the pathway The study on possibility of the soil subsidence and reducing surface water flow in small creek were also needed. This study suggest one of the counter measurement that restoring the declined groundwater table after groundwater environmental study

• Proceedings of the Korean Geotechical Society Conference
• /
• 2005.10a
• /
• pp.198-209
• /
• 2005

Overbreak or underbreak is one of the most important factors in evaluation the results of a tunnel blasting. Overbreak, which depends on the quality of rock, the type and quantity of explosives, and the method and condition of drilling, has been a target of challenge to many blasting engineers as it is connected with economic directly. Drilling is generally known as a primary one of overbreak producing factors. So, This study presented the practical solution to reduce overbreak, which was caused by drilling, through the analyses of how to make a drilling process accurate and how to evaluate the effect of each drilling method. Thus, this solution would give a quantitative analysis of overbreak and provide the information of how to reduce the quantity of overbreak. Moreover, for verifying this solution, we applied it to a tunnel project and then have found out that the quantity of overbreak decreased to approximately 10-40% compared with the previous way of overbreak control.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2007.11a
• /
• pp.872-875
• /
• 2007

Estimation of total construction period and cost in the early stage of the project is very important. Simulation is one of the method considering proper compound such as tools, materials for effective construction management and estimating and analysing affected factors to construction through making suitable process. This study is to develop the model by using Arena simulation considering limited facts like blast time in a subway tunnel construction of both sides inner city. Developed model is easily useful type by using Visual Basic program, and can obtain total construction period and cost as a result. It could be used as a decision making tool in early stage of the construction.

• Geomechanics and Engineering
• /
• v.29 no.5
• /
• pp.523-533
• /
• 2022

Several prediction model of penetration rate (PR) of tunnel boring machines (TBMs) have been focused on applying to design stage. In construction stage, however, the expected PR and its trends are changed during tunneling owing to TBM excavation skills and the gap between the investigated and actual geological conditions. Monitoring the PR during tunneling is crucial to rescheduling the excavation plan in real-time. This study proposes a sequential prediction method applicable in the construction stage. Geological and TBM operating data are collected from Gunpo cable tunnel in Korea, and preprocessed through normalization and augmentation. The results show that the sequential prediction for 1 ring unit prediction distance (UPD) is R²≥0.79; whereas, a one-step prediction is R²≤0.30. In modeling algorithm, a gradient boosted regression tree (GBRT) outperformed a least square-based linear regression in sequential prediction method. For practical use, a simple equation between the R² and UPD is proposed. When UPD increases R² decreases exponentially; In particular, UPD at R²=0.60 is calculated as 28 rings using the equation. Such a time interval will provide enough time for decision-making. Evidently, the UPD can be adjusted depending on other project and the R² value targeted by an operator. Therefore, a calculation process for the equation between the R² and UPD is addressed.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2006.10a
• /
• pp.169-178
• /
• 2006

The pumped-storage power system is the one of the hydroelectric power systems, generating electricity with hydraulic head difference. In this system, the electricity is produced during the hours of peak demand by using water that has been pumped into an upper reservoir from a lower reservoir during the hours of low demand. Generally, the system consists of an under-ground power house and tunnels such as the headrace, pressure, and tailrace tunnels. The Chungsong pumped-storage power station is the sixth one In the pumped-storage power station in Korea. Both the regional self-government and the population of chungsong -Goon had made a great effort to draw this power station construction into this area. The proposed Chungsong pumped-power station construction project was accepted by the central government as a part of the national electricity plan for the first time in Korea.

• Journal of the Korea Construction Safety Engineering Association
• /
• s.54
• /
• pp.41-55
• /
• 2011

The current railway projects under plan, design, or construction have been designed as 'very long and deep underground tunnel'. Therefore, it is reasonable that the standards for preventing disaster in such conditions should be intensified in order to avoid repeating the same failure which happened in Daegu subway disaster, Although we consent to the opinion that nothing can compete with human being's life, it is very difficult to protect the life from all of potential disasters perfectly in railway fields because the excessive standards can result in excess construction cost, which can bring about cancelation of the project itself eventually. Therefore optimized disaster design standard is required to negotiate the conflict between economical cost and social tolerance limitation simultaneously.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.17 no.4
• /
• pp.294-306
• /
• 2005

Most immersed tunnels investigated have been investigated based on the engineer's experience with design and construction. From engineering point of view, it is very important to understand the wave interaction with the seabed and immersed tunnel, since the stability of an immersed tunnel depends largely on the behavior of the seabed foundation. In this study, for the first stage research to find out the mechanism of the wave interaction with the seabed and immersed tunnel, the benchmarking method called as direct numerical simulation (DNS) was employed to analyze comprehensively the wave-induced pore water pressures, vorticity and flows in seabed or inside rubble stone around the immersed tunnel. The immersed tunnel is modeled based on Busan-Geoje fixed link project in Korea, which is now on the stage of planning. Moreover, the nonlinear water wave interaction with an immersed tunnel/its seabed foundation was thoroughly examined with regard to the stabilities of the immersed tunnel subjected to various water wave conditions, median grain size and so forth.

• Journal of the Korean Geotechnical Society
• /
• v.23 no.3
• /
• pp.25-40
• /
• 2007

Excessive earth pressure is one of the major mechanical factors in the deformation and damage of Cut-and-Cover Tunnel lining in shallow tunnels and portals of mountain tunnels (Kim, 2000). Excessive earth pressure may be attributed to insufficient compaction and consolidation of backfill material due to self-weight, precipitation and vibration caused by traffic (Komiya et al., 2000; Taylor et al., 1984; Yoo, 1997). Even though there were a lot of tests performed to determine the earth pressure acting on the tunnel lining, unfortunately there were almost no case histories of studies performed to determine remedial measures that reduce differential settlement and excessive earth pressure. In this study the installation of geotextile mat was selected to reduce the differential settlement and excessive earth pressure acting on the cut-and-cover tunnel lining. In order to determine settlement and earth pressure reduction effect (reinforcement effect) of geotextile mat reinforcement, laboratory tunnel model tests were performed. This study was limited to the modeling of rigid circular cut-and-cover tunnel constructed at a depth of $1.0D\sim1.5D$ in loose sandy ground and subjected to a vibration frequency of 100 Hz. Model tests with varying soil cover, mat reinforcement scheme and slope roughness were performed to determine the most effective mat reinforcement scheme. Slope roughness was adjusted by attaching sandpaper #100, #400 and acetate on the cut slope surface. Mat reinforcement effect of each mat reinforcement scheme were presented by the comparison of earth pressure obtained from the unreinforced and mat reinforced model tests. Soil settlement reduction was analyzed and presented using the Picture Analysis Method (Park, 2003).