• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.5
• /
• pp.431-449
• /
• 2022

As many tunnels generally have been constructed, various experiences and techniques have been accumulated for tunnel design as well as tunnel construction. Hence, there are not a few cases that, for some usual tunnel design works, it is sufficient to perform the design by only modifying or supplementing previous similar design cases unless a tunnel has a unique structure or in geological conditions. In particular, for a tunnel blast design, it is reasonable to refer to previous similar design cases because the blast design in the stage of design is a preliminary design, considering that it is general to perform additional blast design through test blasts prior to the start of tunnel excavation. Meanwhile, entering the industry 4.0 era, artificial intelligence (AI) of which availability is surging across whole industry sector is broadly utilized to tunnel and blasting. For a drill and blast tunnel, AI is mainly applied for the estimation of blast vibration and rock mass classification, etc. however, there are few cases where it is applied to blast pattern design. Thus, this study attempts to automate tunnel blast design by means of machine learning, a branch of artificial intelligence. For this, the data related to a blast design was collected from 25 tunnel design reports for learning as well as 2 additional reports for the test, and from which 4 design parameters, i.e., rock mass class, road type and cross sectional area of upper section as well as bench section as input data as well as16 design elements, i.e., blast cut type, specific charge, the number of drill holes, and spacing and burden for each blast hole group, etc. as output. Based on this design data, three machine learning models, i.e., XGBoost, ANN, SVM, were tested and XGBoost was chosen as the best model and the results show a generally similar trend to an actual design when assumed design parameters were input. It is not enough yet to perform the whole blast design using the results from this study, however, it is planned that additional studies will be carried out to make it possible to put it to practical use after collecting more sufficient blast design data and supplementing detailed machine learning processes.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.6
• /
• pp.617-628
• /
• 2022

A ground support pattern should be designed by properly integrating various support materials in accordance with the rock mass grade when constructing a tunnel, and a technical decision must be made in this process by professionals with vast construction experiences. However, designing supports at the early stage of tunnel design, such as feasibility study or basic design, may be very challenging due to the short timeline, insufficient budget, and deficiency of field data. Meanwhile, the design of the support pattern can be performed more quickly and reliably by utilizing the machine learning technique and the accumulated design data with the rapid increase in tunnel construction in South Korea. Therefore, in this study, the design data and ground exploration data of 48 road tunnels in South Korea were inspected, and data about 19 items, including eight input items (rock type, resistivity, depth, tunnel length, safety index by tunnel length, safety index by rick index, tunnel type, tunnel area) and 11 output items (rock mass grade, two items for shotcrete, three items for rock bolt, three items for steel support, two items for concrete lining), were collected to automatically determine the rock mass class and the support pattern. Three machine learning models (S1, A1, A2) were developed using two machine learning algorithms (SVR, ANN) and organized data. As a result, the A2 model, which applied different loss functions according to the output data format, showed the best performance. This study confirms the potential of support pattern design using machine learning, and it is expected that it will be able to improve the design model by continuously using the model in the actual design, compensating for its shortcomings, and improving its usability.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.23 no.5
• /
• pp.325-337
• /
• 2021

On the road and rail tunnels, the evacuation pathway and facilities such as smoke-control and fire suppression system are essential in tunnel fire. In the long twin tunnels, the cross-connection tunnel is usually designed to evacuate from the tunnel where the fire broke out to the other tunnel. In twin shield tunnels, the segment lining has to be demolished to construct the cross-connection tunnel. Considering the modern shield TBM is mostly the closed chamber type, the exposure of underground soil induced by removal of steel segment lining is the most danger construction step in the shield tunnel construction. This case study introduces the excavation method using the thrust of large steel pipe and reviews the measured data after the construction. The large steel pipe thrust method for the cross-connection tunnel can stabilize the excavated face with the two mechanisms. Firstly, the soil in front of excavated face is cylindrically pre-supported by the large steel pipe. Secondly, the excavated face is supported by the plugging effect caused by the soil pressed into the steel pipe. It was reviewed that the large steel pipe thrust method in the cross-connection tunnel is enough to secure the construct ability and stability in soil from the measurement results about the deformation and stress of steel pipe.

• Proceedings of the Korean Geotechical Society Conference
• /
• 1998.04a
• /
• pp.47-60
• /
• 1998

It is considered in this paper that the main causes of tunnel collapse during the construction were the insufficiency of data of geotechnical investigations, or their limits due to special ground condition such as its heterogeneity and anisotropy It is thought that safety of ground can be affected by the geological conditions such as presences of discontinuities in good intact rocks, and considered to be necessary that awareness of the conditions of discontinuities in advance is important to apply adequate reinforcement measures. It is also shown that a serious accident had occurred because of the unawareness of the permeable alluvial deposits at the top of the tunnel. And it is shown that the example of application of the results of geotechnical investigation such as face-mapping, pilot boring etc. during tunnel construction, and a serious deformation of tunnel under special geological condition. Therefore, it is strongly recommended to perform an adequate geotechnical investigation to confirm the geotechnical conditons of ground before design, and supplimentary investigation is also needed depending on conditions for safe and econonic construction.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2010.03a
• /
• pp.562-570
• /
• 2010

This study was conducted to estimate the number of disc cutter consumption and to predict amount of disc cutters when a shield TBM(Tunnel Boring Machine) of the Han Riverbed Tunnel was applied. In fact, it is almost impossible to change the machine after starting the excavation using the shield TBM method. Therefore, it is important to design an appropriate equipment in the shield method - an efficiency choice of the operation equipment plays a key role in the shield tunnel processing. For the above reason, the disc cutter consumption prediction is quite important so that the detailed analysis is required. A number of disc cutter consumption was predicted by the three methods, viz. KOMATSU, MITSUBISHI and NTNU. In addition, the predicted results were compared with field data. The prediction of disc cutter consumption showed that 237 for KOMATSU, 501 for MITSUBISHI, and 634 for NTNU, respectively. However, a total number of 1,263 disc cutter consumption were investigated during the tunnel construction. It was found that there was a huge difference between the predicted and real values of the disc cutter consumption. The more detailed investigation showed that the disc cutter was worn out bluntly in the northbound tunnel, meanwhile it was worn out sharply in the southbound tunnel. In particular, the disc cutter consumption in the southbound tunnel was increased rapidly because of rear abrasion for remaining mucks in the chamber.

• 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.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.5 no.2
• /
• pp.199-207
• /
• 2003

Tunnel modelling in the field of geotechnical engineering essentially requires models of tunnelling machines and the simulation of tunnelling processes to clarify the detailed behaviour of tunnel construction. Modern advanced mechatronics, including construction processes, machinining and control technologies, are making it possible to fabricate such models. These technologies, however, are essentially developed in a gravity field condition and are needed to examine in a 1g or cenrifuge field condition. This paper presents the simulation method for tunnelling processes and the design method for tunnelling machines with special reference to the problem of earth pressure acting on the lining of a shield tunnel. The paper then introduces and verifies the design method for tunnelling machines in the 1g field by means of checking the reproduceability of experiment data and their comparison with data in the field.

• Explosives and Blasting
• /
• v.13 no.3
• /
• pp.19-30
• /
• 1995

NATM as method of tunneling has been applied to construction of domestic subway, roads, rail way, water way etc. Accordingly, we have NATM's many drafts and constructional results, but many problems and accidents have occurred under construction of tunnel using NATM for shortage of technical data. Poorness of constructional improvement, systemic inconsistency etc. Especially, everyone was shocked at Gupo's train wrecking accident lately. The purpose of this thesis is presentation of means for setting technical problems, by looking into Gupo's train wrecking accident and home records that applying NATM in tunneling failed, to minimize future safety accidents we find that the general problems of home fifteen sites having occured accidents is badly geological survey, nonconfirmationi of base rock's state, formal measuring management, shortage of specialists, systemical discrepancy and that disregarding NATM's rules makes general problems. The results of this study are Summarised as follows : 1. We advise repletion of design standards to practice crosshole test for confirming connected rock base on vertical section of tunnel. 2. We advise to practice pre0boring and pre-grouting for a weak layer difficult in applying NATM. 3. We advise systemic improvements that field servicer can construct tunnel of his own free will considering base rock's state at tunnel . 4. We advise that specialist, who can make a conduct and supervise above mentioned items as well as measuring management, should be posted at field.

• Special Issue of the Society of Naval Architects of Korea
• /
• 2015.09a
• /
• pp.74-78
• /
• 2015

When floating platform or drilling unit is located at operating station during its design life, it has to have the sufficient stability considering external environment. To evaluate whether offshore structure is complied with the required design criteria for intact stability, the factors which decrease the righting moment have to be considered. Wind heeling moment is one of main factors because the direction is opposite to the righting moment. According to 2009 MODU CODE (Code for the construction and equipment of Mobile Offshore Drilling Units, 2009), wind heeling moment derived from wind tunnel test on scale model of offshore structure enables to apply as alternative given formula and method in 2009 MODU CODE. However, there is no the specific method for applying data derived from wind tunnel test. Based on the following reasons, this paper presents that the calculation method of wind heeling moment utilizing non-dimensional coefficient relative to wind loads (wind forces and moments) and the comparison with each method applying an example.

• Wind and Structures
• /
• v.36 no.6
• /
• pp.423-434
• /
• 2023

Aerodynamic force coefficients are generally obtained from traditional wind tunnel tests or computational fluid dynamics (CFD). Unfortunately, the techniques mentioned above can sometimes be cumbersome because of the cost involved, such as the computational cost and the use of heavy equipment, to name only two examples. This study proposed to build a deep neural network model to predict the aerodynamic force coefficients based on data collected from CFD simulations to overcome these drawbacks. Therefore, a series of CFD simulations were conducted using different geometric parameters to obtain the aerodynamic force coefficients, validated with wind tunnel tests. The results obtained from CFD simulations were used to create a dataset to train a multilayer perceptron artificial neural network (ANN) model. The models were obtained using three optimization algorithms: scaled conjugate gradient (SCG), Bayesian regularization (BR), and Levenberg-Marquardt algorithms (LM). Furthermore, the performance of each neural network was verified using two performance metrics, including the mean square error and the R-squared coefficient of determination. Finally, the ANN model proved to be highly accurate in predicting the force coefficients of similar bridge sections, thus circumventing the computational burden associated with CFD simulation and the cost of traditional wind tunnel tests.