• 한국철도학회논문집
• /
• 제10권2호
• /
• pp.131-136
• /
• 2007

In this paper, the methodology to predict the number of deaths and possible fire propagation scenarios will be described in case of fire on a train in a tunnel. We use a probabilistic analysis method for the evaluation of possibility for each scenario and the deaths tolls are calculated with the help of the passenger evacuation simulation program. The resulting safety of passengers is displayed on a F/N graph, which could be used in part as a guideline to predict the safety level of the tunnel in fire.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2000년도 가을 학술발표회 논문집
• /
• pp.501-508
• /
• 2000

In recent years, as lines are selected In disadvantageous region, unavoidable developments is increased. Owing to such developments. environmental problems have been occurred frequently, In excavation of tunnels especially located in close to slope, uneven stress take place to tunnel due to a topographical factor. it is used assistant methods of construction which are excavation of slope, retaining wall, ground anchor, etc for uneven stress. these assistant methods raise problems of environmental. In this study, using slit, we could make better stress state by means of inducing stress concentration in boundary of tunnel. considering a variety of slit and rock mass condition, we use numerical analysis.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권9호
• /
• pp.3797-3822
• /
• 2020

The inspection of cracks on the surface of tunnel linings is a common method of evaluate the condition of the tunnel. In particular, determining the thickness and shape of a crack is important because it indicates the external forces applied to the tunnel and the current condition of the concrete structure. Recently, several automatic crack detection methods have been proposed to identify cracks using captured tunnel lining images. These methods apply an image-segmentation mechanism with well-annotated datasets. However, generating the ground truths requires many resources, and the small proportion of cracks in the images cause a class-imbalance problem. A weakly annotated dataset is generated to reduce resource consumption and avoid the class-imbalance problem. However, the use of the dataset results in a large number of false positives and requires post-processing for accurate crack detection. To overcome these issues, we propose a crack detection method using a ternary classifier. The proposed method significantly reduces the false positive rate, and the performance (as measured by the F1 score) is improved by 0.33 compared to previous methods. These results demonstrate the effectiveness of the proposed method.

• 대한설비공학회:학술대회논문집
• /
• 대한설비공학회 2008년도 동계학술발표대회 논문집
• /
• pp.67-70
• /
• 2008

As a part of the project on road tunnel fire safety system development, Quantitative Risk Assessment program was developed. In this study, We carried out Quantitative Risk Assessment with this program by using a factor of cross passage interval, warning announcement time and congestion ratio etc for 1km tunnel with natural ventilation. In the case of 250m below of cross passage interval, Risk value due to warning announcement time was a slightly changed. but if cross passage interval is more than 250m, expected fatalities in the same HRR(heat release rate) was sharp increased. As a result, Quantitative Risk Assessment program which was developed in this research project is possible to risk assessment with ventilation type, cross passage for evacuation and detection system response property etc. hereafter, this program look forward to use as a tool for road tunnel performance based design.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2007년 가을학술발표회
• /
• pp.160-169
• /
• 2007

In this study, Analyzed stress history, state of stress, ratio of stress/strength to use FEM. Fault Zone depth is 3m, 6m, 9m, 12m and 15m for study, and also Distance is 3m, 6m, 9m, 12m and 15m at center of tunnel with thickness 3m fault zone. It is not appeared that Arching in stress state and stress history by FEM. On the other hand, excessive shear stress and high compressive stress happened. Therefore, Tunnel design is desirable that do it so that state of stress that is the imbalance may be uplemented. it is important that examine each state of stress and stress history in detail tunnel design.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2001년도 가을 학술발표회 논문집
• /
• pp.27-33
• /
• 2001

Objective of this study is to investigate the structural behavior of the concrete lining in water pressure tunnel. In many cases, the concrete lining of water pressure tunnel has not considered as a major structure comparing to the other structures, resulting in use of conservative analysis and design. For the detailed analysis of concrete lining of water pressure tunnel, factors such as rock pressure and water pressure have to be considered. In this study, analysis of concrete lining was performed by using beam element method, shell element method and solid element method. Analysis results showed that the tensile stress at crown of concrete lining is greatly affected by the stability of concrete lining and the tensile stress for the concrete lining has to be evaluated for the section where maximum moment is occurred.

• 한국암반공학회:학술대회논문집
• /
• 한국암반공학회 2008년도 국제학술회의
• /
• pp.43-51
• /
• 2008

Currently an increasing number of urban tunnels with small overburden are excavated according to the principle of the New Austrian Tunneling Method (NATM). For rational management of tunnels from planning to construction and maintenance stages, prediction, control and monitoring of displacements of and around the tunnel have to be performed with high accuracy. Computational method tools, such as finite element method, have been and are indispensable tool for tunnel engineers for many years. It is, however, a commonly acknowledged fact that determination of input parameters, especially material properties exhibiting nonlinear stress-strain relationship, is not an easy task even for an experienced engineer. Use and application of the acquired tunnel information is important for prediction accuracy and improvement of tunnel behavior on construction. Artificial Neural Network (ANN) model is a form of artificial intelligence that attempts to mimic behavior of human brain and nervous system. The main objective of this paper is to perform the deformation analysis in NATM tunnel by means of numerical simulation and artificial neural network (ANN) with field database. Developed ANN model can achieve a high level of prediction accuracy.

• 산업기술연구
• /
• 제26권A호
• /
• pp.3-15
• /
• 2006

To determine the optimum ventilation systems during long tunnel excavation, the velocity vector profile and the contaminant's distribution at working place are studied using 2-D, 3-D numerical analysis. The main results can be summarized as follow; In case of long tunnels, blower-exhaust-mixture types which enable to use soft blast ducts is most appropriate in terms of ventilation and economical efficiency. Of the same ventilation types, ventilation efficiency has a difference according to blast ducts and the distance between fan and working place. The 3-D numerical result shows that arranging blower and exhaust ducts in the right and left corners of the tunnel respectively is effective to discharge contaminant. The result of the real measurement shows that CO concentration can be reduced to below 50 ppm, which is regulation value, as 16-minutes fan operation goes on.

• Geomechanics and Engineering
• /
• 제31권6호
• /
• 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.

• 지질공학
• /
• 제22권3호
• /
• pp.323-330
• /
• 2012

국내 터널현장에서는 기존 H형 강지보를 대체하는 격자지보의 사용이 급격히 증가되고 있다. 터널에 작용하는 지반하중은 숏크리트와 격자지보에 의하여 지지된다. 따라서 터널의 안정성을 평가하기 위해서는 격자지보에 대한 계측이 필수적이다. 그러나 현재까지 국내에서는 격자지보에 대한 계측이 거의 수행되지 않았으며 적절한 계측 방법도 확립 되지 못한 상태이다. 본 연구에서는 격자지보용 로드셀을 이용한 신뢰성 있는 격자지보 계측 방법을 제안하였다. 또한 시공 중인 터널현장에서 격자지보 계측을 수행하여 격자지보에 작용하는 지반하중을 제시하였다.