• Tunnel and Underground Space
• /
• v.30 no.5
• /
• pp.462-472
• /
• 2020

Rock classification is fundamental discipline of exploring geological and geotechnical features in a site, which, however, may not be easy works because of high diversity of rock shape and color according to its origin, geological history and so on. With the great success of convolutional neural networks (CNN) in many different image-based classification tasks, there has been increasing interest in taking advantage of CNN to classify geological material. In this study, a feasibility of the deep CNN is investigated for automatically and accurately identifying rock types, focusing on the condition of various shapes and colors even in the same rock type. It can be further developed to a mobile application for assisting geologist in classifying rocks in fieldwork. The structure of CNN model used in this study is based on a deep residual neural network (ResNet), which is an ultra-deep CNN using in object detection and classification. The proposed CNN was trained on 10 typical rock types with an overall accuracy of 84% on the test set. The result demonstrates that the proposed approach is not only able to classify rock type using images, but also represents an improvement as taking highly diverse rock image dataset as input.

• Tunnel and Underground Space
• /
• v.22 no.6
• /
• pp.429-437
• /
• 2012

This study predicted temperature in the disposal tunnels using computational fluid dynamics based on natural ventilation quantity that comes from high altitude and temperature differences that are the characteristics of high level waste repository. The result of the previous study that evaluated quantitatively natural ventilation quantity using a hydrostatic method and CFD shows that significant natural ventilation quantity is generated. From the result, this study performed the prediction of temperature in disposal tunnels by natural ventilation quantity by the caloric values of the wastes, at both deep geological repository and surface repository. The result of analysis shows that deep geological repository is effective for thermal control in the disposal tunnels due to heat transfer to rock and the generation of sufficient natural ventilation quantity, while surface repository was detrimental to thermal control, because surface repository was strongly affected by external temperature, and could not generate sufficient natural ventilation quantity. Moreover, this study found that in the case of deep geological repository with a depth of 200 m, the heatof about $10^{\circ}C$ was transferred to the depth of 500 m. Thus, it is considered that if the high level waste repository scheduled to be built in the country is designed placing an emphasis on thermal control, deep geological repository rather than surface repository is more appropriate.

• Tunnel and Underground Space
• /
• v.29 no.6
• /
• pp.439-455
• /
• 2019

A buffer is the major component of a high level radioactive waste repository. Due to their thermal conductivity and low permeability, bentonites have been considered as a key component of a buffer system in most countries. The deep geological condition generates ground water inflow and results in swelling pressure in the buffer and backfill. Investigation of swelling pressure of bentonite buffer is an important task for the safe disposal system. The swelling pressure that can be critical is affected by mechanical and hydro properties of the system. Therefore, in this study, a sensitivity analysis was conducted to examine the effect of hydro-mechanical (HM) behaviors in the MX-80 bentonite. Based on the results of the swelling pressure generation with HM model parameters, a coupled HM analysis of an unsaturated buffer and backfill in a deep geological repository was also carried out to investigate the major factor of the swelling pressure generation.

• Tunnel and Underground Space
• /
• v.34 no.3
• /
• pp.208-217
• /
• 2024

There is so much research effort for developing and implementing deep learning-based surveillance systems to manage health and safety issues in construction sites. Especially, the development of deep learning-based object detection in various environmental changes has been progressing because those affect decreasing searching performance of the model. Among the various environmental variables, the accuracy of the object detection model is significantly dropped under low illuminance, and consistent object detection accuracy cannot be secured even the model is trained using low-light images. Accordingly, there is a need of low-light enhancement to keep the performance under low illuminance. Therefore, this paper conducts a comparative study of various deep learning-based low-light image enhancement models (GLADNet, KinD, LLFlow, Zero-DCE) using the acquired construction site image data. The low-light enhanced image was visually verified, and it was quantitatively analyzed by adopting image quality evaluation metrics such as PSNR, SSIM, Delta-E. As a result of the experiment, the low-light image enhancement performance of GLADNet showed excellent results in quantitative and qualitative evaluation, and it was analyzed to be suitable as a low-light image enhancement model. If the low-light image enhancement technique is applied as an image preprocessing to the deep learning-based object detection model in the future, it is expected to secure consistent object detection performance in a low-light environment.

• Tunnel and Underground Space
• /
• v.34 no.4
• /
• pp.330-354
• /
• 2024

In site characterization of high-level radioactive waste, discontinuity(joint) distribution and rock mass classification, which are key evaluation parameters in the rock engineering field, were evaluated using deep boreholes in the Wonju granite and Chuncheon granite, which belong to Mesozoic Jurassic era. To evaluate joint distribution characteristics, fracture zones and joint surfaces extracted from ATV data were used, and major joint sets were evaluated along with joint frequency according to depth, dip direction, and dip. Both the Wonju and Chuncheon granites that were studied showed a tendency for the frequency of joints to increase linearly with depth, and joints with high angles were relatively widely distributed. In addition, relatively large amounts of weathering tended to occur even in deep depth due to groundwater inflow through high-angle joints. RQD values remained consistently low even at considerable depth. Meanwhile, joint groups with low angles showed different joint characteristics from joint sets with high angles. Rock mass classification was performed based on RMR system, and along with rock mass classification for 50 m intervals where uniaxial compressive strength was performed, continuous rock mass classification according to depth was performed using velocity log data and geostatistical techniques. The Wonju granite exhibited a superior rock mass class compared to the Chuncheon granite. In the 50 m interval and continuous rock mass classification, the shallow part of the Wonju granite showed a higher class than the deep part, and the deep part of the Chuncheon granite showed a higher class than the shallow part.

• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.1306-1312
• /
• 2011

Underground Subway station's air pollutants are introduced from the indoor or outdoor. And Radon is a major pollutant in the subway station. Radioactive substances Radon is occuring naturally in granite tunnel wall and underground water. Especially inert gas Radon that causes lung cancer in human is anywhere but 5678 S.M.R.T. tunnels deep and pass through the granite plaque have a lot of Radon. The Radon concentration is determined by the following reasons : radon content of soil and concrete, underground water, ventilation, pressure difference, building structure, temperature, etc. So Radon concentration is hard to predict. And we can't only ventilate owing to era of high oil prices. This study focuses on our efforts for the reduction of Radon concentration. And the purpose is to provide basically datas of specially managed 15 subway station's Radon concentration.

• Geomechanics and Engineering
• /
• v.5 no.2
• /
• pp.99-118
• /
• 2013

Construction of the extension project of the Bangkok MRT Blue Line underground railway was recently started in 2011. The construction of approximately 5 km long underground tunnel and 4 deep excavations of underground station are considered to be the most important geotechnical works. The pressuremeter was selected as a high-quality in situ testing of the soil to evaluate design parameters for the project. In addition, other field and laboratory tests such as vane shear and $CK_0U$ triaxial tests were included in the investigation programme. This paper aims to present the ground conditions encountered along the MRT Blue Line extension project as well as the site investigation and interpretation techniques with particular focus on the pressuremeter tests. The results are also compared with the pressuremeter investigation from the previous Bangkok MRT project.

• Journal of computational fluids engineering
• /
• v.9 no.1
• /
• pp.10-17
• /
• 2004

Comprehensive investigation according to the two kinds of blades is systematically carried out for a design of the centrifugal blower. The motivation of this work is due to demand of enhanced flow rate with higher inlet pressure, such as air purifiers adopting several filters. It is observed that flow rate of the blower with forward blades is larger than that of the system with backward blades. The reason is due to larger outlet velocity from the rotating forward blades and the tendency is validated by a parallel experiment with a wind tunnel. Numerical analysis for the blower system shows detail information between the blades and inside the casing. A series of figures to show the flow details offers deep understanding of a centrifugal blower with the two different blades.

• Tunnel and Underground Space
• /
• v.2 no.1
• /
• pp.1-10
• /
• 1992

As our global population grows each day, it is apparent that we must find new ways to provide space for habitation and the services necessary to support large urban areas. It is no longer advisable nor acceptable to continue to expand our cities on the surface, encroaching on valuable agricultural land and open space. We must also find ways to be more energy efficient in every aspect of our societies. Effective use of underground space can provide the space necessary to accommodate larger populations and the services necessary for their support in existing urban areas we can also find new ways to utilize underground facilities to improve urban efficiency and function. Underground technology has improved dramatically in the last two decades and continues to evolve to meet a great variety of applications. The confluence of available technology, economic feasibility, and greater acceptance of underground solutions with recognition of the need to change the ways we build and use out urban areas and their surrounding environment indicates that we are witnessing only the beginning of appropriate and innovative use of underground space future generations will indeed 'Think deep'.

• Tunnel and Underground Space
• /
• v.7 no.1
• /
• pp.13-19
• /
• 1997

It is necessary to study on thermo-hydro-mechanical effect at rock mass performing project such as radiowaste disposal in deep rock mass. In this study, thermo-hydro-mechanical coupling analysis which is considered interaction and the variation of rock properties induced by temperature increase was performed for the circular shaft when appling temperature of 20$0^{\circ}C$ at the shaft wall. The shaft is diameter of 2 m and under hydrostatic stress of 5 MPa. In the cases, thermal expansion by temperature increase progress from the wall to outward and thermal expansion could induce tensile stress over the tensile strength of rock mass at the wall. When rock properties were given as a function of temperature, thermal expansion increased, tensile stress zone expanded. Lately, water flow is activated by increase of permeability and decrease of viscosity.