• Journal of the Society of Disaster Information
• /
• v.18 no.4
• /
• pp.922-929
• /
• 2022

Purpose: The purpose of this paper is to develop a deep learning model to detect fire extinguishers in images taken from CCTVs in underground utility tunnels. Method: Various fire extinguisher images were collected for detection of fire extinguishers in the running-based underground utility tunnel, and a model applying the One-stage Detector method was developed based on the CNN algorithm. Result: The detection rate of fire extinguishers photographed within 10m through CCTV video in the underground common area is over 96%, showing excellent detection rate. However, it was confirmed that the fire extinguisher object detection rate drops sharply at a distance of 10m or more, in a state where it is difficult to see with the naked eye. Conclusion: This paper develops a model for detecting fire extinguisher objects in underground common areas, and the model shows high performance, and it is judged that it can be used for underground common area digital twin model synchronizing.

• Tunnel and Underground Space
• /
• v.8 no.1
• /
• pp.17-25
• /
• 1998

This paper investigates coupled thermal, mechanical and hydraulic phenomena in deep rock mass especially for underground heat storage system. Firstly, concepts of underground heat storage were presented and coupling phenomena in this area were illustrated. In order to understand the basic mechanism of thermal, hydraulic and deformation behavior in rock cavern disturbed by thermal gradient about 10$0^{\circ}C$, various numerical experiments were conducted using several codes. The study involves the behavior of fractured rock mass including rock joint. In spite of the limitation of codes modelling fully coupled effects, these codes could be applied in analysis of underground heat storage. The heat loss in rock mass, which is a major factor in heat storage, is insignificant in all results.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2020.11a
• /
• pp.50-51
• /
• 2020

Recently, various maintenance materials and construction methods have been developed to secure the sustainable performance of structures. However, waterproofing of underground structures where groundwater infiltration is present is very difficult. In particular, the location of underground structures such as subways is very deep, and it is difficult to apply waterproof materials and construction methods in the case of structures accompanied by vibration. Therefore, we intend to study materials and methods for waterproofing leakage resistance in special environments such as underground structures.

• Proceeding of Spring/Autumn Annual Conference of KHA
• /
• 2009.04a
• /
• pp.113-117
• /
• 2009

By statistics in August, 2007, currently Korean motors registration number broke through 16 million units. The demand of motors is being increased as time goes on and the demand of parking lot within apartment complex is increased together. Therefore, it is inevitable to expand underground parking lots. Underground parking lots have relatively weaker environment than the ground and physical/psychological problems as distance far away from the main building, fear for vehicle damage and crimes, impure air, darkness and closed feeling take place. Underground parking lots also occupy a lot of area ratio within apartment complex and have a lot of effects on other facilities. Therefore, underground parking lots are neglected for all that underground parking lots have deep relations with satisfaction for public space within apartment complex. Accordingly, the purpose of the study is to make reference materials when underground parking lots are planned by grasping satisfaction of underground parking lots through inhabitants'mental survey and surveying preferential location and requirements of parking lots.

• Explosives and Blasting
• /
• v.42 no.2
• /
• pp.29-41
• /
• 2024

The increasing demand for metallic minerals due to global growth and the continued exploitation of near-surface minerals requires safe and efficient ways to mine ores present in deep mines. In deep mines, stresses concentrated around the cavity increase, which can lead to problems such as induced seismicity and rockbursts. In addition, the transfer of energy from blasting to deeply located faults can cause fault slip, which can lead to earthquakes, and controlling these events is key to deep mining methods. In this technical report, we will introduce the Underhand Closed Bench (UCB) mining method, which can control possible accidents and increase productivity when mining in deep mines.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.11 no.2
• /
• pp.157-178
• /
• 2013

This study gives a conceptual and basic direction to develop a URL (underground research laboratory) program for establishing the performance and safety of a deep geological disposal system in Korea. The concept of deep geological disposal is one of the preferred methodologies for the final disposal of spent nuclear fuel (SNF). Advanced countries with radioactive waste disposal have developed their own disposal concepts reasonable to their social and environmental conditions and applied to their commercial projects. Deep geological disposal system is a multi-barrier system generally consisting of an engineered barrier and natural barrier. A disposal facility and its host environment can be relied on a necessary containment and isolation over timescales envisaged as several to tens of thousands of years. A disposal system is not allowed in the commercial stage of the disposal program without a validation and demonstration of the performance and safety of the system. All issues confirming performance and safety of a disposal system include investigation, analysis, assessment, design, construction, operation and closure from planning to closure of the deep geological repository. Advanced countries perform RD&D (research, development & demonstration) programs to validate the performance and safety of a disposal system using a URL facility located at the preferred rock area within their own territories. The results and processes from the URL program contribute to construct technical criteria and guidelines for site selection as well as suitability and safety assessment of the final disposal site. Furthermore, the URL program also plays a decisive role in promoting scientific understanding of the deep geological disposal system for stakeholders, such as the public, regulator, and experts.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.25 no.6
• /
• pp.555-567
• /
• 2023

The cracks in the tunnel are currently determined through visual inspections conducted by inspectors based on images acquired using tunnel imaging acquisition systems. This labor-intensive approach, relying on inspectors, has inherent limitations as it is subject to their subjective judgments. Recently research efforts have actively explored the use of deep learning to automatically detect tunnel cracks. However, most studies utilize public datasets or lack sufficient objectivity in the analysis process, making it challenging to apply them effectively in practical operations. In this study, we selected test datasets consisting of images in the same format as those obtained from the actual inspection system to perform an objective evaluation of deep learning models. Additionally, we introduced ensemble techniques to complement the strengths and weaknesses of the deep learning models, thereby improving the accuracy of crack detection. As a result, we achieved high recall rates of 80%, 88%, and 89% for cracks with sizes of 0.2 mm, 0.3 mm, and 0.5 mm, respectively, in the test images. In addition, the crack detection result of deep learning included numerous cracks that the inspector could not find. if cracks are detected with sufficient accuracy in a more objective evaluation by selecting images from other tunnels that were not used in this study, it is judged that deep learning will be able to be introduced to facility safety inspection.

• Structural Engineering and Mechanics
• /
• v.68 no.4
• /
• pp.497-505
• /
• 2018

Three points bending flexural test was modeled numerically to study the crack propagation in the pre-cracked beams. The pre-existing edge cracks in the beam models were considered to investigate the crack propagation and coalescence paths within the modeled samples. The effects of particle size on the single edge-notched round bar in bending test were considered too. The results show that Failure pattern is constant by increasing the ball diameter. Tensile cracks are dominant mode of failure. These crack initiates from notch tip, propagate parallel to loading axis and coalescence with upper model boundary. Number of cracks increase by decreasing the ball diameter. Also, tensile fracture toughness was decreased with increasing the particle size. In the present study, the influences of particles sizes on the cracks propagations and coalescences in the brittle materials such as rocks and concretes are numerically analyzed by using a three dimensional particle flow code (PFC3D). These analyses improve the understanding of the stability of rocks and concretes structures such as rock slopes, tunnel constructions and underground openings.

• Smart Structures and Systems
• /
• v.22 no.6
• /
• pp.663-673
• /
• 2018

In this study, the effect of particle size on the cracks propagation and coalescence or cracking pattern of the edge notched disc specimens are investigated. Firstly, calibration of PFC3D was performed using Brazilian experimental test output. Then micro parameters were used to build edge notched disc specimen. The horizontal wall of the assembly is let to move downward with a standard low speed of 0.016 m/s. The numerical results show that the tensile cracks are dominant failure pattern for the modeled discs. These tensile cracks initiate from the pre-existing notch tip and propagate parallel to the loading direction then interact with the upper boundary of the modeled specimen. As the size of the balls (ball diameter) decrease the number of tensile cracks increase. The tensile fracture toughness of the samples also decreases as the particle size increases. Understanding the crack propagation and crack coalescence phenomena in brittle materials such as concretes and rocks is of paramount importance in the stability analyses for engineering structures such as rock slopes, underground structures and tunneling.

• Geomechanics and Engineering
• /
• v.23 no.6
• /
• pp.587-600
• /
• 2020

Shear-induced instability of jointed rock mass has greatly threatened the safety of underground openings. To better understand the failure mechanism of surrounding rock mass under shear, the flawed specimens containing a circular opening and two open joints are prepared and used to conduct direct shear tests. Both experimental and numerical results show that joint inclination (β) has a significant effect on the shear strength, dilation, cracking behavior and stress distribution around flaws. The maximum shear strength, occurring at β=30°, usually corresponds to a unifrom stress state around joint and an intense energy release. However, a larger joint inclination, such as β=90°~150°, will cause a more uneven stress distribution and a stronger stress concentration, thus a lower shear strength. The stress distribution around opening changes little with joint inclination, while the magnitude varys much. Both compression and tension around opening will be greatly enhanced by the 30°-joints. In addition, a higher normal stress tends to enhance the compression and suppress the tension around flaws, resulting in an earlier generation and a larger proportion of shear cracks.