• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.4
• /
• pp.341-353
• /
• 2022

Pipelines are buried in urban area, and the position (depth and orientation) of buried pipeline should be clearly identified before ground excavation. Although various geophysical methods can be used to detect the buried pipeline, it is not easy to identify the exact information of pipeline due to heterogeneous ground condition. Among various non-destructive geo-exploration methods, ground penetration radar (GPR) can explore the ground subsurface rapidly with relatively low cost compared to other exploration methods. However, the exploration data obtained from GPR requires considerable experiences because interpretation is not intuitive. Recently, researches on automated detection technology for GPR data using deep learning have been conducted. However, the lack of GPR data which is essential for training makes it difficult to build up the reliable detection model. To overcome this problem, we conducted a preliminary study to improve the performance of the detection model using finite difference time domain (FDTD)-based numerical analysis. Firstly, numerical analysis was performed with homogeneous soil media having single permittivity. In case of heterogeneous ground, numerical analysis was performed considering the ground heterogeneity using fractal technique. Secondly, deep learning was carried out using convolutional neural network. Detection Model-A is trained with data set obtained from homogeneous ground. And, detection Model-B is trained with data set obtained from homogeneous ground and heterogeneous ground. As a result, it is found that the detection Model-B which is trained including heterogeneous ground shows better performance than detection Model-A. It indicates the ground heterogeneity should be considered to increase the performance of automated detection model for GPR exploration.

• Explosives and Blasting
• /
• v.40 no.3
• /
• pp.19-32
• /
• 2022

Hydrogen is a fuel having the highest energy compared with other common fuels. This means hydrogen is a clean energy source for the future. However, using hydrogen as a fuel has implication regarding carrier and storage issues, as hydrogen is highly inflammable and unstable gas susceptible to explosion. Explosions resulting from hydrogen-air mixtures have already been encountered and well documented in research experiments. However, there are still large gaps in this research field as the use of numerical tools and field experiments are required to fully understand the safety measures necessary to prevent hydrogen explosions. The purpose of this present study is to develop and simulate 3D numerical modelling of an existing hydrogen gas station in Jeonju by using handheld LiDAR and Ansys AUTODYN, as well as the processing of point cloud scans and use of cloud dataset to develop FEM 3D meshed model for the numerical simulation to predict peak-over pressures. The results show that the Lidar scanning technique combined with the ANSYS AUTODYN can help to determine the safety distance and as well as construct, simulate and predict the peak over-pressures for hydrogen refueling station explosions.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.5
• /
• pp.601-610
• /
• 2023

The comprehension of water-level behavior in rivers is essential for effective flood and river environmental management. The objective of this study is to propose a methodology that can be used by field engineers engaged in actual practice, to readily identify the characteristics of water-level behavior during flood events. To this end, a total of 45 historical water-level records from 2010 to 2022 year, which provide flood information for the flood vulnerable districts of the Han River, were obtained. A Water-level Rise Behavior Curve (WRBC) was developed and suggested to quantify the amount of water-level rise per unit time during flood. As a result, the water-level rises by more than 80% of the total rise within the first 6.2 hours, followed by a gradual rise. The time required to achieve a particular equilibrium varied depending on the area and runoff characteristics of the upstream. Furthermore, the study revealed that the WRBC provides a statistical representation of the water-level rise trend during floods, and can be effectively utilized for flood mitigation measures in waterfront spaces and irrigation facilities.

• Journal of Convergence for Information Technology
• /
• v.12 no.3
• /
• pp.85-107
• /
• 2022

This study is to analyze the induced effect, network connectivity, and network visualization of the water transportation industry on the overall economy in relation to all industries. For this, various inducement coefficients of the water transportation industry are analyzed using industry linkage analysis and unit structure matrix, and network visualization analysis is performed using network connectivity and NetDraw using Ucinet 6 that utilizes unit structure matrix and inverse matrix function. As a result of the study, analysis results of input coefficient, production inducement coefficient, value-added inducement coefficient, and inter-industry chain effect were presented as various inducement coefficients in the water transportation industry. content was presented. Through this study, the current position and status of the water transportation industry and its relationship with all industries were confirmed, and the strategic relationship with which industries it should be presented was presented. In the future, it is necessary to further analyze the current status and trends of various induced effects, connectivity (centrality), and network visualization analysis using industry-related analysis published since the 2000s.

• The Journal of Bigdata
• /
• v.7 no.1
• /
• pp.15-27
• /
• 2022

In the past five years, the fatality rate of single-vehicle accidents has been 4.7 times higher than that of all accidents, so it is necessary to establish a system that can detect and respond to single-vehicle accidents immediately. The IoT(Internet of Thing)-based real-time traffic accident recognition system proposed in this study is as following. By attaching an IoT sensor which detects the impact and vehicle ingress to the guardrail, when an impact occurs to the guardrail, the image of the accident site is analyzed through artificial intelligence technology and transmitted to a rescue organization to perform quick rescue operations to damage minimization. An IoT sensor module that recognizes vehicles entering the monitoring area and detects the impact of a guardrail and an AI-based object detection module based on vehicle image data learning were implemented. In addition, a monitoring and operation module that imanages sensor information and image data in integrate was also implemented. For the validation of the system, it was confirmed that the target values were all met by measuring the shock detection transmission speed, the object detection accuracy of vehicles and people, and the sensor failure detection accuracy. In the future, we plan to apply it to actual roads to verify the validity using real data and to commercialize it. This system will contribute to improving road safety.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.3D
• /
• pp.295-302
• /
• 2010

Since the late 1990s, the BOT mode in China has been extensively used in the water sector in order to attract private investment, improve technical and operational efficiency, and expand the coverage of water services. The BOT mode has been hailed as this provides a win-win structure between the government and private players through formalized procedures and an optimal risk allocation. However, recent market analyses show that some foreign investors are reluctant to participate in the market or even retreat due to uncertainties and risks in the market. This study aims to explore various risks in the Chinese water BOT market based on the thorough literature review, fieldwork, and the case studies on the two wholly foreign-owned BOT water projects: the Chengdu No. 6 and the Shanghai Dachang Water Supply BOT projects. The research results indicate that the Chinese BOT market embraces high risks in political, institutional and legal, and financial systems. The key to a successful takeoff of the BOT mode in the Chinese water market depends on the extent to which the government will be able to remove risky factors in political, institutional and legal, and financing systems. This research outcome will provide a useful reference to the Korean construction companies which consider expanding business to overseas water markets in the form of public private partnership.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.25 no.4
• /
• pp.284-301
• /
• 2023

The changes in rice climatic yield potential (CYP) across the Korean Peninsula are evaluated based on the new climate change scenario produced by the National Institute of Agricultural Sciences with 18 ensemble members at 1 km resolution under a Shared Socioeconomic Pathway (SSP) and Representative Concentration Pathways (RCP) emission scenarios. To overcome the data availability, we utilize solar radiation f or CYP instead of sunshine duration which is relatively uncommon in the climate prediction f ield. The result show that maximum CYP(CYPmax) decreased, and the optimal heading date is progressively delayed under warmer temperature conditions compared to the current climate. This trend is particularly pronounced in the SSP5-85 scenario, indicating faster warming, except for the northeastern mountainous regions of North Korea. This shows the benef its of lower emission scenarios and pursuing more efforts to limit greenhouse gas emissions. On the other hand, the CYPmax shows a wide range of feasible futures, which shows inherent uncertainties in f uture climate projections and the risks when analyzing a single model or a small number of model results, highlighting the importance of the ensemble approach. The f indings of this study on changes in rice productivity and uncertainties in temperature and solar radiation during the 21st century, based on climate change scenarios, hold value as f undamental information for climate change adaptation efforts.

• 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.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.44 no.2
• /
• pp.173-182
• /
• 2024

In recent, there has been a trend toward primarily utilizing data-driven models employing artificial intelligence technologies, such as machine learning, for flood prediction. These data-driven models offer the advantage of utilizing pre-training results, significantly reducing the required simulation time. However, it remains that a considerable amount of flood data is necessary for the pre-training in data-driven models, while the available observed data for application is often insufficient. As an alternative, validated simulation results from physically-based models are being employed as pre-training data alongside observed data. In this context, we developed a flood mapping accelerator to generate flood maps for pre-training. The proposed accelerator automates the entire process of flood mapping, i.e., estimating flood discharge using HEC-1, calculating water surface levels using HEC-RAS, simulating channel overflow and generating flood maps using RAS Mapper. With the accelerator, users can easily prepare a database for pre-training of data-driven models from hundreds to tens of thousands of rainfall scenarios. It includes various convenient menus containing a Graphic User Interface(GUI), and its practical applicability has been validated across 26 test-beds.

• Proceedings of the KSR Conference
• /
• 2007.11a
• /
• pp.1141-1151
• /
• 2007

In this paper through Honam high-speed railroad which is planned with the north and south axis, we will verify the feasibility of the coordinate conversion using railroad control points after regarding current planned-railroad as the linear central axises. From analysis, distortion of Y axis varies 21cm to 40cm diminishing to a gentle straight line, distortion of X axis varies 14cm to 29cm. Through a revision, the deviation value between the coordinates were 6mm to 9mm and it satisfied the allowable error of national geographic information institute which is following ITRF (International Terrestrial Reference Frame) and cadastral boundary survey(10cm). consequently the coordinate conversion is possible using railroad control points as common control points.