• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.3
• /
• pp.133-139
• /
• 2023

This paper proposes a two-stage Water Shield Automation System (WSAS) to predict the possibility of river overflow and vehicle flooding due to sudden rainfall. The WSAS uses a two-stage Deep Neural Network (DNN) model. First, a river overflow prediction module is designed with LSTM to decide whether the river is flooded by predicting the river's water level rise. Second, a vehicle flooding prediction module predicts flooding of underground parking lots by detecting flooded tires with YOLOv5 from CCTV images. Finally, the WSAS automatically installs the water barrier whenever the river overflow and vehicle flooding events happen in the underground parking lots. The only constraint to implementing is that collecting training data for flooded vehicle tires is challenging. This paper exploits the Image C&S data augmentation technique to synthesize flooded tire images. Experimental results validate the superiority of WSAS by showing that the river overflow prediction module can reduce RMSE by three times compared with the previous method, and the vehicle flooding detection module can increase mAP by 20% compared with the naive detection method, respectively.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.4 no.3
• /
• pp.217-227
• /
• 2002

Geostatistical methods were used for the groundwater flow analysis on the ${\bigcirc}{\bigcirc}$ tunnel area. Linear regression analysis shows that the topographic elevation and ground water level of this area have very high correlation. Groundwater-level contour maps produced by ordinary kriging and cokriging have little differences in mountain areas. But, comparing two maps on the basis of an elevation contour map, a groundwater-level contour map using cokring is more accurate. Analyzing the groundwater flow on two groundwater-level contour maps, the groundwater of study area flows from the north-west mountain areas to near valleys, and from the peak of the mountain to outside areas. In the design steps, the groundwater-level distribution is reasonably considered in the tunnel construction area by cokriging approach. And, geostatistics will provide quantitative information in the unknown groundwatrer-level area.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2006.05b
• /
• pp.185-188
• /
• 2006

During the carbonation process in concrete, the rate of carbonation depends on porosity and moisture content of the concrete. For underground reinforced concrete structures, the interior concrete surface may be exposed to carbonation and the exterior concrete surface exposed to moisture due to wet soil or underground water. In this study, the permeability coefficients in mortar partially carbonated is derived as a function of carbonation depth and porosity of mortar by applying the so-called micro pore structure formation model (MPSFM) which was developed for the modeling of early-aged concrete. The permeability coefficient obtained from the micro-level modeling of carbonated mortar is verified with the results of accelerated carbonation test and water penetration test in cement mortar.

• Journal of the Speleological Society of Korea
• /
• no.67
• /
• pp.21-34
• /
• 2005

Jeomal Cave consists of limestone. Soil distribution is very different from mountain area to piedmont area. The Cave developed in a part of the fault valley. The joints controls the low level stream orders in the cave. in this area the geological structure is close relate to the underground water flow. It is certain that the distribution of the clay came from the surface.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.6
• /
• pp.1235-1240
• /
• 2019

It is well known that the ground water level changes rapidly before and after the earthquake, and the variation of ground water level prediction is used to predict the earthquake. In this paper, we predict the ground water level in Miryang City using ANFIS algorithm for earthquake prediction. For this purpose, this paper used precipitation and temperature acquired from National Weather Service and data of underground water level from Rural Groundwater Observation Network of Korea Rural Community Corporation which is installed in Miryang city, Gyeongsangnam-do. We measure the prediction accuracy using RMSE and MAPE calculation methods. As a result of the prediction, the periodic pattern was predicted by natural factors, but the change value of ground water level was changed by other variables such as artificial factors that was not detected. To solve this problem, it is necessary to digitize the ground water level by numerically quantifying artificial variables, and to measure the precipitation and pressure according to the exact location of the observation ball measuring the ground water level.

• Journal of Korean Society of Water and Wastewater
• /
• v.11 no.2
• /
• pp.31-39
• /
• 1997

Between 40,000 and 60,000 liters of light oil were spilled when an underground pipe broke at a newly constructed landfill site in coastal area, Korea. Methods were presented to examine the subsurface distribution of the contaminants in hydrocarbon-contaminated soil. As results, large quantities of oil and grease were found to have migrated horizontally at the site. Oil and grease plume at concentrations of 38-88 mg/kg was formed horizontally through silty sand with gravel fill and the vertical movement of the contaminants was thought to be limited to groundwater level between 2 and 4 m corresponding to sea water level. Right after finding the leakage area, the early action of excavation and pumping out the mixture of groundwater and oil was taken and it was proved to be very effective for preventing further contamination. Two months after the leakage, oil and grease in sea water sample near contaminated area was not detectable.

• Journal of the Korean Society of Safety
• /
• v.33 no.4
• /
• pp.119-126
• /
• 2018

In recent years, as flood damage caused by heavy rains increased, the great-depth tunnel using urban underground space is emerging as a countermeasure of urban inundation. The great-depth tunnel is used to reduce urban inundation by using the underground space. The drainage efficiency of great-depth tunnel depends on the intake design, which leads to increase discharge into the underground space. The spiral intake and the tangential intake are commonly used for the inlet facility. The spiral intake creates a vortex flow along the drop shaft and reduces an energy of the flow by the wall friction. In the tangential intake, flow simply falls down into the drop shaft, and the design is simple to construct compared to the spiral intake. In the case of the spiral intake, the water level at the drop shaft entrance is risen due to the chocking induced by the flowrate increase. The drainage efficiency of the tangential intake decreases because the flow is not sufficiently accelerated under low flow conditions. Therefore, to compensate disadvantages of the previously suggested intake design, the multi-stage intake was developed which can stably withdraw water even under a low flow rate below the design flow rate. The hydraulic characteristics in the multi-stage intake were analyzed by changing the flow rate to compare the drainage performance according to the intake design. From the measurements, the drainage efficiency was improved in both the low and high flow rate conditions when the multi-stage inlet was employed.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.15 no.2
• /
• pp.123-134
• /
• 2013

Urban underground structures at low ground elevations (i.e. shallow substructures) unlike typical tunnel structures are subjected to low overburden and high water pressures. This often causes the underground structures to become damaged. Various conventional methods for the urban underpass structures such as dead weight increasement, round anchors, and tension piles, are significantly conservative and provok concerns about the costly, time-consuming installation process. Recently, permanent drainage system becomes to widely use for supplementing the conventional method's shortcomings, but, it is applied without the considerations for ground conditions and water table. In this study, therefore, numerical analyses are performed with various parameters such as groundwater level, wall height, and ground conditions in order to establish design guidelines for induced drainage system which is a kind of the permanent drainage method constructed at the Y-area. According to the numerical results, the induced drainage system is very effective in reducing the uplift pressure that acts on the base of underpass structures.

• Tunnel and Underground Space
• /
• v.30 no.2
• /
• pp.149-163
• /
• 2020

This paper presents a logistic regression and GIS based urban ground sink susceptibility assessment using underground facility information considering soil particle loss. In the underground environment, the particle loss due to water flow or groundwater level change leads to the occurrence and expansion of cavities, which directly affect the ground sink. Four different contributory factors were selected according to the two underground facility domains (water pipeline area, sewer pipeline area) and subway line area. The logistic regression method was used to analyze the correlation and to derive the regression equation between the ground sink inventory and the contributory factors. Based on these results, three ground sink susceptibility maps were generated. The results obtained from this study are expected to provide basic data on the area susceptible to ground sink and needed to safety monitoring.

• Geomechanics and Engineering
• /
• v.27 no.6
• /
• pp.583-594
• /
• 2021

The gas permeability behavior of unsaturated bentonite-based materials is of major importance for ensuring effective sealing of high-level radwaste repositories. This study investigated this by taking a sample of Granular Bentonite Material (GBM) at the end of the Engineered Barrier Emplacement (EB) experiment in the Opalinus Clay, placing it under different humidity conditions until it achieved equilibration, and testing the change in the gas permeability under loading and unloading. Environmental humidity is shown to have a significant effect on the water content, saturation, porosity and dry density of GBM and to affect its gas permeability. Higher sensitivity to confining pressure is exhibited by samples equilibrated at higher relative humidity (RH). It should be noted that for the sample at RH=98%, when the confining pressure is raised from 1 MPa to 6 MPa, gas permeability can be reduced from 10^-16 m² to 10^-19 m², which is close to the requirements of gas tightness. Due to higher water content and easier compressibility, samples equilibrated under higher RH show greater irreversibility during the loading and unloading process. The effective gas permeability of highly saturated samples can be increased by 2-3 orders of magnitude after 105℃ drying. In addition, cracks possibly occurred during the dehydration and drying process will become the main channel for gas migration, which will greatly affect the sealing performance of GBM.