• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.6
• /
• pp.617-628
• /
• 2022

A ground support pattern should be designed by properly integrating various support materials in accordance with the rock mass grade when constructing a tunnel, and a technical decision must be made in this process by professionals with vast construction experiences. However, designing supports at the early stage of tunnel design, such as feasibility study or basic design, may be very challenging due to the short timeline, insufficient budget, and deficiency of field data. Meanwhile, the design of the support pattern can be performed more quickly and reliably by utilizing the machine learning technique and the accumulated design data with the rapid increase in tunnel construction in South Korea. Therefore, in this study, the design data and ground exploration data of 48 road tunnels in South Korea were inspected, and data about 19 items, including eight input items (rock type, resistivity, depth, tunnel length, safety index by tunnel length, safety index by rick index, tunnel type, tunnel area) and 11 output items (rock mass grade, two items for shotcrete, three items for rock bolt, three items for steel support, two items for concrete lining), were collected to automatically determine the rock mass class and the support pattern. Three machine learning models (S1, A1, A2) were developed using two machine learning algorithms (SVR, ANN) and organized data. As a result, the A2 model, which applied different loss functions according to the output data format, showed the best performance. This study confirms the potential of support pattern design using machine learning, and it is expected that it will be able to improve the design model by continuously using the model in the actual design, compensating for its shortcomings, and improving its usability.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.23 no.6
• /
• pp.469-484
• /
• 2021

Rock mass classification results have a great influence on construction schedule and budget as well as tunnel stability in tunnel design. A total of 3,526 tunnels have been constructed in Korea and the associated techniques in tunnel design and construction have been continuously developed, however, not many studies have been performed on how to assess rock mass quality and grade more accurately. Thus, numerous cases show big differences in the results according to inspectors' experience and judgement. Hence, this study aims to suggest a more reliable rock mass classification (RMR) model using machine learning algorithms, which is surging in availability, through the analyses based on various rock and rock mass information collected from boring investigations. For this, 11 learning parameters (depth, rock type, RQD, electrical resistivity, UCS, V_p, V_s, Young's modulus, unit weight, Poisson's ratio, RMR) from 13 local tunnel cases were selected, 337 learning data sets as well as 60 test data sets were prepared, and 6 machine learning algorithms (DT, SVM, ANN, PCA & ANN, RF, XGBoost) were tested for various hyperparameters for each algorithm. The results show that the mean absolute errors in RMR value from five algorithms except Decision Tree were less than 8 and a Support Vector Machine model is the best model. The applicability of the model, established through this study, was confirmed and this prediction model can be applied for more reliable rock mass classification when additional various data is continuously cumulated.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.3
• /
• pp.247-262
• /
• 2022

In domestic tunnels, it is mandatory to install CCTVs in tunnels longer than 200 m which are also recommended by installation of a CCTV-based automatic accident detection system. In general, the CCTVs in the tunnel are installed at a low height as well as near by the moving vehicles due to the spatial limitation of tunnel structure, so a severe perspective effect takes place in the distance of installed CCTV and moving vehicles. Because of this effect, conventional CCTV-based accident detection systems in tunnel are known in general to be very hard to achieve the performance in detection of unexpected accidents such as stop or reversely moving vehicles, person on the road and fires, especially far from 100 m. Therefore, in this study, the region of interest is set up and a new concept of inverse perspective transformation technique is introduced. Since moving vehicles in the transformed image is enlarged proportionally to the distance from CCTV, it is possible to achieve consistency in object detection and identification of actual speed of moving vehicles in distance. To show this aspect, two datasets in the same conditions are composed with the original and the transformed images of CCTV in tunnel, respectively. A comparison of variation of appearance speed and size of moving vehicles in distance are made. Then, the performances of the object detection in distance are compared with respect to the both trained deep-learning models. As a result, the model case with the transformed images are able to achieve consistent performance in object and accident detections in distance even by 200 m.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.11 no.1
• /
• pp.57-70
• /
• 2009

Considerable advance has been made on research on effect of steel pipe Umbrella Arch Method (UAM) and mechanical reinforcement mechanism through numerical analyses and experiments. Due to long analysis time of three-dimensional analysis and its complexity, un-quantitative two-dimensional analysis is dominantly used in the design and application, where equivalent material properties of UAM reinforced area and ground are used, For this reason, development of reasonable, theoretical, quantitative and easy to use design and analysis method is required. In this study, both field UAM tests and laboratory tests were performed in the residual soil to highly weathered rock; field tests to observe the range of reinforcement, and laboratory tests to investigate the change of material properties between prior to and after UAM reinforcement. It has been observed that the increase in material property of neighboring ground is negligible, and that only stiffness of steel pipe and cement column formed inside the steel pipe and the gap between steel pipe and borehole contributes to ground reinforcement. Based on these results and concept of Convergence Confinement Method (CCM), two dimensional axisymmetric analyses have been performed to obtain the longitudinal displacement profile (LDP) corresponding to arching effect of tunnel face, UAM effect and effect of supports. In addition, modified load distribution method in two dimensional plane-strain analysis has been suggested, in which effect of UAM is transformed to internal pressure and modified load distribution ratios are suggested. Comparison between the modified method and conventional method shows that larger displacement occur in the conventional method than that in the modified method although it may be different depending on ground condition, depth and size of tunnel, types of steel pipe and initial stress state. Consequently, it can be concluded that the effect of UAM as a beam in a longitudinal direction is not considered properly in the conventional method.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.2
• /
• pp.129-152
• /
• 2024

In the application of deep learning object detection via CCTV in tunnels, a large number of false positive detections occur due to the poor environmental conditions of tunnels, such as low illumination and severe perspective effect. This problem directly impacts the reliability of the tunnel CCTV-based accident detection system reliant on object detection performance. Hence, it is necessary to reduce the number of false positive detections while also enhancing the number of true positive detections. Based on a deep learning object detection model, this paper proposes a false positive data training method that not only reduces false positives but also improves true positive detection performance through retraining of false positive data. This paper's false positive data training method is based on the following steps: initial training of a training dataset - inference of a validation dataset - correction of false positive data and dataset composition - addition to the training dataset and retraining. In this paper, experiments were conducted to verify the performance of this method. First, the optimal hyperparameters of the deep learning object detection model to be applied in this experiment were determined through previous experiments. Then, in this experiment, training image format was determined, and experiments were conducted sequentially to check the long-term performance improvement through retraining of repeated false detection datasets. As a result, in the first experiment, it was found that the inclusion of the background in the inferred image was more advantageous for object detection performance than the removal of the background excluding the object. In the second experiment, it was found that retraining by accumulating false positives from each level of retraining was more advantageous than retraining independently for each level of retraining in terms of continuous improvement of object detection performance. After retraining the false positive data with the method determined in the two experiments, the car object class showed excellent inference performance with an AP value of 0.95 or higher after the first retraining, and by the fifth retraining, the inference performance was improved by about 1.06 times compared to the initial inference. And the person object class continued to improve its inference performance as retraining progressed, and by the 18th retraining, it showed that it could self-improve its inference performance by more than 2.3 times compared to the initial inference.

• Proceedings of the KSEEG Conference
• /
• 2001.05b
• /
• pp.42-63
• /
• 2001

The detail survey on the Songsanri tomb site including the Muryong royal tomb was carried out during the period from May 1 , 1996 to April 30, 1997. A quantitative analysis was tried to find changes of tomb itself since the excavation. Main subjects of the survey are to find out the cause of infiltration of rain water and groundwater into the tomb and the tomb site, monitoring of the movement of tomb structure and safety, removal method of the algae inside the tomb, and air controlling system to solve high humidity condition and dew inside the tomb. For these purposes, detail survery inside and outside the tombs using a electronic distance meter and small airplane, monitoring of temperature and humidity, geophysical exploration including electrical resistivity, geomagnetic, gravity and georadar methods, drilling, measurement of physical and chemical properties of drill core and measurement of groundwater permeability were conducted. We found that the center of the subsurface tomb and the center of soil mound on ground are different 4.5 meter and 5 meter for the 5th tomb and 7th tomb, respectively. The fact has caused unequal stress on the tomb structure. In the 7th tomb (the Muryong royal tomb), 435 bricks were broken out of 6025 bricks in 1972, but 1072 bricks are broken in 1996. The break rate has been increased about 250% for just 24 years. The break rate increased about 290% in the 6th tomb. The situation in 1996 is the result for just 24 years while the situation in 1972 was the result for about 1450 years. Status of breaking of bircks represents that a severe problem is undergoing. The eastern wall of the Muryong royal tomb is moving toward inside the tomb with the rate of 2.95 mm/myr in rainy season and 1.52 mm/myr in dry season. The frontal wall shows biggest movement in the 7th tomb having a rate of 2.05 mm/myr toward the passage way. The 6th tomb shows biggest movement among the three tombs having the rate of 7.44mm/myr and 3.61mm/myr toward east for the high break rate of bricks in the 6th tomb. Georadar section of the shallow soil layer represents several faults in the top soil layer of the 5th tomb and 7th tomb. Raninwater flew through faults tnto the tomb and nearby ground and high water content in nearby ground resulted in low resistance and high humidity inside tombs. High humidity inside tomb made a good condition for algae living with high temperature and moderate light source. The 6th tomb is most severe situation and the 7th tomb is the second in terms of algae living. Artificial change of the tomb environment since the excavation, infiltration of rain water and groundwater into the tombsite and bad drainage system had resulted in dangerous status for the tomb structure. Main cause for many problems including breaking of bricks, movement of tomb walls and algae living is infiltration of rainwater and groundwater into the tomb site. Therefore, protection of the tomb site from high water content should be carried out at first. Waterproofing method includes a cover system over the tomvsith using geotextile, clay layer and geomembrane and a deep trench which is 2 meter down to the base of the 5th tomb at the north of the tomv site. Decrease and balancing of soil weight above the tomb are also needed for the sfety of tomb structures. For the algae living inside tombs, we recommend to spray K101 which developed in this study on the surface of wall and then, exposure to ultraviolet light sources for 24 hours. Air controlling system should be changed to a constant temperature and humidity system for the 6th tomb and the 7th tomb. It seems to much better to place the system at frontal room and to ciculate cold air inside tombs to solve dew problem. Above mentioned preservation methods are suggested to give least changes to tomb site and to solve the most fundmental problems. Repairing should be planned in order and some special cares are needed for the safety of tombs in reparing work. Finally, a monitoring system measuring tilting of tomb walls, water content, groundwater level, temperature and humidity is required to monitor and to evaluate the repairing work.

• Journal of Soil and Groundwater Environment
• /
• v.13 no.4
• /
• pp.40-53
• /
• 2008

Groundwater pollution prediction methods have been developed to plan the sustainable groundwater usage and protection from potential pollution in many countries. DRASTIC established by US EPA is the most widely used groundwater vulnerability mapping method. However, the DRASTIC showed limitation in predicting the groundwater contamination because the DRASTIC method is designed to embrace only hydrogeologic factors. Therefore, in this study, three different methods were applied to improve a groundwater pollution prediction method: US EPA DRASTIC, Modified-DRASTIC suggested by Panagopoulos et al. (2006), and LSDG (Land use, Soil drainage, Depth to water, Geology) proposed by Rupert (1999). The Modified-DRASTIC is the modified version of the DRASTIC in terms of the rating scales and the weighting coefficients. The rating scales of each factor were calculated by the statistical comparison of nitrate concentrations in each class using the Wilcoxon rank-sum test; while the weighting coefficients were modified by the statistical correlation of each parameter to nitrate concentrations using the Spearman's rho test. The LSDG is a simple rating method using four factors such as Land use, Soil drainage, Depth to water, and Geology. Classes in each factor are compared by the Wilcoxon rank-sum test which gives a different rating to each class if the nitrate concentration in the class is significantly different. A database of nitrate concentrations in groundwaters from 149 wells was built in Keumsan area. Application of three different methods for assessing the groundwater pollution potential resulted that the prediction which was represented by a correlation (r) between each index and nitrate was improved from the EPA DRASTIC (r = 0.058) to the modified rating (r = 0.245), to the modified rating and weights (r = 0.400), and to the LSDG (r = 0.415), respectively. The LSDG seemed appropriate to predict the groundwater pollution in that it contained land use as a factor of the groundwater pollution sources and the rating of each class was defined by a real pollution nitrate concentration.

• Journal of the Korean Society of Groundwater Environment
• /
• v.5 no.4
• /
• pp.177-191
• /
• 1998

For various kinds of waters including surface water, shallow groundwater (＜70 m deep) and deep groundwater (500∼810 m deep) from the Pungki area, an integrated study based on hydrochemical, multivariate statistical, thermodynamic, environmental isotopic (tritium, oxygen-hydrogen, carbon and sulfur), and mass-balance approaches was attempted to elucidate the hydrogeochemical and hydrologic characteristics of the groundwater system in the gneiss area. Shallow groundwaters are typified as the 'Ca-HCO$_3$'type with higher concentrations of Ca, Mg, SO$_4$and NO$_3$, whereas deep groundwaters are the 'Na-HCO$_3$'type with elevated concentrations of Na, Ba, Li, H$_2$S, F and Cl and are supersaturated with respect to calcite. The waters in the area are largely classified into two groups: 1) surface waters and most of shallow groundwaters, and 2) deep groundwaters and one sample of shallow groundwater. Seasonal compositional variations are recognized for the former. Multivariate statistical analysis indicates that three factors may explain about 86% of the compositional variations observed in deep groundwaters. These are: 1) plagioclase dissolution and calcite precipitation, 2) sulfate reduction, and 3) acid hydrolysis of hydroxyl-bearing minerals(mainly mica). By combining with results of thermodynamic calculation, four appropriate models of water/ rock interaction, each showing the dissolution of plagioclase, kaolinite and micas and the precipitation of calcite, illite, laumontite, chlorite and smectite, are proposed by mass balance modelling in order to explain the water quality of deep groundwaters. Oxygen-hydrogen isotope data indicate that deep groundwaters were originated from a local meteoric water recharged from distant, topograpically high mountainous region and underwent larger degrees of water/rock interaction during the regional deep circulation, whereas the shallow groundwaters were recharged from nearby, topograpically low region. Tritium data show that the recharge time was the pre-thermonuclear age for deep groundwaters (＜0.2 TU) but the post-thermonuclear age for shallow groundwaters (5.66∼7.79 TU). The $\delta$$\^$34/S values of dissolved sulfate indicate that high amounts of dissolved H$_2$S (up to 3.9 mg/1), a characteristic of deep groundwaters in this area, might be derived from the reduction of sulfate. The $\delta$$\^$13/C values of dissolved carbonates are controlled by not only the dissolution of carbonate minerals by dissolved soil CO$_2$(for shallow groundwaters) but also the reprecipitation of calcite (for deep groundwaters). An integrated model of the origin, flow and chemical evolution for the groundwaters in this area is proposed in this study.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.63 no.2
• /
• pp.140-148
• /
• 2018

As the global warming causing desertification increase, there is growing concern about damage of crops. It was to investigate how the treatment with hydrogen peroxide before leaf development affects the growth and yield of sorghum for minimizing a damage of crops to drought. The germination experiment was conducted at alternating temperature of $25^{\circ}C/20^{\circ}C$(12 hr/12 hr) under water stress condition of 0 ~ -0.20 MPa adjusted with PEG solution containing 0 and 10 mM $H_2O_2$. In order to know the effect of foliar application of hydrogen peroxide on the growth of sorghum, 10 mM hydrogen peroxide was treated to leaves at 3-leaf stage of sorghum growing in greenhouse conditions. Seed germination rate was increased by 20% in hydrogen peroxide treatment as compared to the Control. under water stress conditions (-0.15 ~ -0.20 MPa). The length of seedlings was also on the rise by the hydrogen peroxide treatment. In the greenhouse pot experiment, the morphological characteristics (plant height, stem diameter, leaf length, and leaf number) and physiological characteristics (chlorophyll content, chlorophyll fluorescence (Fv/Fm), stomatal conductance) were higher in the plants treated with hydrogen peroxide under the drought stress condition than those of plants of $H_2O$ treatment. Experiment conducted with the soil moisture gradient system showed that the foliar application of hydrogen peroxide increased photosynthetic ability of sorghum plant with respect to SPAD value and stomatal conductance and rooting capacity (root weight and root length) under drought condition. Generally, hydrogen peroxide treatment in sorghum increased the tolerance to drought stress and maintained better growth due to ameliorating oxidative stress.

• Korean Journal of Environmental Agriculture
• /
• v.21 no.2
• /
• pp.109-116
• /
• 2002

The objective of this study was to know the qualities of soil and shallow groundwater in plastic film house fields around Central Part of Korea. The study was conducted at 11 sites in Suweon, Hwasung, Pyungtaek, Yongin and Chuncheon through May to August in 1999. Soil textures of plastic films house were mainly sandy loam or loam. Electric conductivity and organic matter content of surface soils mostly exceeded the critical levels for crop production. Average concentration of $NO_3-N$ in the sha]low groundwater was 19.1 mg/L, and it reached almost the limiting level of agricultural groundwater quality (20 mg/L). Moreover about 36% of survey sites exceeded the limiting level of agricultural groundwater quality. Sulfate concentrations also at some sites exceeded agricultural groundwater quality limit level (50 mg/L). Nitrate-N, one of the most important factors in the groundwater quality, had positive correlations with other ions in foundwater.