• Journal of Korean Association for Spatial Structures
• /
• v.23 no.3
• /
• pp.87-94
• /
• 2023

Chloride is one of the most common threats to reinforced concrete (RC) durability. Alkaline environment of concrete makes a passive layer on the surface of reinforcement bars that prevents the bar from corrosion. However, when the chloride concentration amount at the reinforcement bar reaches a certain level, deterioration of the passive protection layer occurs, causing corrosion and ultimately reducing the structure's safety and durability. Therefore, understanding the chloride diffusion and its prediction are important to evaluate the safety and durability of RC structure. In this study, the chloride diffusion coefficient is predicted by machine learning techniques. Various machine learning techniques such as multiple linear regression, decision tree, random forest, support vector machine, artificial neural networks, extreme gradient boosting annd k-nearest neighbor were used and accuracy of there models were compared. In order to evaluate the accuracy, root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE) and coefficient of determination (R2) were used as prediction performance indices. The k-fold cross-validation procedure was used to estimate the performance of machine learning models when making predictions on data not used during training. Grid search was applied to hyperparameter optimization. It has been shown from numerical simulation that ensemble learning methods such as random forest and extreme gradient boosting successfully predicted the chloride diffusion coefficient and artificial neural networks also provided accurate result.

• Korean Journal of Remote Sensing
• /
• v.33 no.5_2
• /
• pp.699-708
• /
• 2017

The present study was to develop an approach for predicting soybean yield using a crop growth simulation model at the regional level where the detailed and site-specific information on cultivation management practices is not easily accessible for model input. CROPGRO-Soybean model included in Decision Support System for Agrotechnology Transfer (DSSAT) was employed for this study, and Illinois which is a major soybean production region of USA was selected as a study region. As a first step to predict soybean yield of Illinois using CROPGRO-Soybean model, genetic coefficients representative for each soybean maturity group (MG I~VI) were estimated through sowing date experiments using domestic and foreign cultivars with diverse maturity in Seoul National University Farm ($37.27^{\circ}N$, $126.99^{\circ}E$) for two years. The model using the representative genetic coefficients simulated the developmental stages of cultivars within each maturity group fairly well. Soybean yields for the grids of $10km{\times}10km$ in Illinois state were simulated from 2,000 to 2,011 with weather data under 18 simulation conditions including the combinations of three maturity groups, three seeding dates and two irrigation regimes. Planting dates and maturity groups were assigned differently to the three sub-regions divided longitudinally. The yearly state yields that were estimated by averaging all the grid yields simulated under non-irrigated and fully-Irrigated conditions showed a big difference from the statistical yields and did not explain the annual trend of yield increase due to the improved cultivation technologies. Using the grain yield data of 9 agricultural districts in Illinois observed and estimated from the simulated grid yield under 18 simulation conditions, a multiple regression model was constructed to estimate soybean yield at agricultural district level. In this model a year variable was also added to reflect the yearly yield trend. This model explained the yearly and district yield variation fairly well with a determination coefficients of $R^2=0.61$ (n = 108). Yearly state yields which were calculated by weighting the model-estimated yearly average agricultural district yield by the cultivation area of each agricultural district showed very close correspondence ($R^2=0.80$) to the yearly statistical state yields. Furthermore, the model predicted state yield fairly well in 2012 in which data were not used for the model construction and severe yield reduction was recorded due to drought.

• KEPCO Journal on Electric Power and Energy
• /
• v.2 no.2
• /
• pp.227-232
• /
• 2016

To test the effectiveness of using an energy storage system for frequency regulation, the Energy New Business Laboratory at KEPCO Research Institute installed a 4 MW energy storage system (ESS) demonstration facility at the Jocheon Substation on Jeju Island. And after the successful completion of demonstration operations, a total of 52 MW ESS for frequency regulation was installed in Seo-Anseong (28 MW, governor-free control) and in Shin-Yongin (24 MW, automatic generation control). The control system used in these two sites was based on the control system developed for the 4 MW ESS demonstration facility. KEPCO recently finished the construction of 184 MW ESS for frequency regulation in 8 locations, (e.g. Shin-Gimjae substation, Shin-Gaeryong substation, etc.) and they are currently being tested for automatic operation. KEPCO plans to construct additional ESS facilities (up to a total of about 500 MW for frequency regulation by 2017), thus, various operational tests would first have to be conducted. The high-speed characteristic of ESS can negatively impact the power system in case the 500 MW ESS is not properly operated. At this stage we need to verify how effectively the 500 MW ESS can regulate frequency. In this paper, the effect of using ESS for frequency regulation on the power system of Korea was studied. Simulations were conducted to determine the effect of using a 524 MW ESS for frequency regulation. Models of the power grid and the ESS were developed to verify the performance of the operation system and its control system. When a high capacity power plant is tripped, a 24 MW ESS supplies power automatically and 4 units of 125MW ESS supply power manually. This study only focuses on transient state analysis. It was verified that 500 MW ESS can regulate system frequency faster and more effectively than conventional power plants. Also, it was verified that time-delayed high speed operations of multiple ESS facilities do not negatively impact power system operations. It is recommended that further testing be conducted for a fleet of multiple ESSs with different capacities distributed over multiple substations (e.g. 16, 24, 28, and 48 MW ESS distributed across 20 substations) because each ESS measures frequency individually. The operation of one ESS facility will differ from the other ESSs within the fleet, and may negatively impact the performance of the others. The following are also recommended: (a) studies wherein all ESSs should be operated in automatic mode; (b) studies on the improvement of individual ESS control; and (c) studies on the reapportionment of all ESS energies within the fleet.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.29 no.4
• /
• pp.78-86
• /
• 2011

The recovering of historical mountain fortress needs the maintenance of forest scape for achieving visibility. In the study, the methods for the maintenance of the forest around the fortress were proposed. The Cumulative Visibility Analysis and Multiple Sight Surface Analysis were tested to verify the methods using GIS on the Myeong-hwal Fortress in Kyungju. The results of the study are as follows. First, the Cumulative Visibility Analysis was made on the Myeong-hwal Fortress from surrounding major viewpoints. The Cumulative Visibility Analysis enables the selection of excellent visibility sectors on the fortress. The 6 excellent visibility sectors were 1,937m(which occupied 41.2% of the area). Second, two cases of pine tree height were compared in the Cumulative Visibility Analysis. One used the average height of pines and the other used the maximum growth height. The comparative result demonstrated that the case of average height would be more effective for deciding the pine removal zone as well as achieving visibility to the mountain fortress. Third, to examine the feasibility of the management method, the tree removal plan and removal execution were compared on the A zone which showed high visibility frequency. Asa comparative result, there was insignificant difference(3.3%) in area between the tree removal plan($10,935m^2$) and removal execution($11,296m^2$). This study proved the Cumulative Visibility Analysis and Multiple Sight Surface Analysis to be effective for forest scape maintenance around a mountain fortress.

• Journal of the Korean earth science society
• /
• v.21 no.4
• /
• pp.408-422
• /
• 2000

Multiple geophysical methods were applied over the Manjang cave area in Cheju Island to compare and contrast the effectiveness of each method for exploration of underground cavities. The used methods are gravity, magnetic, electrical resistivity and GPR(Ground Pentrating Radar) survey, of which instruments are portable and operations are relatively economical. We have chosen seven survey lines and applied appropriate multiple surveys depending on the field conditions. In the case of magnetic method. two-dimensional grid-type surveys were carried out to cover the survey area. The geophysical survey results reveal the characteristic responses of each method relatively well. Among the applied methods, the electric resistivity methods appeared to be the most effective ones in detecting the Manjang Cave and surrounding miscellaneous cavities. Especially, on the inverted resistivity section obtained from the dipole-dipole array data, the two-dimensional distribution of high resistivity cavities are revealed well. The gravity and magnetic data are contaminated easily by various noises and do not show the definitive responses enough to locate and delineate the Manjang cave. But they provide useful information in verifying the dipole-dipole resistivity survey results. The grid-type 2-D magnetic survey data show the trend of cave development well, and it may be used as a reconnaissance regional survey for determining survey lines for further detailed explorations. The GPR data show very sensitive response to the various shallow volcanic structures such as thin spaces between lava flows and small cavities, so we cannot identify the response of the main cave. Although each geophysical method provides its own useful information, the integrated interpretation of multiple survey data is most effective for investigation of the underground caves.

• Journal of the Korea Computer Graphics Society
• /
• v.14 no.4
• /
• pp.7-18
• /
• 2008

To realistically produce fluids such as smoke for the visual effects in the films or animations, we need two main processes: a physics-based modeling of smoke and a rendering of smoke simulation data, based on light transport theory. In the computer graphics community, the physics-based fluids simulation is generally adopted for smoke modeling. Recently, the interest of the particle-based Lagrangian simulation methods is increasing due to the advantages at simulation time, instead of the grid-based Eulerian simulation methods which was widely used. As a result, because the smoke rendering technique depends heavily on the modeling method, the research for rendering of the particle-based smoke data still remains challenging while the research for rendering of the grid-based smoke data is actively in progress. This paper focuses on realistic rendering technique for the smoke particles produced by Lagrangian simulation method. This paper introduces a technique which is called particle map, that is the expansion and modification of photon mapping technique for the particle data. And then, this paper suggests the novel particle map technique and shows the differences and improvements, compared to previous work. In addition, this paper presents irradiance map technique which is the pre-calculation of the multiple scattering term in the volume rendering equation to enhance efficiency at rendering time.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.50 no.4
• /
• pp.221-237
• /
• 2005

For developing the site-specific fertilizer management strategies of crop, it is essential to know the spatial variability of soil factors and to assess their influence on the variability of crop growth and yield. In 2002 and 2003 cropping seasons within-field spatial variability of rice growth and yield was examined in relation to spatial variation of soil properties in the· two paddy fields having each area of ca. $6,600m^2$ in Suwon, Korea. The fields were managed without fertilizer or with uniform application of N, P, and K fertilizer under direct-seeded and transplanted rice. Stable soil properties such as content of clay (Clay), total nitrogen (TN), organic mater (OM), silica (Si), cation exchange capacity (CEC), and rice growth and yield were measured in each grid of $10\times10m$. The two fields showed quite similar spatial variation in soil properties, showing the smallest coefficient of variation (CV) in Clay $(7.6\%)$ and the largest in Si $(21.4\%)$. The CV of plant growth parameters measured at panicle initiation (PIS) and heading stage (HD) ranged from 6 to $38\%$, and that of rice yield ranged from 11 to $21\%$. CEC, OM, TN, and available Si showed significant correlations with rice growth and yield. Multiple linear regression model with stepwise procedure selected independent variables of N fertilizer level, climate condition and soil properties, explaining as much as $76\%$ of yield variability, of which $21.6\%$ is ascribed to soil properties. Among the soil properties, the most important soil factors causing yield spatial variability was OM, followed by Si, TN, and CEC. Boundary line response of rice yield to soil properties was represented well by Mitcherich equation (negative exponential equation) that was used to quantify the influence of soil properties on rice yield, and then the Law of the Minimum was used to identify the soil limiting factor for each grid. This boundary line approach using five stable soil properties as limiting factor explained an average of about $50\%$ of the spatial yield variability. Although the determination coefficient was not very high, an advantage of the method was that it identified clearly which soil parameter was yield limiting factor and where it was distributed in the field.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.1
• /
• pp.454-459
• /
• 2017

In this study, a thermal system was designed using a 3-way valve and PTC attached to a solar module. This design could help solve the problem of rising fossil fuel costs caused by limited reserves and environmental problems resulting from fossil fuel use. The thermal system is a hot-air and heating control system composed of a temperature sensor part, mode setting part (for hot air and heating modes), supply part, and thermal system control part. The temperature sensor part has piping and an indoor temperature display, and the temperature setting part has multiple monitoring functions. The mode setting part switches between hot air and heating modes and can be used to set the temperature. The thermal system control part performs functions such as PTC control and temperature setting, PTC day and night and time selection, hot air and heating control, and three-way valve selection. The results verify that the system operates with stable response speeds of $680{\mu}s$ in the temperature sensor part, $700{\mu}s$ in the mode setting part, and $610{\mu}s$ in the thermal system control part.

• The KIPS Transactions:PartD
• /
• v.11D no.4
• /
• pp.983-990
• /
• 2004

Multiple-count problem is occurred when rectangle objects span across several buckets. The CD histogram is a technique which selves this problem by keeping four sub-histograms corresponding to the four points of rectangle. Although It provides exact results with constant response time, there is still a considerable issue. Since it is based on a query window which aligns with a given grid, a number of errors nay be occurred when it is applied to real applications. In this paper, we propose selectivity estimation techniques using the generalized cumulative density histogram based on two probabilistic models : \circled1 probabilistic model which considers the query window area ratio, \circled2 probabilistic model which considers intersection area between a given grid and objects. Our method has the capability of eliminating an impact of the restriction on query window which the existing cumulative density histogram has. We experimented with real datasets to evaluate the proposed methods. Experimental results show that the proposed technique is superior to the existing selectivity estimation techniques. Furthermore, selectivity estimation technique based on probabilistic model considering the intersection area is very accurate(less than 5% errors) at 20% query window. The proposed techniques can be used to accurately quantify the selectivity of the spatial range query on rectangle objects.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.8
• /
• pp.171-180
• /
• 2020

Smart Factory consists of digital automation solutions throughout the production process, including design, development, manufacturing and distribution, and it is an intelligent factory that installs IoT in its internal facilities and machines to collect process data in real time and analyze them so that it can control itself. The smart factory's equipment works in a physical combination of numerous hardware, rather than a virtual character being driven by a single object, such as a game. In other words, for a specific common goal, multiple devices must perform individual actions simultaneously. By taking advantage of the smart factory, which can collect process data in real time, if reinforcement learning is used instead of general machine learning, behavior control can be performed without the required training data. However, in the real world, it is impossible to learn more than tens of millions of iterations due to physical wear and time. Thus, this paper uses simulators to develop grid sortation systems focusing on transport facilities, one of the complex environments in smart factory field, and design cooperative multi-agent-based reinforcement learning to demonstrate efficient behavior control.