• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.11
• /
• pp.527-536
• /
• 2017

With the recent development of smart grid industry, the necessity for efficient EMS(Energy Management System) has been increased. In particular, in order to reduce electric load and energy cost, sophisticated electric load forecasting and efficient smart grid operation strategy are required. In this paper, for more accurate electric load forecasting, we extend the data collected at demand time into high time resolution and construct an artificial neural network-based forecasting model appropriate for the high time resolution data. Furthermore, to improve the accuracy of electric load forecasting, time series data of sequence form are transformed into continuous data of two-dimensional space to solve that problem that machine learning methods cannot reflect the periodicity of time series data. In addition, to consider external factors such as temperature and humidity in accordance with the time resolution, we estimate their value at the time resolution using linear interpolation method. Finally, we apply the PCA(Principal Component Analysis) algorithm to the feature vector composed of external factors to remove data which have little correlation with the power data. Finally, we perform the evaluation of our model through 5-fold cross-validation. The results show that forecasting based on higher time resolution improve the accuracy and the best error rate of 3.71% was achieved at the 3-min resolution.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.32 no.5
• /
• pp.313-322
• /
• 2019

Recently, there have been frequent occurrences of bridge fires. Fires in cable-supported bridges can damage and brake cables due to high temperatures. In this study, fire scenarios that can occur on cable-supported bridges were set up. In addition, based on the results of vehicle fire tests, a fire intensity model was proposed and cable heat transfer analyses were performed on a target bridge. The analyses results demonstrated that temperature rises were identified on cables with a smaller cross-sectional area. Furthermore, vehicles other than tankers did not exceed the fire resistance criteria. When the tanker fire occurred on a bridge shoulder, the minimum diameter cable exceeded the fire resistance criteria; the height of the cable exceeding the fire resistance criteria was approximately 14 m from the surface. Therefore, the necessity of countermeasures and reinforcements of fire resistance was established. The results of this study confirmed that indirect evaluation of the temperature changes of bridge cables under fire is possible, and it was deemed necessary to further study the heat transfer analysis considering wind effects and the serviceability of the bridge when the cable temperature rises due to fire.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2008.03a
• /
• pp.89-96
• /
• 2008

This paper investigates the effect of blade deformation, caused by manufacturing inaccuracies, on the performance of a 2-stage axial steam turbine. A high fidelity 3D coordinate Measurement Machine has been employed to obtain the exact geometrical model of the blades. A Streamline Curvature solver was used to predict the overall performance of the turbine. During the manufacturing process of the casts and of the blades themselves, several types of errors can occur which lead to a different geometry from that envisaged by the designer. The main objective of this study is to investigate the effect of those errors on the performance of a 2-stage experimental axial steam turbine. A high fidelity measurement of the actual geometry of both stator and rotor blades has been carried out, using a 3D Coordinate Measurement Machine. The cross sections of the blades obtained by the measurement were compared with those produced by the design process to evaluate the change in blade inlet/exit angles. In addition, the geometrical deviations from the initial design have been subjected to a statistical study in order to locate the nature of the error. The actual(measured) model has been used as input into a Streamline Curvature solver to evaluate its performance. Finally, a comparison with the performance plots of the original geometry has been carried out. A measurable change of efficiency as well as in the total power delivered by the turbine was found. This suggests that the accumulated error caused during the manufacturing procedure plays a significant role in the overall performance of the machine by making it less efficient by more than 1%. Reverse engineering techniques are proposed to predict and alleviate these errors leading thereby to a final design of each stage with improved performance.

• Geophysics and Geophysical Exploration
• /
• v.1 no.1
• /
• pp.8-18
• /
• 1998

In exploration seismology, the Kirchhoff hyperbola has been successfully used to migrate reflection seismo-grams. The mathematical basis of Kirchhoff hyperbola has not been clearly defined and understood for the application of prestack or poststack migration. The travel time from the scatterer in the subsurface to the receivers (exploding reflector model) on the surface can be a kinematic approximation of Green's function when the source is excited at position of the scatterer. If we add the travel time from the source to the scatterer in the subsurface to the travel time of exploding reflector model, we can view this travel time as a kinematic approximation of the partial derivative wavefield with respect to the velocity or the density in the subsurface. The summation of reflection seismogram along the Kirchhoff hyperbola can be evaluated as an inner product between the partial derivative wavefield and the field reflection seismogram. In addition to this kinematic interpretation of Kirchhoff hyperbola, when we extend this concept to shallow refraction seismic data, the stacking of refraction data along the straight line can be interpreted as a measurement of an inner product between the first arrival waveform of the partial derivative wavefield and the field refraction data. We evaluated the Kirchhoff hyperbola and the straight line for stacking the refraction data in terms of the first arrival waveform of the partial derivative wavefield with respect to the velocity or the density in the subsurface. This evaluation provides a firm and solid basis for the conventional Kirchhoff migration and the straight line stacking of the refraction data.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.1
• /
• pp.34-45
• /
• 2021

Weather is one of the important factors in the agricultural industry as it affects the price, production, and quality of crops. Upland crops are directly exposed to the natural environment because they are mainly grown in mountainous areas. Therefore, it is necessary to provide accurate weather for upland crops. This study examined the effectiveness of 12 forest soil factors to interpolate the weather in mountainous areas. The daily temperature and precipitation were collected by the Korea Meteorological Administration between January 2009 and December 2018. The Generalized Additive Model (GAM), Kriging, and Random Forest (RF) were considered to interpolate. For evaluating the interpolation performance, automatic weather stations were used as training data and automated synoptic observing systems were used as test data for cross-validation. Unfortunately, the forest soil factors were not significant to interpolate the weather in the mountainous areas. GAM with only geography aspects showed that it can interpolate well in terms of root mean squared error and mean absolute error. The significance of the factors was tested at the 5% significance level in GAM, and the climate zone code (CLZN_CD) and soil water code B (SIBFLR_LAR) were identified as relatively important factors. It has shown that CLZN_CD could help to interpolate the daily average and minimum daily temperature for upland crops.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.5B
• /
• pp.501-509
• /
• 2006

The safety of levee that depends on the river flood elevation has been regarded as very important keys to build up various flood prevention systems. However, deterministic methods for computation of water surface profile cannot reflect the effect of possible inaccuracies in the input parameters. The purpose of this study is to develop a methodology of uncertainty computation of design flood level based on steady flow analysis and Monte Carlo simulation. This study addresses the uncertainty of water surface elevation by Manning's coefficients, design discharges, river cross sections and boundary condition. Monte Carlo simulation with the variations of these parameters is performed to quantify the variations of water surface elevations in a river. The proposed model has been applied to the Kumho-river. The reliability analysis was performed within 38.5 km (95 sections) reach considered the variations of the above-mentioned parameters. Overtopping risks were evaluated by comparing the elevations of the flood condition with the those of the levees. The results show that there is a necessity which will raise the levee elevation between 1 cm and 56 cm at 7 sections. The model can be used for preparing flood risk maps, flood forecasting systems and establishing flood disaster mitigation plans as well as complement of conventional levee design.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.26 no.4
• /
• pp.197-206
• /
• 2014

The purpose of this study is to evaluate coastal erosion due to a sea-level rise. The shoreline retreat rate was calculated due to future sea-level rise. Shoreline retreat rates were quantified with the cross-sectional data of 23 sandy coasts (12 sites from east coast, 5 sites from south coast, and 6 sites of west coast) and 3 cross-sectional profiles from each side of the coasts in Korea. The theory of equilibrium beach profile was employed in this study to evaluate the applicability of the theory into the coast of Korea and was tested with 15 cross-sectional beach profiles. Four scenarios of future sea level rise such as 38 cm, 59 cm, 75 cm, and 100 cm were adopted to estimate the shoreline retreat rates. Overall shoreline retreat rates for the coasts in Korea were predicted as 43.7% for 38 cm, 60.3% for 59 cm, 69.2% for 75 cm, and 80.1% for 100 cm sea level rises, respectively. Retreat rates in the east coast (29.6% for 38 cm, 45.1% for 59 cm, 56.0% for 75 cm, and 69.9% for 100 cm) showed relatively low compared to the south coast (51.9%, 67.6%, 77.2%, 87.3%) and the west coast (53.8%, 71.0%, 78.5%, 86.4%). However, all sandy coasts in Korea were assessed to be vulnerable with increasing sea-level rise. There are uncertainties in the assessment of this study, which include the limitation of the assessment model and the lack of the spatio-temporal data of the beach profiles. Therefore, this study shows that it is very important to spend integrated efforts to respond coastal erosion including comprehensive observations(monitoring) and the development of scientific understanding on the field.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.139-156
• /
• 2021

The biggest reason for using a deep learning model in image classification is that it is possible to consider the relationship between each region by extracting each region's features from the overall information of the image. However, the CNN model may not be suitable for emotional image data without the image's regional features. To solve the difficulty of classifying emotion images, many researchers each year propose a CNN-based architecture suitable for emotion images. Studies on the relationship between color and human emotion were also conducted, and results were derived that different emotions are induced according to color. In studies using deep learning, there have been studies that apply color information to image subtraction classification. The case where the image's color information is additionally used than the case where the classification model is trained with only the image improves the accuracy of classifying image emotions. This study proposes two ways to increase the accuracy by incorporating the result value after the model classifies an image's emotion. Both methods improve accuracy by modifying the result value based on statistics using the color of the picture. When performing the test by finding the two-color combinations most distributed for all training data, the two-color combinations most distributed for each test data image were found. The result values were corrected according to the color combination distribution. This method weights the result value obtained after the model classifies an image's emotion by creating an expression based on the log function and the exponential function. Emotion6, classified into six emotions, and Artphoto classified into eight categories were used for the image data. Densenet169, Mnasnet, Resnet101, Resnet152, and Vgg19 architectures were used for the CNN model, and the performance evaluation was compared before and after applying the two-stage learning to the CNN model. Inspired by color psychology, which deals with the relationship between colors and emotions, when creating a model that classifies an image's sentiment, we studied how to improve accuracy by modifying the result values based on color. Sixteen colors were used: red, orange, yellow, green, blue, indigo, purple, turquoise, pink, magenta, brown, gray, silver, gold, white, and black. It has meaning. Using Scikit-learn's Clustering, the seven colors that are primarily distributed in the image are checked. Then, the RGB coordinate values of the colors from the image are compared with the RGB coordinate values of the 16 colors presented in the above data. That is, it was converted to the closest color. Suppose three or more color combinations are selected. In that case, too many color combinations occur, resulting in a problem in which the distribution is scattered, so a situation fewer influences the result value. Therefore, to solve this problem, two-color combinations were found and weighted to the model. Before training, the most distributed color combinations were found for all training data images. The distribution of color combinations for each class was stored in a Python dictionary format to be used during testing. During the test, the two-color combinations that are most distributed for each test data image are found. After that, we checked how the color combinations were distributed in the training data and corrected the result. We devised several equations to weight the result value from the model based on the extracted color as described above. The data set was randomly divided by 80:20, and the model was verified using 20% of the data as a test set. After splitting the remaining 80% of the data into five divisions to perform 5-fold cross-validation, the model was trained five times using different verification datasets. Finally, the performance was checked using the test dataset that was previously separated. Adam was used as the activation function, and the learning rate was set to 0.01. The training was performed as much as 20 epochs, and if the validation loss value did not decrease during five epochs of learning, the experiment was stopped. Early tapping was set to load the model with the best validation loss value. The classification accuracy was better when the extracted information using color properties was used together than the case using only the CNN architecture.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.28 no.6
• /
• pp.256-268
• /
• 2016

This article reviews the papers published in the Korean Journal of Air-Conditioning and Refrigeration Engineering during 2015. It is intended to understand the status of current research in the areas of heating, cooling, ventilation, sanitation, and indoor environments of buildings and plant facilities. Conclusions are as follows. (1) The research works on the thermal and fluid engineering were carried out in the areas of flow, heat and mass transfer, cooling and heating, and air-conditioning, the renewable energy system and the flow inside building rooms. Research issues dealing with air-conditioning machines and fire and exhausting smoke were reduced. CFD seems to be spreading to more research areas. (2) Research works on heat transfer area were carried out in the categories of heat transfer characteristics, pool boiling and condensing heat transfer and industrial heat exchangers. Researches on heat transfer characteristics included the economic analysis of GHG emission, micro channel heat exchanger, effect of rib angle on thermal performance, the airside performance of fin-and-tube heat exchangers, theoretical analysis of a rotary heat exchanger, heat exchanger in a cryogenic environment, the performance of a cross-flow-type, indirect evaporative cooler made of paper/plastic film. In the area of pool boiling and condensing, the bubble jet loop heat pipe was studied. In the area of industrial heat exchangers, researches were performed on fin-tube heat exchanger, KSTAR PFC and vacuum vessel at baking phase, the performance of small-sized dehumidification rotor, design of gas-injection port of an asymmetric scroll compressor, effect of slot discharge-angle change on exhaust efficiency of range hood system with air curtain. (3) In the field of refrigeration, various studies were carried in the categories of refrigeration cycle, alternative refrigeration/energy system, system control. In the refrigeration cycle category, a cold-climate heat pump system, $CO_2$ cascade systems, ejector cycles and a PCM-based continuous heating system were investigated. In the alternative refrigeration/energy system category, a polymer adsorption heat pump, an alcohol absorption heat pump and a desiccant-based hybrid refrigeration system were investigated. In the system control category, turbo-refrigerator capacity controls and an absorption chiller fault diagnostics were investigated. (4) In building mechanical system research fields, eighteen studies were reported for achieving effective design of the mechanical systems, and also for maximizing the energy efficiency of buildings. The topics of the studies included energy performance, HVAC system, ventilation, and renewable energies, piping in the buildings. Proposed designs, performance tests using numerical methods and experiments provide useful information and key data which can improve the energy efficiency of the buildings. (5) The field of architectural environment was mostly focused on indoor environment and building energy. The main researches of indoor environment were related to the user and location awareness technology applied dimming lighting control system, the lighting performance evaluation for light-shelves, the improvement evaluation of air quality through analysis of ventilation efficiency and the evaluation of airtightness of sliding and LS window systems. The subjects of building energy were worked on the energy saving estimation of existing buildings, the developing model to predict heating energy usage in domestic city area and the performance evaluation of cooling applied with economizer control. The studies were also performed related to the experimental measurement of weight variation and thermal conductivity in polyurethane foam, the development of flame spread prevention system for sandwich panels, the utilization of heat from waste-incineration facility in large-scale horticultural facilities.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.949-965
• /
• 2023

In this study, we propose a method to monitor the surface area of agricultural reservoirs in South Korea using Sentinel-1 synthetic aperture radar images and the deep learning model, Swin Transformer. Utilizing the Google Earth Engine platform, datasets from 2017 to 2021 were constructed for seven agricultural reservoirs, categorized into 700 K-ton, 900 K-ton, and 1.5 M-ton capacities. For four of the reservoirs, a total of 1,283 images were used for model training through shuffling and 5-fold cross-validation techniques. Upon evaluation, the Swin Transformer Large model, configured with a window size of 12, demonstrated superior semantic segmentation performance, showing an average accuracy of 99.54% and a mean intersection over union (mIoU) of 95.15% for all folds. When the best-performing model was applied to the datasets of the remaining three reservoirsfor validation, it achieved an accuracy of over 99% and mIoU of over 94% for all reservoirs. These results indicate that the Swin Transformer model can effectively monitor the surface area of agricultural reservoirs in South Korea.