• Applied Chemistry for Engineering
• /
• v.29 no.6
• /
• pp.789-798
• /
• 2018

The role of empirical equation to predict the performance of polymer electrolyte membrane fuel cell is important. The activation, ohmic and mass transfer losses were separated in a polarization curve, and the curve fitting according to each region was performed using Kim's model and Hao's model. Changes of each loss were compared according to operation variables of the temperature, pressure, oxygen concentration and membrane thickness. The existing model showed a good fitting convergence, but less fitting accuracy in the separated loss region. A new model using the convergence coefficient was suggested to improve the accuracy of performance prediction of fuel cells of which results were demonstrated.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.19 no.7
• /
• pp.1691-1701
• /
• 1995

Two aspects of Large-Eddy Simulation(LES) are investigated in order to improve its performance. The first one is on how to determine the model coefficient in conjunction with a dynamic subgrid-scale model, and the second one is on a wall-layer model(WLM) which allows one to skip near-wall regions to save a large number of grid points otherwise required. Especially, a WLM suitable for a separated flow is considered. Firstly, an averaging technique to calculate the model coefficient of dynamic subgrid-scale modeling(DSGSM) is introduced. The technique is based on the concept of local averaging, and useful to stabilize numerical solution in conjunction with LES of complex turbulent flows using DSGSM. It is relatively simple to implement, and takes very low overhead in CPU time. It is also able to detect the region of negative model coefficient where the "backscattering" of turbulence energy occurs. Secondly, a wall-layer model based on a local turbulence intensity is considered. It locally determines wall-shear stresses depending on the local flow situations including separation, and yields better predictions in separated regions than the conventional WLM. The two techniques are tested for a turbulent obstacle flow, and show the direction of further improvements.rovements.

• Journal of the Korea Organic Resources Recycling Association
• /
• v.29 no.4
• /
• pp.99-106
• /
• 2021

The purpose of this study was to evaluate the performance of novel process with thermal hydrolysis and separation as pre-treatment of anaerobic digestion (AD). The dewatered sludge was pre-treated using THP, and then separated. The separated liquid used as substrate for AD and separated solid was returned on THP(Thermal Hydrolysis Process). The degree of disintegration (DD, based on COD) using only THP found 45.1-49.3%. The DD using THP+separation found 76.1-77.6%, which was higher than only THP. As result from dual-pool two-step model, the ratio of rapidly degradable substrate to total degradable substrate found 0.891-0.911 in separated liquid, which was higher than only THP. However, the rapidly degradable substrate reaction constant (kF) of only THP and THP+separation were similar. This results found that dewatered sludge was disintegrated by THP, and then rapidly degradable substrate of hydrolyzed sludge was sorted by separation.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.69-88
• /
• 2022

One of the characteristics of South Korea's economic structure is that it is highly dependent on exports. Thus, many businesses are closely related to the global economy and diplomatic situation. In addition, small and medium-sized enterprises(SMEs) specialized in exporting are struggling due to the spread of COVID-19. Therefore, this study aimed to develop a model to forecast exports for next year to support SMEs' export strategy and decision making. Also, this study proposed a strategy to recommend promising export countries of each item based on the forecasting model. We analyzed important variables used in previous studies such as country-specific, item-specific, and macro-economic variables and collected those variables to train our prediction model. Next, through the exploratory data analysis(EDA) it was found that exports, which is a target variable, have a highly skewed distribution. To deal with this issue and improve predictive performance, we suggest a separated learning method. In a separated learning method, the whole dataset is divided into homogeneous subgroups and a prediction algorithm is applied to each group. Thus, characteristics of each group can be more precisely trained using different input variables and algorithms. In this study, we divided the dataset into five subgroups based on the exports to decrease skewness of the target variable. After the separation, we found that each group has different characteristics in countries and goods. For example, In Group 1, most of the exporting countries are developing countries and the majority of exporting goods are low value products such as glass and prints. On the other hand, major exporting countries of South Korea such as China, USA, and Vietnam are included in Group 4 and Group 5 and most exporting goods in these groups are high value products. Then we used LightGBM(LGBM) and Exponential Moving Average(EMA) for prediction. Considering the characteristics of each group, models were built using LGBM for Group 1 to 4 and EMA for Group 5. To evaluate the performance of the model, we compare different model structures and algorithms. As a result, it was found that the separated learning model had best performance compared to other models. After the model was built, we also provided variable importance of each group using SHAP-value to add explainability of our model. Based on the prediction model, we proposed a second-stage recommendation strategy for potential export countries. In the first phase, BCG matrix was used to find Star and Question Mark markets that are expected to grow rapidly. In the second phase, we calculated scores for each country and recommendations were made according to ranking. Using this recommendation framework, potential export countries were selected and information about those countries for each item was presented. There are several implications of this study. First of all, most of the preceding studies have conducted research on the specific situation or country. However, this study use various variables and develops a machine learning model for a wide range of countries and items. Second, as to our knowledge, it is the first attempt to adopt a separated learning method for exports prediction. By separating the dataset into 5 homogeneous subgroups, we could enhance the predictive performance of the model. Also, more detailed explanation of models by group is provided using SHAP values. Lastly, this study has several practical implications. There are some platforms which serve trade information including KOTRA, but most of them are based on past data. Therefore, it is not easy for companies to predict future trends. By utilizing the model and recommendation strategy in this research, trade related services in each platform can be improved so that companies including SMEs can fully utilize the service when making strategies and decisions for exports.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.26 no.7
• /
• pp.875-880
• /
• 2016

A new hybrid permanent magnet biased magnetic levitation actuator (maglev) is developed. This new maglev actuator is composed of two C-core electromagnetic cores separated with two permanent magnets. Compared to the conventional hybrid maglev actuators, the new actuator has unique flux paths such that bias flux paths are separated with control flux paths. The control flux paths have minimum reluctances only developed by air gaps, so the currents to produce control fluxes can be minimized. The gravity load can be compensated with the permanent magnet bias fluxes developed at off-centered air gap positions while external disturbances are controlled with control fluxes by currents. The consumed power to operate this levitation system can be minimized. 1-D magnetic circuit model is developed for this model such that the flux densities and magnetic forces are extensively analyzed. 3-D finite element model is also developed to analyze the performances of the maglev actuator.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.1085-1088
• /
• 1999

This paper presents a method for soccer scene analysis and coordinate transformation from scene to ground model using a priori knowledge. First, the ground and spectator regions are separated, and various objects are extracted from the separated ground region. Second, an affine model is used for mapping the object positions on the soccer image into the position on the ground model. Problems regarding holes arising from mapping processing are solved using inverse mapping instead of a usual interpolation method. Experiments are performed on a PC using about 100 RGB images acquired at 240＊640 resolution and 3∼5 frames per second.

• Journal of Advanced Marine Engineering and Technology
• /
• v.38 no.7
• /
• pp.821-827
• /
• 2014

In this study, an experimental study was performed to predict the two-phase frictional pressure drop of FC-72 in parallel micro-channels. The parallel micro-channels consist of 15 channels with depth 0.2 mm, width 0.45 mm and length 60 mm. And tests were performed in the ranges of mass fluxes from 152.2 to $584.2kg/m^2s$ and heat fluxes from 7.5 to $28.3kW/m^2$. The experimental data was compared and analyzed with existing correlations to predict the pressure drop. The existing methods to predict the pressure drop used the homogeneous model and the separated model. In this study, the new correlation was proposed by modified existing correlation using the separated model, and the new correlation predicted consequently with the experimental data within MAE of 9.6%.

• Design & Manufacturing
• /
• v.15 no.3
• /
• pp.1-6
• /
• 2021

An artificial neural network model based on a deep learning algorithm is known to be more accurate than humans in image classification, but there is still a limit in the sense that there needs to be a lot of training data that can be called big data. Therefore, various techniques are being studied to build an artificial neural network model with high precision, even with small data. The transfer learning technique is assessed as an excellent alternative. As a result, the purpose of this study is to develop an artificial neural network system that can classify burr images of light guide plate products with 99% accuracy using transfer learning technique. Specifically, for the light guide plate product, 150 images of the normal product and the burr were taken at various angles, heights, positions, etc., respectively. Then, after the preprocessing of images such as thresholding and image augmentation, for a total of 3,300 images were generated. 2,970 images were separated for training, while the remaining 330 images were separated for model accuracy testing. For the transfer learning, a base model was developed using the NASNet-Large model that pre-trained 14 million ImageNet data. According to the final model accuracy test, the 99% accuracy in the image classification for training and test images was confirmed. Consequently, based on the results of this study, it is expected to help develop an integrated AI production management system by training not only the burr but also various defective images.

• Journal of Fisheries and Marine Sciences Education
• /
• v.25 no.3
• /
• pp.625-631
• /
• 2013

Two-phase pressure drop experiments were performed during flow boiling to deionized water in a microchannel having a hydraulic diameter of $500{\mu}m$. Tests were made in the ranges of heat fluxes from 100 to $400kW/m^2$, vapor qualities from 0 to 0.2 and mass fluxes of 200, 400 and $600kg/m^2s$. The frictional pressure drop during flow boiling is predicted by using two models; the homogeneous model that assumes equal phase velocity and the separate flow model that allows a slip velocity between two phases. From the experimental results, it is found that the two phase multiplier decreases with an increase in mass flux. Measured data of pressure drop are compared to a few available correlations proposed for macroscale and mini/microscale. Among the separated flow models, the correlation model suggested by Lee and Garimella predicted the frictional pressure drop within MAE of 47.2%, which is better than other correlations.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1996.06b
• /
• pp.18-21
• /
• 1996

In the field of Virtual Reality, many studies have been reported. Especially, there are many studies on generating virtual creatures on computer systems. In this paper we propose an algorithm to automatically generate 3D fish models from 2D images which are printed in illustrated books, pictures or handwritings. At first, 2D fish images are captured by means of image scanner. Next, the fish image is separated from background and segmented to several parts such as body, anal fin, dorsal fin, ectoral fin and ventral fin using the proposed method“Active Balloon model”. After that, users choose front view model and top view model among six samples, respectively. 3D model is automatically generated from separated body, fins and the above two view models. The number of patches is decreased without any influence on the accuracy of the generated 3D model to reduce the time cost when texture mapping is applied. Finally, we can get any kinds of 3D fish models.