• 한국재료학회지
• /
• 제33권7호
• /
• pp.273-278
• /
• 2023

In this study, based on the saturation magnetic flux density experimental values (B_s) of 622 Fe-based bulk metallic glasses (BMGs), regression models were applied to predict B_s using artificial neural networks (ANN), and prediction performance was evaluated. Model performance evaluation was investigated by using the F1 score together with the coefficient of determination (R² score), which is mainly used in regression models. The coefficient of determination can be used as a performance indicator, since it shows the predicted results of the saturation magnetic flux density of full material datasets in a balanced way. However, the BMG alloy contains iron and requires a high saturation magnetic flux density to have excellent applicability as a soft magnetic material, and in this study F1 score was used as a performance indicator to better predict B_s above the threshold value of B_s (1.4 T). After obtaining two ANN models optimized for the R² and F1 score conditions, respectively, their prediction performance was compared for the test data. As a case study to evaluate the prediction performance, new Fe-based BMG datasets that were not included in the training and test datasets were predicted using the two ANN models. The results showed that the model with an excellent F1 score achieved a more accurate prediction for a material with a high saturation magnetic flux density.

• 멤브레인
• /
• 제10권1호
• /
• pp.30-38
• /
• 2000

투과증발공정에서 polydimethylsiloxane(PDMS)막에 대한 용매의 수착특성과 투과 플럭스를 예측하는 방법을 제시하였다. 이 방법을 이용하여 chloroform, toluene, methoanol, n-butanol의 수착량과 투과 플럭스를 계산하였으며, 계산값과 실험값을 비교하였다. 팽윤을 촉진시키는 정용매(good solvent)인 toluene과 chloroform의 경우 계산된 수착량과 투과 플럭스는 실험값과 잘 일치하였다. 막의 밀도가 작을수록 수착량과 투과 플럭스는 증가하였다. 팽윤을 억제시키는 부용매(poor solvent)인 methanol, n-butanol의 경우는 실험값과 상당한 오차가 있었다. 따라서, 본 미케니즘에 의해 PDMS막에 대한 정용매의 수착량과 투과 플럭스는 실험에 의하지 않고도 이론적으로 예측할 수 있는 가능성을 보여주었다.

• Journal of Mechanical Science and Technology
• /
• 제17권8호
• /
• pp.1171-1184
• /
• 2003

An experimental study on critical heat flux (CHF) has been performed in an internally heated vertical annulus with non-uniform heating. The CHF data for the chopped cosine heat flux have been compared with those for uniform heat flux obtained from the previous study of the authors, in order to investigate the effect of axial heat flux distribution on CHF. The local CHF with the parameters such as mass flux and critical quality shows an irregular behavior. However, the total critical power with mass flux and the average CHF with critical quality are represented by a unique curve without the irregularity. The effect of the heat flux distribution on CHF is large at low pressure conditions but becomes rapidly smaller as the pressure increases. The relationship between the critical quality and the boiling length is represented by a single curve, independent of the axial heat flux distribution. For non-uniform axial heat flux distribution, the prediction results from Doerffer et al.'s and Bowling's CHF correlations have considerably large errors, compared to the prediction for uniform heat flux distribution.

• 상하수도학회지
• /
• 제35권1호
• /
• pp.93-100
• /
• 2021

Forward osmosis (FO) process is a chemical potential driven process, where highly concentrated draw solution (DS) is used to take water through semi-permeable membrane from feed solution (FS) with lower concentration. Recently, commercial FO membrane modules have been developed so that full-scale FO process can be applied to seawater desalination or water reuse. In order to design a real-scale FO plant, the performance prediction of FO membrane modules installed in the plant is essential. Especially, the flux prediction is the most important task because the amount of diluted draw solution and concentrate solution flowing out of FO modules can be expected from the flux. Through a previous study, a theoretical based FO module model to predict flux was developed. However it needs an intensive numerical calculation work and a fitting process to reflect a complex module geometry. The idea of this work is to introduce deep learning to predict flux of FO membrane modules using 116 experimental data set, which include six input variables (flow rate, pressure, and ion concentration of DS and FS) and one output variable (flux). The procedure of optimizing a deep learning model to minimize prediction error and overfitting problem was developed and tested. The optimized deep learning model (error of 3.87%) was found to predict flux better than the theoretical based FO module model (error of 10.13%) in the data set which were not used in machine learning.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2001년도 추계학술대회논문집B
• /
• pp.288-293
• /
• 2001

A critical heat flux (CHF) prediction method using an artificial neural network (ANN) was evaluated for application to the high-heat-flux (HHF) subcooled flow boiling. The developed ANN predictions were compared with the experimental database consisting of a total of 3069 CHF data points. Also, the prediction performance by the ANN was compared with those by mechanistic models and a look up table technique. The parameter ranges of the experimental data are: $0.33{\leq}D{\leq}37.5mm$, $0.002{\leq}L{\leq}4m$, $0.37{\leq}G{\leq}134Mg/m^2s$, $0.1{\leq}P{\leq}20MPa$, $50\leq{\Delta}h_{sub,in}\leq1660kJ/kg$, and $1.1{\leq}q_{CHF}\leq276MW/m^2$. $276MW/m^2$. It was found that 91.5% of the total data points were predicted within $a{\pm}20%$ error band, which showed the best prediction performance among the existing CHF prediction methods considered.

• 한국항공우주학회지
• /
• 제35권9호
• /
• pp.826-835
• /
• 2007

발사체 열환경 설계를 위해서 여러 종류의 태양열 모델을 비교 검토하였으며, 측정된 태양열과 잘 일치하는 태양열 모델을 개발하였다. 기존의 태양열 모델은 태양 직사광 예측은 정확하지만 산란광에 대해서는 오차가 포함되어 있었다. 이에 반하여 새롭게 개발된 산란광 모델은 등방성, 이방성 산란을 고려하였으며 기존의 어느 모델보다 관측값과 잘 일치하였다. 우주 센터의 태양광 측정 데이터가 매우 적기 때문에 본 모델은 발사체 열하중 설계에 필요한 설계 데이터를 제공할 수 있었다. 또한 본 모델은 위도, 경도, 날짜, 고도에 대한 제한이 없는 일반적인 모델이기 때문에 추후 태양열에 민감한 반응을 보이는 비행기구 등의 개발에 효과적인 열환경 예측 수단을 제공할 수 있다.

• Nuclear Engineering and Technology
• /
• 제54권3호
• /
• pp.1126-1135
• /
• 2022

The MARS code has been assessed for the prediction of onset of flow instability (OFI) in a vertical channel. For assessment, we built an experiment database that consists of experiments under various geometry and thermal-hydraulic condition. It covers pressure from 0.12 to 1.73 MPa; heat flux from 0.67 to 3.48 MW/m²; inlet sub-cooling from 39 to 166 ℃; hydraulic diameters between 2.37 and 6.45 mm of rectangular channels and pipes. It was shown that the MARS code can predict the OFI mass flux for pipes reasonably well. However, it could not predict the OFI in a rectangular channel well with a mean absolute percentage error of 8.77%. In the cases of rectangular channels, the error tends to depend on the hydraulic diameter. Because the OFI is directly related to the subcooled boiling in a flow channel, we suggest a modified subcooled boiling model for better prediction of OFI in a rectangular channel; the net vapor generation (NVG) model and the modified wall evaporation model were modified so that the effect of hydraulic diameter and heat flux can be accurately considered. The assessment of the modified model shows the prediction of OFI mass flux for rectangular channels is greatly improved.

• Architectural research
• /
• 제2권1호
• /
• pp.41-46
• /
• 2000

The sawtooth skylight is an excellent daylighting concept for the uniform interior illuminance over large working areas. In computer simulation, it is difficult for an architect to get accurate daylight illuminances for the spaces where sawtooth apertures are applied. In this study, daylight prediction algorithms for sawtooth apertures are developed. The flux transfer method is applied for this study to predict daylight illuminances. The simplified equations from this study can be used effectively for preliminary prediction of daylight in sawtooth spaces.

• 한국전산유체공학회:학술대회논문집
• /
• 한국전산유체공학회 2004년도 추계 학술대회논문집
• /
• pp.221-225
• /
• 2004

Evaluation of turbulence models is performed for a better prediction of thermal stratification in an upper plenum of a liquid metal reactor by applying them to the experiment conducted at JNC. The turbulence models tested in the present study are the two-layer model, the $\kappa-\omega$ model, the v2-f model and the low-Reynolds number differential stress-flux model. When the algebraic flux model or differential flux model are used for treating the turbulent heat flux, there exist little differences between turbulence models in predicting the temporal variation of temperature. However, the v2-f model and the low-Reynolds number differential stress-flux model better predict the steep gradient o( temperature at the interface of thermal stratification, and only the v2-f model predicts properly the oscillation of temperature. The LES Is needed for a better prediction of the amplitude and frequency of the temperature fluctuation.

• 한국해양공학회지
• /
• 제22권1호
• /
• pp.13-21
• /
• 2008

In this study a method to predict CHF(Critical heat flux) in vertical round tubes with axially non-uniform cosine heat flux distribution for water was examined. For this purpose a local condition hypothesis based CHF prediction correlation for uniform heat flux in vertical round tubes for water was developed from 9,366 CHF data points. The local correlation consisted of 4 local condition variables: the system pressure(P), tube diameter(D), mass flux of water(G), and 'true mass quality' of vapor($X_t$). The CHF data points used were collected from 13 different published sources having the following operation ranges: 1.01 ${\leq}$ P (pressure) ${\leq}$ 206.79 bar, 9.92${\leq}$ G (mass flux) ${\leq}$ 18,619.39 $kg/m^2s$, 0.00102 ${\leq}$ D(diameter) ${\leq}$ 0.04468 m, 0.0254${\leq}$ L (length) ${\leq}$ 4.966 m, 0.11 ${\leq}$ qc (CHF) ${\leq}$ 21.41 $MVW/m^2$, and -0.87 ${\leq}X_c$ (exit qualities) ${\leq}$ 1.58. The result of this work showed that a uniform CHF correlation can be easily extended to predict CHF in axially non-uniform heat flux heater. In addition, the location of the CHF in axially non-uniform tube can also be determined. The local uniform correlation predicted CHF in tubes with axially cosine heat flux profile within the root mean square error of 12.42% and average error of 1.06% for 297 CHF data points collected from 5 different published sources.