• 산업경영시스템학회지
• /
• 제43권2호
• /
• pp.48-55
• /
• 2020

Recently, a study of prognosis and health management (PHM) was conducted to diagnose failure and predict the life of air craft engine parts using sensor data. PHM is a framework that provides individualized solutions for managing system health. This study predicted the remaining useful life (RUL) of aeroengine using degradation data collected by sensors provided by the IEEE 2008 PHM Conference Challenge. There are 218 engine sensor data that has initial wear and production deviations. It was difficult to determine the characteristics of the engine parts since the system and domain-specific information was not provided. Each engine has a different cycle, making it difficult to use time series models. Therefore, this analysis was performed using machine learning algorithms rather than statistical time series models. The machine learning algorithms used were a random forest, gradient boost tree analysis and XG boost. A sliding window was applied to develop RUL predictions. We compared model performance before and after applying the sliding window, and proposed a data preprocessing method to develop RUL predictions. The model was evaluated by R-square scores and root mean squares error (RMSE). It was shown that the XG boost model of the random split method using the sliding window preprocessing approach has the best predictive performance.

• Tribology and Lubricants
• /
• 제35권3호
• /
• pp.190-198
• /
• 2019

Gas foil bearings (GFBs) enable small- to medium-sized turbomachinery to operate at ultra-high speeds in a compact design by using ambient air or process gas as a lubricant. When using air or process gas, which have lower viscosity than lubricant oil, the turbomachinery has the advantage of reduced power loss from bearing friction drag. However, GFBs may have high Reynolds number, which causes turbulent flows due to process gas with low viscosity and high density. This paper analyzes gas foil journal bearings (GFJBs) with high Reynolds numbers and studies the effects of turbulent flows on the static and dynamic performance of bearings. For comparison purposes, air and R-134a gas lubricants are applied to the GFJBs. For the air lubricant, turbulence is dominant only at rotor speeds higher than 200 krpm. At those speeds, the journal eccentricity decreases, but the film thickness, power loss, and direct stiffness and damping coefficients increase. On the other hand, the R-134a gas lubricant, which that has much higher density than air, causes dominant turbulence at rotor speeds greater than 10 krpm. The turbulent flow model predicts decreased journal eccentricity but increased film thickness and power loss when compared with the lamina flow model predictions. The vertical direct stiffness and damping coefficients are lower at speeds below 100 krpm, but higher beyond that speeds for the turbulent model. The present results indicate that turbulent flow effects should be considered for accurate performance predictions of GFJBs with high Reynolds number.

• Korean Journal of Radiology
• /
• 제24권11호
• /
• pp.1151-1163
• /
• 2023

Objective: To develop a deep-learning-based bone age prediction model optimized for Korean children and adolescents and evaluate its feasibility by comparing it with a Greulich-Pyle-based deep-learning model. Materials and Methods: A convolutional neural network was trained to predict age according to the bone development shown on a hand radiograph (bone age) using 21036 hand radiographs of Korean children and adolescents without known bone development-affecting diseases/conditions obtained between 1998 and 2019 (median age [interquartile range {IQR}], 9 [7-12] years; male:female, 11794:9242) and their chronological ages as labels (Korean model). We constructed 2 separate external datasets consisting of Korean children and adolescents with healthy bone development (Institution 1: n = 343; median age [IQR], 10 [4-15] years; male: female, 183:160; Institution 2: n = 321; median age [IQR], 9 [5-14] years; male: female, 164:157) to test the model performance. The mean absolute error (MAE), root mean square error (RMSE), and proportions of bone age predictions within 6, 12, 18, and 24 months of the reference age (chronological age) were compared between the Korean model and a commercial model (VUNO Med-BoneAge version 1.1; VUNO) trained with Greulich-Pyle-based age as the label (GP-based model). Results: Compared with the GP-based model, the Korean model showed a lower RMSE (11.2 vs. 13.8 months; P = 0.004) and MAE (8.2 vs. 10.5 months; P = 0.002), a higher proportion of bone age predictions within 18 months of chronological age (88.3% vs. 82.2%; P = 0.031) for Institution 1, and a lower MAE (9.5 vs. 11.0 months; P = 0.022) and higher proportion of bone age predictions within 6 months (44.5% vs. 36.4%; P = 0.044) for Institution 2. Conclusion: The Korean model trained using the chronological ages of Korean children and adolescents without known bone development-affecting diseases/conditions as labels performed better in bone age assessment than the GP-based model in the Korean pediatric population. Further validation is required to confirm its accuracy.

• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 1996년도 추계학술발표회논문집(1)
• /
• pp.230-235
• /
• 1996

The new concept of dry area formation based on Poisson distribution of active nucleation sites and the concept of the critical active site density is presented. A simple statistical model is developed to predict the change of slope of the boiling curve up to critical heat flux (CHF) quantitatively. The predictions by the present model are in good agreement with the experimental data. Also it turns out that the present model well explains the mechanism on how the surface wettability influences CHF.

• 한국연소학회:학술대회논문집
• /
• 한국연소학회 2012년도 제44회 KOSCO SYMPOSIUM 초록집
• /
• pp.107-109
• /
• 2012

A quasidimensional model is developed with the surrogate mechanism of isooctane and n-heptane to predict knock and emissions of a homogeneous GDI engine. It is composed of unburned and burned zone with the latter divided into multiple zones of equal mass to resolve temperature stratification. Validation is performed against measured pressure traces, NOx and CO emissions at different load and rpm conditions. Comparison is made between the empirical knock model and predictions by the chemistry model in this work.

• 대한설비공학회:학술대회논문집
• /
• 대한설비공학회 2006년도 하계학술발표대회 논문집
• /
• pp.1199-1204
• /
• 2006

The pressure drop and heat transfer coefficient were measured at room temperature in CFB heat exchanger with multiple vertical tubes. Also the circulation rate of solid particles was measured. The theoretical model for predicting heat transfer coefficient using the solid flowrate was developed in this study. The model predictions were compared with the measured heat transfer coefficient to show relatively good agreement.

• 해양환경안전학회지
• /
• 제25권3호
• /
• pp.344-353
• /
• 2019

The wakes behind a square cylinder were simulated using two-equation turbulence models, $k-{\varepsilon}$ and RNG $k-{\varepsilon}$ models. For comparisons between the model predictions and analytical solutions, we employed three skill assessments:, the correlation coefficient for the similarity of the wake shape, the error of maximum velocity difference (EMVD) of the accuracy of wake velocity, and the ratio of drag coefficient (RDC) for the flow patterns as in the authors' previous study. On the basis of the calculated results, we discussed the feasibility of each model for wake simulation and suggested a suitable value for an eddy viscosity related constant in each turbulence model. The $k-{\varepsilon}$ model underestimated the drag coefficient by over 40 %, and its performance was worse than that in the previous study with one-equation and mixing length models, resulting from the empirical constants in the ${\varepsilon}-equation$. In the RNG $k-{\varepsilon}$ model experiments, when an eddy viscosity related constant was six times higher than the suggested value, the model results were yielded good predictions compared with the analytical solutions. Then, the values of EMVD and RDC were 3.8 % and 3.2 %, respectively. The results of the turbulence model simulations indicated that the RNG $k-{\varepsilon}$ model results successfully represented wakes behind the square cylinder, and the mean error for all skill assessments was less than 4 %.

• 한국지반공학회논문집
• /
• 제15권3호
• /
• pp.113-129
• /
• 1999

본 연구에서는 사질토 지반에서의 굴착단계별 연성 벽체의 거동분석을 수행하기 위해 흙막이벽의 모형실험을 실시하였다. 모형 흙막이벽 실험에서는 재료의 역학적 특성이 비교적 널리 알려진 주문진 표준사를 이용하여 상대밀도가 79%, 41%, 24%인 모형지반을 조성한 후 모형벽체의 연성지수를 변화시켜 각 굴착단계별로 배면지반과 연성 벽체의 거동특성을 규명하였다. 본 연구에서는 벽체의 수평변위, 벽체의 배면에 작용하는 수평토압, 굴착으로 인한 배면지반의 침하량 및 침하영향거리, 벽체에 작용하는 앵커의 하중, 그리고 벽체에 작용하는 휨모멘트와 축력에 대해 굴착단계에 따라 살펴보고 이를 토대로 지반과 벽체의 거동특성을 분석하였다.

• The Korean Journal of Ecology
• /
• 제24권6호
• /
• pp.335-339
• /
• 2001

The dynamic model was developed to simulate the photosynthetic rate of Phragmites communis stands in coastal ecosystem. The model was composed of the compartments of both climatic and biological variables. The former were photosynthetic photon flux density(PPFD), daily maximum- and minimum-temperature. The latter were combinations of the specific physiological responses of plant organs with the biomass of each organs. The PPFD and air temperature were calculated and using those values, gas exchange rate of each plant organ was calculated at every hour. The carbon budget was constructed using the modelled predictions. Analysis of annual productivity and fluxes showed that yearly gross population productivity, yearly population respiration and yearly net population productivity were 33.4, 21.3 and 12.1 $CO_2ton{\cdot}ha^{-2}{\cdot}yr^{-1}$, respectively. The final result was tested over two stands, produced promising predictions with regards to the levels of production attained. The model can be used to determine production potential under given climatic conditions and could even be applied to plant canopies with analogous biological characteristics.

• Steel and Composite Structures
• /
• 제14권2호
• /
• pp.173-190
• /
• 2013

The major objective of this paper is to evaluate the behavior and ultimate resisting capacity of circular CFT columns. To consider the confinement effect, proper material models with respect to the confinement pressure are selected. A fiber section approach is adopted to simulate the nonlinear stress distribution along the section depth. Material nonlinearity due to the cracking of concrete and the yielding of the surrounding steel tube, as well as geometric nonlinearity due to the P-${\Delta}$ effect, are taken into account. The validity of the proposed numerical analysis model is established by comparing the analytical predictions with the results from previous experimental studies about pure bending and eccentric axial loading. Numerical predictions using an unconfined material model were also compared to investigate the confinement effects on various loading combinations. The ultimate resisting capacities predicted by the proposed numerical model and the design guidelines in Eurocode 4 are compared to evaluate the existing design recommendation.