• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.701-704
• /
• 2023

본 연구는 반도체 제조 과정에서 생산 가용 능력이 저하되는 시점을 조기 탐지하기 위한 프레임워크를 제안한다. 이를 위해 데이터 패턴의 불규칙한 변동이 잦은 환경에서 모델의 재학습 없이 최적의 성능을 유지할 수 있도록 온라인 학습 방식을 활용하였다. Augmented Dicky-Fuller test 를 통해 데이터의 정상성 여부를 검정하고, 데이터에 변화가 있을 경우 학습 모델은 지속적으로 업데이트된다. 특히, 상한 재공재고는 생산량과 직결되는 주요 지표로써, 낮게 예측된 시점에서 주요 원인 변수를 파악하는 것이 중요하다. 따라서 정확도와 효율성 측면에서 다른 모델 대비 가장 우수한 성능을 보였던 제안 기법에 shapley additive explanations(SHAP)을 적용하여 생산 저하 시 문제가 되는 원인 변수를 분석하고자 하였다.

• Proceedings of the KIEE Conference
• /
• 2001.07b
• /
• pp.1217-1219
• /
• 2001

본 논문은 경량전철차량시스템의 하부장치별로 정의된 목표신뢰도를 바탕으로 제동장치의 구성품에 대한 신뢰도를 예측했다. 신뢰도를 예측하기 위하여 제동장치의 주요 구성품에 대한 모델방법 정의, 국내 외 차량시스템에 사용된 제동장치의 요구신뢰도를 조사 분석 하였다. 신뢰도예측결과는 제동장치의 작동환경에 따라 커다란 차이를 갖고 있다. 본 논문의 신뢰도 예측에 필요한 자료는 신뢰도분석 Tool의 데이터 및 현 차량시스템에 적용된 제품의 데이터를 활용하였다. 향후 차량시스템의 상세설계와 함께 보다 정확한 제동장치의 신뢰성예측이 이루어질 것이다.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2014.10a
• /
• pp.939-942
• /
• 2014

고속도로 교통 소음 저감을 위해 상용소음예측프로그램인 SoundPLAN과 소음예측 시 주로 사용하는 도로 교통 소음예측식인 RLS-90을 이용하여 경제적이고 효율적인 방음대책 설계방안에 대한 연구를 하였다. 대상지역에서 측정한 실제 소음도와 예측 소음도의 차이를 비교하여 모델을 검증하고 장래교통량에 대하여 소음을 예측하여 방음대책을 설계하였다. 방음벽의 높이와 길이, 저소음 포장의 길이를 조절하고 저소음 포장과 방음벽을 혼용했을 경우에 대하여 소음규제 기준에 적합하게 설계하였고 각각의 설치 단가를 이용하여 경제성을 비교하여 보다 효율적인 방음대책을 알아보았다.

• Proceedings of the Korea Society for Simulation Conference
• /
• 1998.10a
• /
• pp.170-173
• /
• 1998

본 연구에서는 시뮬레이터나 그와 유사한 가상현실환경(Virtual Reality Environment ; VRE)에서 일어날 수 있는 Simulator Sickness가 어떤 사람들에게 쉽게 발생하는지를 예측하기 위하여 다중선형회귀(Multiple linear regression) 방정식으로 예측회귀모형을 제시하였다. 이 회귀모형에서의 종속변수는 김도희 외(1998)에 의해 개발된 RSSQ의 종합점수이고, 독립변수는 실제운전경력에 1을 더한 값에 나이를 곱한 값, 과거 멀미를 경험한 정도, 1주일 평균 동화상 시간, 현재의 건강상태로 되어져 있다. 이 회귀모형의 R2값은 약 0.52로 Kolasinski(1996)의 모델보다 설명력이 18% 증가하였고, 부수적인 별도의 실험을 하지 않고도 간단한 개인 신상에 관한 간단한 자료만으로도 훨씬 좋은 결과를 예측할 수 있게 되었다. 따라서 시뮬레이터나 가상현실에서 일어나는 Simulator Sickness가 어떠한 사람에게 걸리기가 쉬운지를 쉽게 예측할 수 있게 되었고, 이러한 사람들에게는 시뮬레이터나 가상현실의 이용을 자제시키거나 주의를 주어 특별관리 함으로써 시뮬레이터나 가상현실을 운영하는데 많은 도움을 줄 수 있을 것이다.

• The Journal of Engineering Geology
• /
• v.30 no.3
• /
• pp.315-325
• /
• 2020

This study was performed to develop a model to predict landslides and determine the variable importance of landslides susceptibility factors based on the probabilistic prediction of landslides occurring on slopes along the road. Field survey data of 30,615 slopes from 2007 to 2020 in Korea were analyzed to develop a landslide prediction model. Of the total 131 variable factors, 17 topographic factors and 114 geological factors (including 89 bedrocks) were used to predict landslides. Automated machine learning (AutoML) was used to classify landslides and non-landslides. The verification results revealed that the best model, an extremely randomized tree (XRT) with excellent predictive performance, yielded 83.977% of prediction rates on test data. As a result of the analysis to determine the variable importance of the landslide susceptibility factors, it was composed of 10 topographic factors and 9 geological factors, which was presented as a percentage for each factor. This model was evaluated probabilistically and quantitatively for the likelihood of landslide occurrence by deriving the ranking of variable importance using only on-site survey data. It is considered that this model can provide a reliable basis for slope safety assessment through field surveys to decision-makers in the future.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.2
• /
• pp.426-434
• /
• 2010

This study is experimentally performed to evaluate the strength reduction behavior and its statistical properties of plain woven glass/epoxy composites. The results indicate that the major impact damage of plain woven glass/epoxy composites is the fiber breakage and matrix crack, whereas the dominant impact damage of unidirectional carbon/epoxy laminates is the delamination, which depends on the stacking sequence. The residual strength prediction models, previously proposed on unidirectional laminates, are applied to evaluate the residual strength of plain woven glass/epoxy composites with impact damage. Among these models, the results by Caprino and Avva's model have a good agreement with the experimental results. To investigate the variability of residual strength of the impacted composite materials, a statistical model was proposed and its results were in conformance with the experimental results regardless of their thickness.

• Korean Chemical Engineering Research
• /
• v.60 no.1
• /
• pp.25-33
• /
• 2022

This study developed the black liquor evaporation process models using the multiple-effect-evaporator according to the number of effects to predict steam consumption. The developed models were divided into the black liquor preheating and evaporation processes, and a virtual reboiler was added to predict steam consumption. In simulation results, the steam consumption in the double-effect-evaporator was decreased by 48.9 %, and as the number of effects increased, the steam consumption was decreased. Finally, the steam consumption in the octuple-effect-evaporator was decreased by 61.2 %. Also, this study suggests a strategy for deriving the optimal number of effects in the process by analyzing the latent heat recovered from the saturated vapor produced in the multiple-effect-evaporator and the amount of saturated vapor produced by each effect.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.4
• /
• pp.29-34
• /
• 1997

The prediction of detection range of a passive sonar system is essential to estimate the performance and to optimize the operation of a developed sonar system. In this paper, a model for the prediction of detection range in a range-dependent ocean environment based on the sonar equation is developed and tested. The prediction model calculates the transmission loss using PE propagation model, signal excess, and the detection probability at each target depth and range. The detection probability is integrated to give the estimated detection range. In order to validate the developed model, two cases are considered. One is the case when target depth is known. The other is the case when the target depth is unknown. The computational results agree well with the previously published results for the range-independent environment. Also,the developed model is applied to the range-dependent ocean environment where the warm eddy exists. The computational results are shown and discussed. The developed model can be used to find the optimal frequency of detection, as well as the optimal search depth for the given range-dependent ocean environment.

• Journal of Cadastre & Land InformatiX
• /
• v.52 no.2
• /
• pp.211-231
• /
• 2022

This study attempted to identify the effects of macroeconomic variables such as the All Industry Production Index, Consumer Price Index, CD Interest Rate, and KOSPI on apartment lease prices divided into nationwide, Seoul, metropolitan, and region, and to present a methodological prediction model of apartment lease prices by region using Long Short Term Memory (LSTM). According to VAR analysis results, the nationwide apartment lease price index and consumer price index in Lag1 and 2 had a significant effect on the nationwide apartment lease price, and likewise, the Seoul apartment lease price index, the consumer price index, and the CD interest rate in Lag1 and 2 affect the apartment lease price in Seoul. In addition, it was confirmed that the wide-area apartment jeonse price index and the consumer price index had a significant effect on Lag1, and the local apartment jeonse price index and the consumer price index had a significant effect on Lag1. As a result of the establishment of the LSTM prediction model, the predictive power was the highest with RMSE 0.008, MAE 0.006, and R-Suared values of 0.999 for the local apartment lease price prediction model. In the future, it is expected that more meaningful results can be obtained by applying an advanced model based on deep learning, including major policy variables

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.48 no.7
• /
• pp.505-511
• /
• 2020

The circular composite tubes have been used as a main spar of HALE-UAV(High Altitude Long Endurance-Unmanned Air Vehicle). In this paper, an analytical model is presented for the prediction of the failure load of unsymmetrically stiffened circular spar using a modified Brazier approach. This model was used to predict the moment carrying capacity of the unsymmetrically stiffened circular spar. From the results, we can know that a stiffened cap placed in the top sector of a spar increased the bending capabilities. Four point bending tests were conducted to estimate the effect of the cap on the failure load and compared with the proposed model. And numerical simulations were performed to analyze the behavior of stiffened circular spar. Comparisons of the results from the proposed model with those from experiments and numerical modes show good correlation.