• 한국컴퓨터정보학회논문지
• /
• 제24권11호
• /
• pp.51-59
• /
• 2019

웹에서 정보 접근에 대한 폭발적인 주문으로 웹 사용자의 다음 접근 페이지를 예측하는 필요성이 대두되었다. 웹 접근 예측을 위해 마코브(markov) 모델, 딥 신경망, 벡터 머신, 퍼지 추론 모델 등 많은 모델이 제안되었다. 신경망 모델에 기반한 딥러닝 기법에서 대규모 웹 사용 데이터에 대한 학습 시간이 엄청 길어진다. 이 문제를 해결하기 위하여 딥 신경망 모델에서는 학습을 여러 컴퓨터에 동시에, 즉 병렬로 학습시킨다. 본 논문에서는 먼저 스파크 클러스터에서 다층 Perceptron 모델을 학습 시킬 때 중요한 데이터 분할, shuffling, 압축, locality와 관련된 기본 파라미터들이 얼마만큼 영향을 미치는지 살펴보았다. 그 다음 웹 접근 예측을 위해 다층 Perceptron 모델을 학습 시킬 때 성능을 높이기 위하여 이들 스파크 파라미터들을 튜닝 하였다. 실험을 통하여 논문에서 제안한 스파크 파라미터 튜닝을 통한 웹 접근 예측 모델이 파라미터 튜닝을 하지 않았을 경우와 비교하여 웹 접근 예측에 대한 정확성과 성능 향상의 효과를 보였다.

• 한국정밀공학회지
• /
• 제16권7호
• /
• pp.168-177
• /
• 1999

Fatigue damage is the phenomena which is accumulated gradually with loading cycle in material. It is represented by fatigue crack growth rate da/dN and fatigue life ratio $N/N_{f}$. Fracture mechanical parameters estimating large crack growth behavior can calculate quantitative amount of fatigue crack growth resistance in engineering material. But fatigue damage has influence on various load, material and environment. Therefore, In this study, we propose that artificial intelligent fatigue damage model can predicts fatigue crack growth rate da/dN and fatigue life ratio $N/N_{f}$ simultaneously using fracture mechanical and nondestructive parameters.

• 생물환경조절학회지
• /
• 제2권2호
• /
• pp.99-109
• /
• 1993

Cooling of nutrient solution is essential to improve the growth environment of crops in hydroponic culture during summer season in Korea. This study was carried out to provide fundamental data for development of the cooling system satisfying the required cooling load of nutrient solution in hydroponic greenhouse. A numerical model for prediction of the cooling load of nutrient solution in hydroponic greenhouse was developed, and the results by the model showed good agreements with those by experiments. Main factors effecting on cooling load were solar radiation and air temperature in weather data, and conductivity of planting board and area ratio of bed to floor in greenhouse parameters. Using the model developed, the design cooling load of nutrient solution in hydroponic greenhouse of 1,000$m^2$(300pyong) was predicted to be 95,000 kJ/hr in Suwon and the vicinity.

• 한국분무공학회지
• /
• 제20권4호
• /
• pp.241-246
• /
• 2015

The objective of the current study is to develop an 1D thermoacoustic model for predicting basic characteristics of combustion instability and to investigate effects of key parameters on the instabilities such as effects of flame geometry and acoustic boundary conditions. Another focus of the paper is placed on limit cycle prediction. In order to improve the model accuracy, the 1D model was modified considering the actual flame location and flame length (i.e. distribution of time delay). As a result, it is found that the reflection coefficients have a great effect on the growth rate of the instabilities. In addition, instability characteristics are shown to be strongly dependent upon the fuel compositions.

• Nuclear Engineering and Technology
• /
• 제52권12호
• /
• pp.2949-2957
• /
• 2020

Fatigue crack growth model has been developed for dissimilar metal weld joints of a piping component under cyclic loading, where in the crack is located at the center of the weld in the circumferential direction. The fracture parameter, Stress Intensity Factor (SIF) has been computed by using principle of superposition as K_H + K_M. K_H is evaluated by assuming that, the complete specimen is made of the material containing the notch location. In second stage, the stress field ahead of the crack tip, accounting for the strength mismatch, the applied load and geometry has been characterized to evaluate SIF (K_M). For each incremental crack depth, stress field ahead of the crack tip has been quantified by using J-integral (elastic), mismatch ratio, plastic interaction factor and stress parallel to the crack surface. The associated constants for evaluation of K_M have been computed by using the quantified stress field with respect to the distance from the crack tip. Net SIF (K_H + K_M) computed, has been used for the crack growth analysis and remaining life prediction by Paris crack growth model. To validate the model, SIF and remaining life has been predicted for a pipe made up of (i) SA312 Type 304LN austenitic stainless steel and SA508 Gr. 3 Cl. 1. Low alloy carbon steel (ii) welded SA312 Type 304LN austenitic stainless-steel pipe. From the studies, it is observed that the model could predict the remaining life of DMWJ piping components with a maximum difference of 15% compared to experimental observations.

• 한국신뢰성학회:학술대회논문집
• /
• 한국신뢰성학회 2004년도 정기학술대회
• /
• pp.161-166
• /
• 2004

A method of estimating B$_{\alpha}$ life of crack growth is proposed based on the linear elastic fracture mechanic model. It is assumed that the coefficients in the Paris-Erdogan equation are random variables and their distributions are estimated by the method of 2-stage estimation from the fatigue crack growth data. A case study is also given. is also given.

• 한국전산구조공학회논문집
• /
• 제25권3호
• /
• pp.267-275
• /
• 2012

본 연구에서는 모드 I의 변동진폭하중 하에서 평판의 두께관통 균열성장을 예측하고 예측결과를 실험을 통해 검증하였다. 균열성장 모델을 위해 과하중으로 인한 균열가속과 지연효과를 고려하는 Huang의 모델식을 이용하였다. 실험적 검증을 위해 Al6016-T6 평판 균열을 제작하여 변동하중을 부여하고 균열길이를 일정 주기로 육안 측정하였다. 측정데이터로부터 모델 변수를 추정하기 위해 베이지안 접근법에 기반한 파티클 필터 방법을 이용하였고, 이를 통해 위험크기까지의 미래 거동 및 잔존수명을 확률적으로 예측하였으며, 이를 실제 실험한 결과와 비교하였다. 그 결과 변동하중에 의한 균열지연이 잘 예측됨을 확인하였고, 측정 데이터가 증가할수록 예측된 중앙값(median)이 실제와 점점 더 일치하였다.

• Spatial Information Research
• /
• 제18권3호
• /
• pp.33-40
• /
• 2010

급격한 도시화로 인한 난개발, 도시의 과대팽창 등을 막기 위해 다양한 방법의 성장관리 기법들이 제시되어왔다. 우리나라의 많은 도시들도 예외가 아니며, 특히 개발의 압력을 받는 많은 수도권내의 도시들이 그러하다. 본 연구는 GIS와 계량적 방법을 통해 도시의 미래 성장을 예측하고 성장관리를 위한 모델을 구축하는 것이 연구의 목적이다. 특히, 계획적 제도와 수요를 고려한 예측시나리오를 제시함으로써 보다 합리적인 관리방안을 제시한다. 이를 위해 GIS 기법과 계량분석을 이용하여 과학적이고 객관적인 근거를 마련하도록 하였으며 시뮬레이션을 통해 향후 계획의 의사결정 및 집행을 위한 기반을 마련하였다.

• 한국작물학회:학술대회논문집
• /
• 한국작물학회 2022년도 추계학술대회
• /
• pp.58-58
• /
• 2022

With the development of advanced technology, automation of agricultural work is spreading. In association with the 4th industrial revolution-based technology, research on field smart farm technology is being actively conducted. A state-of-the-art unmanned automated agricultural production demonstration complex was established in Naju-si, Jeollanam-do. For the operation of the demonstration area platform, it is necessary to build a sophisticated, advanced, and intelligent field smart farming model. For the operation of the unmanned automated agricultural production demonstration area platform, we are building data on the growth of soybean for smart cultivated crops and conducting research to determine the optimal time for agricultural work. In order to operate an unmanned automation platform, data is collected to discover digital factors for water management immediately after planting, water management during the growing season, and determination of harvest time. A subsurface drip irrigation system was established for smart water management. Irrigation was carried out when the soil moisture was less than 20%. For effective water management, soil moisture was measured at the surface, 15cm, and 30cm depth. Vegetation indices were collected using drones to find key factors in soybean production prediction. In addition, major growth characteristics such as stem length, number of branches, number of nodes on the main stem, leaf area index, and dry weight were investigated. By discovering digital factors for effective decision-making through data construction, it is expected to greatly enhance the efficiency of the operation of the unmanned automated agricultural production demonstration area.

• Food Science and Biotechnology
• /
• 제15권5호
• /
• pp.715-720
• /
• 2006

This study was performed to develop a predictive model for the growth kinetics of Listeria monocytogenes in tryptic soy broth (TSB) using a response surface model with a combination of potassium lactate (PL), temperature, and pH. The growth parameters, specific growth rate (SGR), and lag time (LT) were obtained by fitting the data into the Gompertz equation and showed high fitness with a correlation coefficient of $R^2{\geq}0.9192$. The polynomial model was identified as an appropriate secondary model for SGR and LT based on the coefficient of determination for the developed model ($R^2\;=\;0.97$ for SGR and $R^2\;=\;0.86$ for LT). The induced values that were calculated using the developed secondary model indicated that the growth kinetics of L. monocytogenes were dependent on storage temperature, pH, and PL. Finally, the predicted model was validated using statistical indicators, such as coefficient of determination, mean square error, bias factor, and accuracy factor. Validation of the model demonstrates that the overall prediction agreed well with the observed data. However, the model developed for SGR showed better predictive ability than the model developed for LT, which can be seen from its statistical validation indices, with the exception of the bias factor ($B_f$ was 0.6 for SGR and 0.97 for LT).