• Proceedings of the Korea Society for Simulation Conference
• /
• 2000.11a
• /
• pp.6-10
• /
• 2000

In regression model we estimate the unknown parameters using various methods. There are the least squares method which is the most general, the least absolute deviation, the regression quantile and the asymmetric least squares method. In this paper, we will compare each others with two case: to begin with the theoretical comparison in the asymptotic sense, and then the practical comparison using Monte Carlo simulation for a small sample size.

• Macromolecular Research
• /
• v.11 no.5
• /
• pp.393-397
• /
• 2003

By applying a configurational-bias Gibbs ensemble Monte Carlo algorithm, priority simulation results regarding the conformation of non-dilute polyelectrolytes in solvents are obtained. Solutions of freely-jointed chains are considered, and a new method termed strandwise configurational-bias sampling is developed so as to effectively overcome a difficulty on the transfer of polymer chains. The structure factors of polyelectrolytes in the bulk as well as in the confined space are estimated with variations of the polymer charge density.

• Proceeding of EDISON Challenge
• /
• 2016.03a
• /
• pp.80-85
• /
• 2016

본 연구에서는 Grand-Canonical Monte Carlo 시뮬레이션(GCMC)을 이용하여 서로 반대의 전하를 띤 고분자 전해질의 정전기적 특징을 이해하고, 고분자 전해질 다이오드의 메커니즘을 연구하였다. 고분자 전해질과 서로 반대의 전하를 띤 이온들의 모델은 전하를 띤 free-jointed hard chain과 hard sphere을 이용하였다. 본 연구진은 위와 같은 시뮬레이션을 통해, 평형 상태일 때의 고분자 전해질과 이온의 분포를 연구하였으며, 이 시스템에 전압을 걸어줌에 따라 이온의 이동 모습을 관찰하였다. 또한 전압의 효과와 더불어 고분자 전해질의 농도와 이온들의 크기 변화에 대해서도 연구를 진행하였다.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2012.08a
• /
• pp.98-98
• /
• 2012

최고진공도 10-10 mbar, 배기속도 2500 L/s를 구현할 대용량 복합 분자펌프(TMP) 설계를 위한 3차원 유동해석을 실시하였다. 진공도가 10-5 mbar 이상이 되는 고진공도에서는 Knudsen 수가 102~107에 이르러 분자간 충돌을 거의 무시할 수 있게 되며, 이때의 유체해석 방법으로서는 통상 희박기체 해석법으로 많이 쓰이는 Direct Simulation Monte Carlo (DSMC) 방법이나 Continuum fluid에 대한 Navier-Stokes 해석보다, 충돌이 없는 분자의 자유운동을 모사하는 Monte Carlo 방법이 더 적합할 수 있다. 본 연구에서는 다단계 rotor와 stator로 구성되는 복합분자 내 유동장에 Monte Carlo 해석법을 적용하여 유동해석을 실시하였다. 해석 방법의 타당성을 확인하기 위해 동일한 형상에 대해 Navier-Stokes 해석과 DSMC 해석을 병행하였다. 각각의 수치적 해석에서 공통적으로, TMP의 성능에 지배적인 영향을 미치는 설계변수는 rotor-stator의 날개각임이 확인되었고, 이 설계변수들의 최적값을 다양한 3차원 유동해석을 통해 도출하였다. 해석결과는 펌프설계에 적용되어 펌프 성능시험결과를 통해 확증된다.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.5 no.3
• /
• pp.244-250
• /
• 1981

The rediant heat tranfer and temperature distribution between infinite parallel gray plates at different temperatures separated by an absorbing and emitting gray gas with or without a sinusoidal heat source in the gas are analyzed by Monte Carlo method. The Monte Carlo result were compared with the numerical solution by Usiskin and Sparrow and the exact solution by Hottel in the case of similar problem limited black walls and gas optical thickness is less than two. For gray walls and large optical thichness the results were compared with modified diffusion approximate solution by Deissler.

• Proceedings of the Korean Statistical Society Conference
• /
• 2000.11a
• /
• pp.135-140
• /
• 2000

베이지안 신경망 모형(Bayesian Neural Networks Models)에서 주어진 입력값(input)은 블랙 박스(Black-Box)와 같은 신경망 구조의 각 층(layer)을 거쳐서 출력값(output)으로 계산된다. 새로운 입력 데이터에 대한 예측값은 사후분포(posterior distribution)의 기대값(mean)에 의해 계산된다. 주어진 사전분포(prior distribution)와 학습데이터에 의한 가능도함수(likelihood functions)를 통해 계산되어진 사후분포는 매우 복잡한 구조를 갖게 됨으로서 기대값의 적분계산에 대한 어려움이 발생한다. 이때 확률적 추정에 의한 근사 방법인 몬테칼로 적분을 이용한다. 이러한 방법으로서 Hybrid Monte Carlo 알고리즘은 우수한 결과를 제공하여준다(Neal 1996). 본 논문에서는 Hybrid Monte Carlo 알고리즘과 기존에 많이 사용되고 있는 Gibbs sampling, Metropolis algorithm, 그리고 Slice Sampling등의 몬테칼로 방법들을 비교한다.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.15 no.5
• /
• pp.21-28
• /
• 2006

Vibration of a non-linear system with multiple degrees of freedom under random parametric excitations was evaluated by probabilistic method. The non-linear characteristic terms of system structure were quasi-linearized and excitation terms were remained as they were. An analytical method where the expectation values of square mean of error was minimized was used. The numerical results were compared with those obtained by Monte Carlo simulation. A linear congruential generator and Box-Muller method were used in Monte Carlo simulation. The comparison showed the results by probabilistic method agreed well with those by Monte Carlo simulation.

• Journal of the Korean Society of Safety
• /
• v.32 no.3
• /
• pp.54-59
• /
• 2017

This paper presents an efficient finite analysis model and a simulation-based reliability analysis method for stowage device system failure of a container crane with respect to lateral load. A quasi-static analysis model is introduced to simulate the nonlinear resistance characteristics and failure of tie-down and stowage pin, which are the main structural stowage devices of a crane. As a reliability analysis method, a subset simulation method is applied considering the uncertainties of later load and mechanical characteristic parameters of stowage devices. An efficient Markov chain Monte Carlo (MCMC) method is applied to sample random variables. Analysis result shows that the proposed model is able to estimate the probability of failure of crane system effectively which cannot be calculated practically by crude Monte Carlo simulation method.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 1995.11a
• /
• pp.152-157
• /
• 1995

The electron transport coefficients in $SP_{6}$ gas is calculated and analysed for range of E/N values from 150∼800(Td) by a Monte Carlo simulation, using a set of electron collision cross sections determined by the authors. The result of the Monte Carlo simulation such as electron drift velocity, ionization and electron attachment coefficients, longitudinal and transverse diffusion coefficients in neatly agreement with the respective experimental and theoretical for a range of E/N. The validity of the results obtained has been confirmed by a Monte Carlo simulation carried out parallel to the analysis.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.51 no.9
• /
• pp.425-432
• /
• 2002

This Paper illustrates a method for evaluating nodal probabilistic production cost using the CMELDC. A new method for constructing CMELDC(CoMposite Power System Equivalent Load Duration Curve) has been developed by authors. The CMELDC can be obtained by convolution integral processing between the probability distribution functions of the fictitious generators outage capacity and the load duration curves at each load point. In general, if complex operating conditions are involved and/or the number of severe events is relatively large, Monte Carlo methods are more efficient. Because of that reason, Monte Carlo Methods are applied for the construction of CMELDC in this study. And IEEE-RTS 24 buses model is used as our case study with satisfactory results.