• Journal of the Korean Geotechnical Society
• /
• v.24 no.8
• /
• pp.111-123
• /
• 2008

Geotechnical engineering problems are characterized by many sources of uncertainty. Some of these sources are connected to the uncertainties of soil properties involved in the analysis. In this paper, a numerical procedure for a probabilistic analysis that considers the spatial variability of soil properties is presented to study the response of spatially random soil. The approach integrates a commercial finite difference method and random field theory into the framework of a probabilistic analysis. Two-dimensional non-Gaussian random fields are generated based on a Karhunen-$Lo{\grave{e}}ve$ expansion in a fashion consistent with a specified marginal distribution function and an autocorrelation function. A Monte Carlo simulation is then used to determine the statistical response based on the random fields. A series of analyses were performed to study the effects of uncertainty due to the spatial heterogeneity on the settlement and bearing capacity of a rough strip footing. The simulations provide insight into the application of uncertainty treatment to the geotechnical problem and show the importance of the spatial variability of soil properties with regard to the outcome of a probabilistic assessment.

• Korean Journal of Construction Engineering and Management
• /
• v.15 no.6
• /
• pp.44-52
• /
• 2014

Generally, the most difficult works at scheduling are to estimate the duration of activities and linkages between them because the possibility that the duration and linkages could be exposed to the uncertainties is so high. When estimating a project duration, therefore, the probabilistic estimation of the duration as well as the probabilistic estimation of the linkages between activities should be considered concurrently. The PERT that is one of the most popular techniques applied for the probabilistic estimation of a project duration can not consider the uncertainties of the linkages because it only estimates the probabilistic duration limited to 'FS0' relationship. The purpose of this study is to propose the new method "PLET" for stochastically estimating the project duration based on the probabilistic estimation of the BDM's relationships, and also provide more wide and various probabilsitic information about the project duration by it.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 1994.10a
• /
• pp.29-34
• /
• 1994

본 연구에서는 계의 변수들이 불확실성을 갖고 비정상확률입력을 받는 비선형 동적계를 포함한 일반적인 확률적 선형/비선형 동적계의 해석을 수행하기 위하여 동적계의 확률적 모델과 새로운 확률과정근사법을 이용한 확률해석을 제시하고, 그 타당성을 Monte Carlo 시뮬레이션으로 검증하고자 한다.

• Proceedings of the Korean Statistical Society Conference
• /
• 2002.11a
• /
• pp.61-68
• /
• 2002

통계학은 불확실성(uncertainty)에 대한 연구이다. 베이지안 통계 방법은 불확실성 아래서 통계 추론과 의사 결정 모두를 위한 완전한(complete) 패러다임을 제공한다. 베이지안 방법론은 합리적인 초기 정보와 결합하는 것을 가능하게 만들고, 전통적인 통계적 방법론에 의하여 직면하는 많은 어려움들을 풀 수 있는 coherent 방법론을 제공하면서 엄격한 수학적 기본에 근거하고 있다. 베이지안 패러다임은 일반적인 용어로써 확률이란 단어의 사용을 가장 잘 어울리게 하는 불확실성의 조건부 측도(conditional measure of uncertainty)로써 확률의 해석에 근거한다. 관심있는 것에 대한 통계적 추론은 증거의 관점에서 그 값에 대한 불확실성의 변형으로써 묘사되며, 베이즈 정리(Bayes' theorem)는 이러한 변형이 어떻게 만들어지는 가를 자세히 설명할 수 있다. 베이지안 방법들은 전통적인 통계적 방법론에 접근할 없는 복잡하고, 다양한 구조적 문제들에 응용할 수 있다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2004.05b
• /
• pp.277-281
• /
• 2004

수자원장기종합계획에서는 물의 과부족 또는 가용한 물을 정량적으로 평가하기 위해 물수지 분석을 실시한다. 물수지 분석은 미래 예측되는 용수수요량과 공급가능량을 비교하는 단순한 과정이지만, 분석 과정에 포함되어 있는 자료와 모형의 불확실성으로 인하여 물수지 분석을 실시한 각종 보고서마다 서로 다른 결과를 보여주고 있어 국민의 신뢰를 얻지 못한 실정이다. 본 연구에서는 Monte Carlo simulation 기법 중 Latin Hypercube Sampling에 기반한 확률적 모사로 물수지의 불확실성을 표현하고, 이를 기존에서 제시한 단일 물부족량과 비교하여 불확실성의 범위와 특성을 분석하였다. 또한 민감도 분석을 수행함으로써 입력변수들 간의 상대적 중요도를 산정하여 수자원계획 수립시 투자 우선순위를 제시하였다.

• Journal of Information Management
• /
• v.21 no.1
• /
• pp.34-52
• /
• 1990

The probabilistic reasoning method using Bayesian theory is studied to use uncertain or incomplete knowledge in ways that take the uncertainty into account. This method presented for knowledge acquisition process of expert system to evaluate certainty degree of input knowledge.

• Journal of the military operations research society of Korea
• /
• v.34 no.3
• /
• pp.107-116
• /
• 2008

This paper deals with modelling and introducing of the project portfolio construction and evaluation problem under uncertainty. The common way in industry of managing project portfolio is construction of initial portfolio considering uncertainties which exist inside and outside of portfolio, and periodic revision of portfolio due to the deviation from plans. In this paper, we introduce algorithm which reflecting the industrial common practice of initial planning and periodic revision. With this simulation method, probabilistic distribution of portfolio's performance in consideration can be found.

• Korean Journal of Construction Engineering and Management
• /
• v.8 no.3
• /
• pp.76-86
• /
• 2007

Construction development work invents profit as those finalize object, and a make or break success of project depends on correct analysis and forecast business feasibility at project early. Business feasibility study would be decision-making under precarious situation because is connoting uncertainty that is future. estimate at present visual point essentially. Under uncertainty, a decision-making method is based on probability theory of statistics, but business feasibility study had applied with not feasibility study by probabilistic decision method but it by determinism derision method so far. Therefore in this study doing decision-making by a probability theory method for successful project at early business feasibility study, it present a probabilistic study method that use simulation that can supply a little more correct and reliable data to decision-maker As result, a probabilistic study method is more suitable than deterministic study method as technique for a financial feasibility study of construction development work. Making good use of this probabilistic study method at important business or careful decision-making, because efficient Judgment that is based accuracy and authoritativeness may become available.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.6A
• /
• pp.1001-1011
• /
• 2006

It is a general agreement that exact statistical solutions can be found by a Monte Carlo technique. Due to difficulties, however, in the numerical generation of random fields, which satisfy not only the probabilistic distribution but the spectral characteristics as well, it is recognized as relatively difficult to find an exact response variability of a structural response. In this study, recognizing that the random field assumes a constant over the domain under consideration when the correlation distance tends to infinity, a semi-theoretical solution of response variability is proposed for general structures. In this procedure, the probability density function is directly used. It is particularly noteworthy that the proposed methodology provides response variability for virtually any type of probability density function, and has capability of considering correlations between multiple random variables.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.404-404
• /
• 2022

효율적인 수자원 관리를 위해 빈도해석을 통한 수문 자료의 통계적 특성을 고려하여 정확한 확률강수량을 산정해야 한다. 지점빈도해석은 지점 자료만을 이용하여 확률강수량을 산정하기 때문에 정확도를 높이기 위해서는 자료 확충이 필요하지만, 지점별로 활용할 수 있는 자료가 제한적이며 지점마다 변동성이 크다. 지역빈도해석은 수문기상학적으로 동질한 주변 지점들의 자료를 모두 포함해서 빈도해석을 수행함으로써 지역에 대한 통합 결과를 제시하고 자료에 대한 신뢰성 확보가 가능하다. 일반적으로 빈도해석은 자료에 적합한 확률분포 기반으로 수행되지만 확률분포 선정과정에 따라 결과는 상이하다. 본 연구에서는 지역빈도해석에서 확률강수량 산정방법으로 Quantile Regression(QR)을 적용하였다. QR 기반의 빈도해석은 확률분포 아니라 자료 자체로 확률강수량을 산정하여 기존의 확률분포 기반의 빈도해석에서 발생했던 불확실성을 개선하였다. 또는, 확률강수량의 시간에 따른 변동성도 고려되어 바정상성 빈도해석도 가능하다. 최종적으로 본 연구에서 소개된 지역빈도해석 결과와 기존의 지역빈도해석 결과 비교 검증하였다.