• 한국지리정보학회지
• /
• 제20권3호
• /
• pp.125-140
• /
• 2017

지금까지 지가나 주택가격을 추정하는데 회귀모형 기반 공간내삽법과 크리깅(Krging) 기반 공간내삽법이 많이 사용되었지만, 이들 공간내삽법의 성능을 서로 비교한 연구는 거의 없는 실정이다. 따라서 본 연구는 대구시 달서구를 사례로 지가를 추정하는데 회귀모형 기반 공간내삽법과 크리깅 기반 공간내삽법을 적용해 보고 그 정확성을 평가하였다. 회귀모형 기반 공간내삽을 위해 최소자승모형(OLS), 공간지체모형(SLM), 공간오차모형(SEM), 지리가중회귀모형(GWR)을 사용하였고, 크리깅 기반 공간내삽을 위해 단순 크리깅(SK), 정규 크리깅(OK), 일반 크리깅(UK), 공동 크리깅(CK)을 이용하였다. 먼저, 전역적 정확성 지수인 평균 제곱근 오차(RMSE), 수정된 평균 제곱근 오차(adjusted RMSE), 분산지수(COD)를 이용하여 그 정확성을 통계적으로 평가하였다. 다음으로, 3차원 잔차도와 산점도를 이용하여 그 정확성을 시각적으로 서로 비교하였다. 통계적 및 시각적 분석결과에 의하면, 공간적 의존성을 반영할 수 있는 공간회귀모형(SAR)과 크리깅 기법들 보다 공간적 이질성을 고려할 수 있는 GWR이 사례지역에서 지가를 추정하는데 상대적으로 정확한 공간내삽방법인 것으로 나타났다. 본 연구의 결과는 지가를 통해 도시의 공간구조를 분석하는 이차적 연구에 기여할 것이다.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2005년도 추계학술대회 논문집
• /
• pp.289-295
• /
• 2005

LMTT(Linear Motor-based Transfer Technology)는 항만 자동화를 위한 수평 이송 시스템이며, 셔틀카(shuttle car)와 격자구조의 레일에 부착된 스테이터 모듈(stator module)로 구성된 PMLSM(Permanent Magnetic Linear Synchronous Motor)에 의해 구동된다. 본 논문에서는 LMTT시스템에서 컨테이너 운반을 담당하는 셔틀카(shuttle car)를 구성하는 부품인 이동체(mover)의 경량화를 위하여 직교배열표 및 크리깅 방법을 이용하여 최적설계를 수행한다. 설계변수로는 가로빔, 세로빔, 휠빔의 두께를 제한조건 함수로는 안전율이 고려된 응력을 넘지 않도록 설정하였다. 목적함수로는 중량을 설정하였다. 본 연구에서 제시된 방법으로 구한 최적해는 크리깅 내삽법(Kriging interpolation)으로 알려진 DACE(Design and Analysis of Computer Experiments) 모델을 엑셀(Excel)로 수식화하고 구했으며, GENESIS를 이용하여 민감도기반 최적설계로 구해진 최적해와 비교 및 검토하였다.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2003년도 춘계학술발표회 논문집
• /
• pp.415-420
• /
• 2003

GIS technique was applied to the analysis of ambient air quality information. For this study, the air quality information was imported with the geographical information in Capital Area. This study well proves that GIS technique has a great deal of potential to analyze those air quality information, to produce useful information, and to ease the efforts for air quality improvement. Concerning about the data interpolation, the discrepancy caused by applying different method was ignorable, although Kriging method is further developed.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2004년도 추계학술대회
• /
• pp.870-875
• /
• 2004

Current trend of design technologies shows engineers to objectify or automate the given decision-making process. The numerical optimization is an example of such technologies. However, in numerical optimization, the uncertainties are uncontrollable to efficiently objectify or automate the process. To better manage these uncertainties, Taguchi method, reliability-based optimization and robust optimization are being used. To obtain the target performance with the maximum robustness is the main functional requirement of a mechanical system. In this research, the robust design strategy is developed based on the DACE and the global optimization approaches. The DACE modeling, known as the one of Kriging interpolation, is introduced to obtain the surrogate approximation model of the system. The robustness is determined by the DACE model to reduce the real function calculations. The simulated annealing algorithm of global optimization methods is adopted to determine the global robust design of a surrogated model. The mathematical problems and the MEMS design problem are investigated to show the validity of the proposed method.

• 한국기계가공학회지
• /
• 제6권3호
• /
• pp.38-46
• /
• 2007

Weight reduction for an automobile component has been sought to achieve fuel efficiency and energy conservation. In response to this trend, a new disc-brake called the circumferential friction disc-brake is suggested. This paper compares the mechanical performances of a conventional disc-brake and a suggested disc-brake, under the dynamic braking condition. The thermoelastic instability is considered to simulate the test condition. Furthermore, the metamodel using kriging interpolation method is introduced to obtain the optimum design of a suggested circumferential friction disc-brake. The design results obtained by the kriging method are compared with those obtained by the ANSYS.

• Interaction and multiscale mechanics
• /
• 제2권4호
• /
• pp.353-374
• /
• 2009

A new seamless multiscale simulation was developed for coupling the continuum model with its molecular dynamics. Kriging-based Finite Element Method (K-FEM) is employed to model the continuum base of the entire domain, while the molecular dynamics (MD) is confined in a localized domain of interest. In the coupling zone, where the MD domain overlaps the continuum model, the overall Hamiltonian is postulated by contributions from the continuum and the molecular overlays, based on a quartic spline scaling parameter. The displacement compatibility in this coupling zone is then enforced by the Lagrange multiplier technique. A multiple-time-step velocity Verlet algorithm is adopted for its time integration. The validation of the present method is reported through numerical tests of one dimensional atomic lattice. The results reveal that at the continuum/MD interface, the commonly reported spurious waves in the literature are effectively eliminated in this study. In addition, the smoothness of the transition from MD to the continuum can be significantly improved by either increasing the size of the coupling zone or expanding the nodal domain of influence associated with K-FEM.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2004년도 춘계학술대회
• /
• pp.1035-1040
• /
• 2004

In the proto design stage of a new car, the performance of an occupant protection system is often evaluated by CAE instead of the real test. CAE predicts and recommends the appropriate design values hence reducing the number of the real tests. However, the existing researches using CAE in predicting the performances do not consider the uncertainties of parameters, in which inconsistency between the actual test results and CAE exists. In this research, the optimization procedure of a protection system such as airbag and load limiter is suggested for the frontal collision. The DACE modeling known as Kriging interpolation is introduced to obtain the meta model of the system followed by the tabu search method to determine a global optimum. Finally, the distribution of a suggested design is determined through the Monte-Carlo Simulation.

• 한국공작기계학회논문집
• /
• 제14권6호
• /
• pp.125-131
• /
• 2005

The purpose of this study is an optimization of gate valve made by forging method instead of welding method. In this study, we propose an optimal shape design to improve the mechanical efficiency of gate valve. In order to optimize more efficiently and reliably, the meta-modeling technique has been developed to solve such a complex problems combined with the DACE (Design and Analysis of Computer Experiments). The DACE modeling, known as the one of Kriging interpolation, is introduced to obtain the surrogate approximation model of the function. Also, we prove reliability of the DACE model's application to gate valve by computer simulations using FEM(Finite Element Method).

• 대한지리학회지
• /
• 제45권6호
• /
• pp.806-819
• /
• 2010

센서스 단위의 인구자료는 기초적인 인문사회 자료로 행정구역 단위로 요약되어 공간분석에 시용된다. 정밀한 인구 분포를 추정하기 위해 기존의 연구에서는 위성영상과 회귀분석 모형을 이용하였다. 하지만 회귀식에 의한 추정치는 공간자료의 공간적자기상관과 잔차 때문에 정확도에 있어 한계가 있었다. 본 연구는 회귀모형과 회귀모형에서 추출된 잔차에 대해 공간적자기상관을 고려하도록 크리깅 보간하는 RK모형(Regression Kriging Model)을 이용하여 인구분포의 추정 정확도를 향상하였다. RK모형을 적용하여 서울시의 4개구를 대상으로 사례분석을 하였으며, 모형의 효율성을 검증하기 위해 회귀분석만을 이용한 예측 결과와 RK모형을 이용한 예측 결과를 서로 비교하였다. 비교한 결과로 상관관계 계수 평균제곱근 오차, G 통계량 수치에서 RK모형의 추정 정확도가 기존의 회귀모형에 비해 높게 나온 것을 확인할수 있었다. 향후 정확한 인구추정을 위해 RK모형이 많이 활용될 수 있을 것이다.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2001년도 춘계학술대회논문집C
• /
• pp.537-542
• /
• 2001

In recent engineering, the designer has become more and more dependent on computer simulation. But defining exact model using computer simulation is too expensive and time consuming in the complicate systems. Thus, designers often use approximation models, which express the relation between design variables and response variables. These models are called metamodel. In this paper, we introduce one of the metamodel, named Kriging. This model employs an interpolation scheme and is developed in the fields of spatial statistics and geostatistics. This class of interpolating model has flexibility to model response data with multiple local extreme. By reason of this multi modality, we can't use any gradient-based optimization algorithm to find global extreme value of this model. Thus we have to introduce global optimization algorithm. To do this, we introduce DE(Differential Evolution). DE algorithm is developed by Ken Price and Rainer Storn, and it has recently proven to be an efficient method for optimizing real-valued multi-modal objective functions. This algorithm is similar to GA(Genetic Algorithm) in populating points, crossing over, and mutating. But it introduces vector concept in populating process. So it is very simple and easy to use. Finally, we show how we determine Kriging metamodel and find global extreme value through two mathematical examples.