• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2003년도 추계학술대회
• /
• pp.1430-1435
• /
• 2003

Satellite upper platform is optimized by response surface method which has non-gradient, semi-glogal, discrete and fast convergency characteristics. Sampling points are extracted by design of experiments using Central Composite Method and Factorial Design. Also response surface is generated by the various regression functions. Structure analysis is execuated with regard for static and dynamic environment in launching stage. As a result response surface method is superior to other optimization method with respect to optimum value and cost of computation time. Also a confidence is varified in the various regression models.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2005년도 춘계 학술발표회 논문집
• /
• pp.95-100
• /
• 2005

In this paper a class of multifactor designs for estimating the slope of second order response surface regression models with correlated errors is considered. General conditions for second order slope rotatability over all directions and also with respect to the maximum directional variance in case of k=2 have been derived assuming errors have a general correlated error structure. And we consider the measures for evaluating slope rotatability with correlated errors similar to in case of uncorrelated error structures.

• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 2002년도 춘계공동학술발표회요약집
• /
• pp.54-54
• /
• 2002

• 동아시아식생활학회지
• /
• 제1권3호
• /
• pp.305-311
• /
• 1991

The study was designed to investigate overall acceptability of rice extrudate with added ginseng flour extruded by single screw extruder. Graphic three dimension analysis on response surface regression was conducted for overall acceptability evaluated by balanced incomplete block design. Overall acceptability, which formed a saddle point, increased as moisture content increased at lower die temperature, and as moisture content decreased at higher die temperature. Critical values of each variable which indicated optimum response are 5.0% ginseng content, 17.8% moisture content and 104.6$^{\circ}C$ die temperature, and optimum inferred score of overall acceptability is 59.6 and 90. Key words: extrdate, overall acceptability, response surface regression analysis, balanced incomplete block method.

• 한국식품영양학회지
• /
• 제6권3호
• /
• pp.178-188
• /
• 1993

This research was attempted to investigate changes in physicochemical properties of rice extrudate with added ginger powder extruded by single screw extruder. Graphic three dimensional analysis on response surface regression was used to evaluate effects of extrusion variables on quality factors of the extrudate according to two independent variables, ginger consent 0∼12%, moisture content 14∼26%. The summarized results are as follows : 1) Regarding proximate composition of rice extrudate with added ginger powder, as ginger powder content of raw material Increased, crude tat, crude protein, crude ash and crude fiber increased, while soluble nitrogen free extract decreased. 2) Graphic three dimensional analysis on response surface regression was conducted for each dependent variable which revealed statistically significant relationship with independent variables, 0∼120A ginger and 14∼26% moisture content. Expansion ratio had a critical point as moisture content changed. As ginger and moisture content Increased, bulk density, break strength and water absorption Index Increased, while water solubility Index decreased. The predicted maximum degree of gelatinization in 6.15% ginger and 15.56% moisture content is 88.27%, and lightness decreased as ginger content Increased. According to the microstructure for the cross section of extrudate obsorbed with image analyzer, air cell number and perimeter revealed saddle point, meanwhile total area and fractarea of air cell had critical points as moisture content changed. In view of the results, quality of rice extrudate with added ginger powder was optimum when rice flour was fed to the extruder with 2∼7% singer powder and 15∼20% moisture content.

• Journal of Dairy Science and Biotechnology
• /
• 제26권2호
• /
• pp.51-56
• /
• 2008

Using central composite design, we have designed optimization of the manufacturing of processed butter. And response surface analysis by least-square regression was used Statistical Analysis System(SAS). Central composite design can be achieved by response surface techniques that allow flexibility in modeling and analysis. Response surface methodology(RSM) was used to optimize hardness(%) using as independent variables; the content of butter($X_1$), ranging from 50 to 90(%), the content of soybean oil($X_2$), from 0 to 20(%), and the hydrogenated soybean oil($X_3$) from 0 to 4(%). The results on the regression coefficients calculated for overrun by response surface by least-square regression(RSREG) were followed. It was considered that the linear regression was significant(p<0.01). As for the processed butter, the regression model equation for the hardness(Y, %) to the change of an independent variable could be predicted as follow: $Y=60.88-8.92X_2-{29.3X_2}^2$. The optimal for the manufacturing of processed butter were determined at the content of butter of 88.22%, soybean oil of 6.71% and hydrogenated soybean oil of 2.36%, respectively. Optimum compositions were resulted in hardness of 65.78 N. Finally the reference sample(Butter in the morning, Seoul Dairy Co-op.) and processed butter manufacturing under the optimal conditions were compared with spreadability test. The spreadability scores result from reference sample and butter under optimal conditions was not found a significant difference.

• Journal of the Korean Statistical Society
• /
• 제36권4호
• /
• pp.557-578
• /
• 2007

In Response Surface Methodology (RSM), rotatability is a natural and highly desirable property. For second order general correlated regression model, the concept of robust rotatability was introduced by Das (1997). In this paper a new measure of robust rotatability for second order response surface designs with correlated errors is developed and illustrated with an example. A comparison is made between the newly developed measure with the previously suggested measure by Das (1999).

• Journal of the Korean Statistical Society
• /
• 제9권1호
• /
• pp.61-77
• /
• 1980

In response surface experiments, a polynomial model is often used to fit the response surface by the method of least squares. However, if the vectors of predictor variables are multicollinear, least squares estimates of the regression parameters have a high probability of being unsatisfactory. Hoerland Kennard have demonstrated that these undesirable effects of multicollinearity can be reduced by using "ridge" estimates in place of the least squares estimates. Ridge regrssion theory in literature has been mainly concerned with selection of k for the first order polynomial regression model and the precision of $\hat{\beta}(k)$, the ridge estimator of regression parameters. The problem considered in this paper is that of selecting k of ridge regression for a given polynomial regression model with an arbitrary order. A criterion is proposed for selection of k in the context of integrated mean square error of fitted responses, and illustrated with an example. Also, a type of admissibility condition is established and proved for the propose criterion.criterion.

• 한국항공우주학회지
• /
• 제33권1호
• /
• pp.26-32
• /
• 2005

본 연구에서는 반응표면법에 다항함수, 지수함수, 로그함수등을 적용한 다양한 회귀함수를 이용하여 최적화를 수행하였다. 이를 검증하기 위해 트러스 구조와 하니콤 복합재 플랫폼에 대하여 응력 및 고유진동수를 고려하여 최적설계를 수행하였다. 근사함수를 효과적이고 용이하게 하는 방법을 실험계획법이라 하는데 중심합성법, 요인설계법, 회전계획법, 심플렉스법 등이 있으며, 본 연구에서는 중심합성법을 이용하여 반응표면을 생성하였다. 이를 위하여 구조해석 코드로 MSC/NASTRAN을 사용하였으며 최적설계 프로그램은 중심합성법을 기반으로 하여 다양한 회귀모델에 의한 반응표면을 적용하여 작성하였다. 또한 이 결과를 기존의 도함수를 이용한 최적화 기법이나 유전자알고리즘을 이용한 최적화 결과와 비교하여 반응표면법의 설계상의 장점 및 반응표면 생성 시 다양한 회귀모델에의 사용에 대한 신뢰성을 확인하였다.

• Journal of the Korean Statistical Society
• /
• 제7권2호
• /
• pp.109-119
• /
• 1978

When a response surface by a seconde order polynomial regression model, the stationary point is obtained by solving simultaneous linear equations. But the point is a function of random variables. We can find a confidence region for this point as Box and Hunter provided. However, the confidence region is often too large to be useful for the experiments, and it is necessary to augment additional design points in order to obtain a satisfactory confidence region for the stationary point. In this note, the author suggests a method how to augment design points "eficiently", and shows the change of the confidence region of the estimated stationary point in a response surface.e surface.