• 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).

• 대한기계학회논문집A
• /
• 제32권11호
• /
• pp.970-977
• /
• 2008

This paper deals with the dynamic characteristics of the shaft with impeller model which is the most important part in developing the resin mixing machine. Through reverse engineering, it is possible to make the shaft with impeller geometry model which is necessary vibration characteristic analysis by commercial impeller. The natural frequency analysis and structural analysis using finite element analysis software are performed on the imported commercial shaft with impeller model. The most important fundamental natural frequency of the shaft with impeller model is around 14.5 Hz, which well agrees with modal testing. The most effective design variables were extracted by ANOM(analysis of means) and pareto chart. This paper presents approximation 2nd order polynomial as design variables using RSM(response surface methodology). Generally, RSM take 2 or 3 design variables, but this method uses 5 design variables with table of mixed orthogonal array. Further more, the analyzed result of the commercial shaft with impeller is to be utilized for the structural design of resin chock mixing machine.

• International Journal of Naval Architecture and Ocean Engineering
• /
• 제13권1호
• /
• pp.321-339
• /
• 2021

Response Surface Method (RSM) has been widely used for flammable cloud size prediction as it can reduce computational intensity for further Explosion Risk Analysis (ERA) especially during the early design phase of offshore platforms. However, RSM encounters the overfitting problem under very limited simulations. In order to overcome the disadvantage of RSM, Bayesian Regularization Artificial Neural (BRANN)-based model has been recently developed and its robustness and efficiency have been widely verified. However, for ERA during the early design phase, there seems to be room to further reduce the computational intensity while ensuring the model's acceptable accuracy. This study aims to develop an integrated method, namely the combination of Center Composite Design (CCD) method with Bayesian Regularization Artificial Neural Network (BRANN), for flammable cloud size prediction. A case study with constant and transient leakages is conducted to illustrate the feasibility and advantage of this hybrid method. Additionally, the performance of CCD-BRANN is compared with that of RSM. It is concluded that the newly developed hybrid method is more robust and computational efficient for ERAs during early design phase.

• 한국산학기술학회논문지
• /
• 제20권6호
• /
• pp.557-564
• /
• 2019

매입형 영구자석 동기전동기(IPMSM : Interior Permanent Magnet Synchronous Motor, 이하 IPMSM)의 회전자 자석의 크기 및 위치와 고정자 슬롯의 크기는 출력 토크 및 토크 리플률 특성에 영향을 준다. 본 논문은 반응표면분석법(RSM : Response Surface Methodology, 이하 RSM)을 이용한 IPMSM의 토크와 토크 리플률(ripplerate) 향상을 위한 최적설계 방법에 대해 다룬다. 토크 출력과 토크 리플률에 영향을 주는 설계변수에 대하여 Plackett-Burmann(PB, 이하 PB)의 민감도 분석을 통해 토크 출력 및 토크 리플 두 가지 목적함수에 영향이 큰 설계변수를 도출하였다. 도출된 목적함수로부터 2차 설계변수를 선정하였으며 중심합성계획법(CCD : Central Composite Design, 이하 CCD)에 따른 실험계획표 정의 및 해석결과를 통해 RSM의 2차 회귀모형 함수를 추정하였다. 2차 회귀모형함수는 분산분석표(ANOVA table)를 활용한 검증 기준을 통해 신뢰성을 가짐을 확인하였다. 실험계획표에 따른 해석은 유한요소법(FEM : Finite Element Method, 이하 FEM) 해석 소프트웨어인 JMAG을 통하여 실험 결과를 확인하였다. 최적화된 최종 설계변수를 적용한 IPMSM의 최적설계 결과는 토크와 토크 리플률을 모두 고려할 경우, 토크 출력은 11.5 % 증가하였으며 토크 리플률은 9.1 % 감소하였다.

• Journal of Dairy Science and Biotechnology
• /
• 제40권3호
• /
• pp.93-102
• /
• 2022

본 연구는 L. plantarum K79를 이용하여 ACE 억제활성 향상을 위한 최적의 발효조건을 RSM을 이용하여 예측하고자 하였다. 4개의 독립변수[탈지유(포도당 1% 첨가) 농도(6%-14%), 배양 온도(32℃-42℃), 배양 시간(8-24시간), 스타터 첨가량(0.02%-0.2%)] 5단계 중심 합성 설계 및 반응 표면 분석법을 사용하여 최적의 발효 조건을 결정하는 데 사용하였다. 종속변수는 ACE 억제 활성과 pH였다(이때 ACE 억제율은 조건별 발효원액에서 100배 희석하여 나타낸 값이다). 결정 계수(R²)는 ACE 억제 활성, pH에 대해 각각 0.791, 0.905이었다. 최대 ACE 억제 활성은 10% 탈지유(포도당 1% 첨가) 농도, 37℃ 배양 온도, 17.8 h 배양 시간 및 0.2% 스타터 첨가량 조건에서 90%이었다. RSM에 기초하여 예측된 최적 발효 ACE 조건은 탈지유(포도당 1% 첨가) 농도 13.49%, 스타터 0.0578%, 배양온도 33.4℃에서 21.5시간 동안 배양할 때 ACE 억제 활성 및 pH의 예측 값은 86.69% 및 pH 4.6이었으며 실제 값은 각각 85.5%와 pH 4.58이었다.

• Food Science and Biotechnology
• /
• 제14권1호
• /
• pp.28-31
• /
• 2005

To extract apple pectins, apple pomace (AP) was extruded under 14 different conditions of screw speed (250-350 rpm), feed rate of 30-40 kg/hr, and 20-30% moisture content using twin-screw extrusion. Response surface methodology (RSM), based on three variables by three-level factorial design, was employed to investigate effects of screw speed, feed rate, and moisture on dependent variables of extrudates, soluble dietary fiber (SDF), yield of anhydrogalacturonic acid ($Y_{AGA}$) representing pectin, and intrinsic viscosity ([${\eta}$]). Second order models were used to generate three-dimensional response surface for dependent variables, and their coefficients of determination ($R^2$) ranged from 0.96 to 0.99. Moisture content showed highest effect on solubilization of AP.

• 한국식품영양학회지
• /
• 제7권2호
• /
• pp.137-143
• /
• 1994

To optimize extrusion cooking condition of single screw extuder for production of puffed rice extrudate using response surface methodology (RSM), moisture content, barrel temperature and screw speed were determined from contour maps, showing relationship between dependent (hardness, expansion ratio, water absorption index, water solubility Index, degree of gelatinization) and independent variables. Optimum operational conditions for production of puffed rice extrudate with suitable quality properties were moisture content 17%, barrel temperature 1$25^{\circ}C$ and screw speed 210 rpm, respectively.

• 한국물환경학회지
• /
• 제26권1호
• /
• pp.35-43
• /
• 2010

This experimental design and response surface methodology (RSM) have been applied to the investigation of the electrocoagulation/flotation of dye wastewater. The electrocoagulation/flotation reactions were mathematically described as a function of parameters current (A), NaCl concentration (B), initial RhB concentration (C) and time (D) being modeled by use of the central composite design (CCD). The application of RSM using the CCD yielded the following regression equation, which is an empirical relationship between the RhB removal (%) and test variables in RhB removal (%) = $-300.42+129.21{\cdot}Current+46.99{\cdot}NaCl-0.11{\cdot}RhB-+43.71{\cdot}Time-5.67{\cdot}Current{\cdot}NaCl-3.18{\cdot}Current{\cdot}Time-2.41{\cdot}NaCl{\cdot}Time-19.79{\cdot}Current^2-2.27{\cdot}NaCl^2-1.59{\cdot}Time^2$. the model predictions agreed well with the experimentally observed result ($R^{2}=0.9728$). The estimated ridge of maximum response and optimal conditions for RhB removal (%) using canonical analysis was 99.4% (A: 1,77 A, NaCl concentration: 2.23 g/L, RhB concentration: 56.12 mg/L, Time: 9.98 min). To confirm this optimum condition, three additional experiments were performed and RhB removal (%) were within range of 86.87% (95% PI low)~111.93% (95% PI high) obtained.

• 한국식품과학회지
• /
• 제29권4호
• /
• pp.752-757
• /
• 1997

Papaya 유액 추출물에서 protein을 정제 회수하기 위해 papaya 유액으로부터 추출한 추출액을 경제적이고도 처리가 비교적 간단한 ethanol 침전방법을 사용하였다. 실험계획법에 의하여 설정된 3수준의 부분요인 실험법에 의하여 실시된 각 처리구의 실험 결과를 다중 회귀분석 방법에 의해 다음과 같은 모델식 $Y=7.4554+1.2657X_{2}+1.0552X_{3}-1.7407X_{4}-0.01666X_{2}\;^{2}-0.1134X_{4}^{2}$을 산출하였으며 pH는 다중 회귀분석에 의해 제거되었다. 반응표면 분석법(RSM)을 이용한 결과 protein을 회수하기 위한 최적 조건으로는 protein 농도가 38.2 mg/ml, 40%의 ethanol 농도, 침전 온도는 $-8^{\circ}C$였다. 이러한 최적 조건에 의한 회수율의 실험치는 68.97%로 예측치인 77.28%에 근접한 결과였다. 또한 유의 수준을 검정하는 자유도와 F-value도 양호한 값(p<0.001)을 나타내어 종속변수와 독립변수와의 상관관계가 뛰어남을 알 수 있으며 따라서 다중 회귀분석에 얻어진 모델식의 각 변수들 사이에는 유의성이 높음을 알 수 있었다.

• 한국유체기계학회 논문집
• /
• 제15권3호
• /
• pp.39-45
• /
• 2012

In this study, optimization of the impeller and design of volute were carried out in order to improve the performance of a centrifugal pump. Design parameters from vane plane development for impeller design were selected, and effect of the design parameters on the performance of the pump was analyzed by using Response Surface Methodology(RSM) to optimized impeller. In addition, total pump design method was suggested by designing volute which was suitable for the optimized impeller through volute design where Stepanoff theory was applied and numerical analysis.