• Journal of Korean Society for Quality Management
• /
• v.27 no.1
• /
• pp.165-194
• /
• 1999

Taguchi's parameter design seeks proper choice of levels of controllable factors (Parameters in Taguchi's terminology) that makes the qualify characteristic of a product optimal while making its variability small. This aim can be achieved by response surface techniques that allow flexibility in modeling and analysis. In this article, a collection of response surface modeling and analysis techniques is proposed to deal with the multiresponse optimization problem in experimentation with Taguchi's signal and noise factors.

• Journal of the Korean Statistical Society
• /
• v.5 no.2
• /
• pp.101-107
• /
• 1976

One of the important properties of a 'good' response surface design is that the design should be insensitive to wild observations. In this note, a measure of sensitivity to wild observations is studied. It is shown that designs are made robust to wild observations by making $Tr[X'X)^{-1}M]$ small where M is a moment matrix over some region of interest. The proposed criterion is compared with that suggested by Box and Draper. Some about robust two-variable response surface designs are given.

• Journal of the Korean Society for Precision Engineering
• /
• v.13 no.10
• /
• pp.56-61
• /
• 1996

In this study a method for a robust design of mechanisms is proposed. The method used in the experimental analysis and quality engineering is applied for mechanisms design. A mathematical model for a mechanism is estimated by the response surface analysis and the estimated model is used in minimization of the variance. Using this result, robust design can be carried out. The method can be applied for general mechansims. Furthermore because the method can be used in the design stage using the computer model, improved quality and lower cost of the product is achieved even in the design stage.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.33 no.2
• /
• pp.32-38
• /
• 2005

In this research, a procedure to improve the feasibility of design space is proposed by an approximation model. The Chebyshev Inequality is used as the criterion of modification of design space. This procedure is applied to the aero-elastic transonic wing design problem and the feasibility of the design space is greatly improved. Also the optimization results are improved by appling this procedure. That is, the probability to satisfy all imposed constraints is increased and the better design points are included in design space after this procedure. And the use of both a second-order response surface model and the Kriging model is investigated and compared in accuracy, efficiency, and robustness as approximation models in this procedure for different sampling methods. As a result, the second-order response surface model is more appropriate for our application than the Kriging model, because it is linear enough to be fitted well by the response surface model.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.32 no.7
• /
• pp.13-18
• /
• 2004

This paper describes an efficient and robust optimization method for helicopter rotor airfoil design in forward flight. Navier-Stokes analysis was employed to compute the dynamic response of an airfoil, which simulates the unsteady rotor flow-field in forward flight. The optimization system consists of two categories; Response Surface Method to construct the response surface model based on D-optimal 3-level factorial design, and Genetic Algorithm to obtain the optimum solution of a defined objective function including penalty terms of constraints. The influence of design variables and their interactions on the aerodynamic performance was examined through the optimization process.

• Structural Engineering and Mechanics
• /
• v.49 no.1
• /
• pp.111-128
• /
• 2014

The stochastic response surface method (SRSM) and the response surface method (RSM) are often used for structural reliability analysis, especially for reliability problems with implicit performance functions. This paper aims to compare these two methods in terms of fitting the performance function, accuracy and efficiency in estimating probability of failure as well as statistical moments of system output response. The computational procedures of two response surface methods are briefly introduced first. Then their capabilities are demonstrated and compared in detail through two examples. The results indicate that the probability of failure mainly reflects the accuracy of the response surface function (RSF) fitting the performance function in the vicinity of the design point, while the statistical moments of system output response reflect the accuracy of the RSF fitting the performance function in the entire space. In addition, the performance function can be well fitted by the SRSM with an optimal order polynomial chaos expansion both in the entire physical and in the independent standard normal spaces. However, it can be only well fitted by the RSM in the vicinity of the design point. For reliability problems involving random variables with approximate normal distributions, such as normal, lognormal, and Gumbel Max distributions, both the probability of failure and statistical moments of system output response can be accurately estimated by the SRSM, whereas the RSM can only produce the probability of failure with a reasonable accuracy.

• Korean Journal of Computational Design and Engineering
• /
• v.5 no.2
• /
• pp.127-135
• /
• 2000

Emergent computing paradigms such as genetic algorithms have found increased use in problems in engineering design. These computational tools have been shown to be applicable in the solution of generically difficult design optimization problems characterized by nonconvexities in the design space and the presence of discrete and integer design variables. Another aspect of these computational paradigms that have been lumped under the bread subject category of soft computing, is the domain of artificial intelligence, knowledge-based expert system, and machine learning. The paper explores a machine learning paradigm referred to as teaming classifier systems to construct the high-quality global function approximations between the design variables and a response function for subsequent use in design optimization. A classifier system is a machine teaming system which learns syntactically simple string rules, called classifiers for guiding the system's performance in an arbitrary environment. The capability of a learning classifier system facilitates the adaptive selection of the optimal number of training data according to the noise and multimodality in the design space of interest. The present study used the polynomial based response surface as global function approximation tools and showed its effectiveness in the improvement on the approximation performance.

• Journal of Mechanical Science and Technology
• /
• v.16 no.2
• /
• pp.203-210
• /
• 2002

For effective response surface modeling during sequential approximate optimization (SAO), the normalized and the augmented D-optimality criteria are presented. The normalized D-optimality criterion uses the normalized Fisher information matrix by its diagonal terms in order to obtain a balance among the linear-order and higher-order terms. Then, it is augmented to directly include other experimental designs or the pre-sampled designs. This augmentation enables the trust region managed sequential approximate optimization to directly use the pre-sampled designs in the overlapped trust regions in constructing the new response surface models. In order to show the effectiveness of the normalized and the augmented D-optimality criteria, following two comparisons are performed. First, the information surface of the normalized D-optimal design is compared with those of the original D-optimal design. Second, a trust-region managed sequential approximate optimizer having three D-optimal designs is developed and three design problems are solved. These comparisons show that the normalized D-optimal design gives more rotatable designs than the original D-optimal design, and the augmented D-optimal design can reduce the number of analyses by 30% - 40% than the original D-optimal design.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2006.04a
• /
• pp.275-282
• /
• 2006

System algorithms estimated by deterministic input may occur the error between predicted and actual output. Especially, actual system can't predict the exact outputs due to uncertainty and tolernce of input parameters. A single output to a set of inputs has a limited value without the variation. Hence, we should consider various scatters caused by the load assessment, material characteristics, stress analysis and manufacturing methods in order to perform the robust design or etimate the reliability of structure. The system design with uncertainty should perform the probabilistic structural optimization with the statistical response and the reliability. This method calculated the probability distributions of the characteristics such as stress by combining stress analysis, response surface methodology and Monte Carlo simulation and got the probabilistic sensitivity. The sensitivity of structural response with respect to in constant design variables was estimated by fracture probability. Therefore, this paper proposed the probabilistic reliability design method for fracture of uncorved freight end beam and the design criteria by fracture probability.

• Food Science of Animal Resources
• /
• v.39 no.1
• /
• pp.114-120
• /
• 2019

Response surface methodology (RSM) is a useful set of statistical techniques for modeling and optimizing responses in research studies of food science. As a design for a response surface experiment, a central composite design (CCD) with multiple runs at the center point is frequently used. However, sometimes there exist situations where some among the responses at the center point are outliers and these outliers are overlooked. Since the responses from center runs are those from the same experimental conditions, there should be no outliers at the center point. Outliers at the center point ruin statistical analysis. Thus, the responses at the center point need to be looked at, and if outliers are observed, they have to be examined. If the reasons for the outliers are not errors in measuring or typing, such outliers need to be deleted. If the outliers are due to such errors, they have to be corrected. Through a re-analysis of a dataset published in the Korean Journal for Food Science of Animal Resources, we have shown that outlier elimination resulted in the increase of the maximum possible R-square that the modeling of the data can obtain, which enables us to improve the quality of response surface analysis.