• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.38 no.5
• /
• pp.489-495
• /
• 2014

A micro-genetic algorithm (MGA) is one of the improved forms of a genetic algorithm. It is used to reduce the number of iterations and the computing resources required by using small populations. The efficiency of MGAs has been proved through many problems, especially problems with 3-5 design variables. This study proposes an optimization algorithm based on the sequential design of experiments (SDOE) and an MGA. In a previous study, the authors used the SDOE technique to reduce trial-and-error in the conventional approximate optimization method by using the statistical design of experiments (DOE) and response surface method (RSM) systematically. The proposed algorithm has been applied to various mathematical examples and a structural problem.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.34 no.9
• /
• pp.33-44
• /
• 2006

As many scientific phenomena are now investigated using complex computer models, the effective use of Kriging on physical problems has been expanded to provide global approximations for optimization problems. This paper is focused on the two types of strategies to improve efficiency and accuracy of approximate optimization models using Kriging. These methods are performed by the stochastic process, stochastic-localization method(SLM), as the criterion to move the local domains and the design of experiments(DOE), the classical design and space-filling design. The proposed methodology is applied to the designs of 3-bar truss, Sandgren's pressure vessel, and honeycomb upper platform of a satellite structure.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.32 no.3
• /
• pp.258-266
• /
• 2008

The conventional approximate optimization method, which uses the statistical design of experiments(DOE) and response surface method(RSM), can derive an approximated optimum results through the iterative process by a trial and error. The quality of results depends seriously on the factors and levels assigned by a designer. The purpose of this study is to propose a new technique, which is called a sequential design of experiments(SDOE), to reduce a trial and error procedure and to find an appropriate condition for using artificial neural network(ANN) systematically. An appropriate condition is determined from the iterative process based on the analysis of means. With this new technique and ANN, it is possible to find an optimum design accurately and efficiently. The suggested algorithm has been applied to various mathematical examples and a structural problem.

• Journal of the Korean Society for Precision Engineering
• /
• v.30 no.10
• /
• pp.1079-1086
• /
• 2013

Optimal mount position of a front pillar trim considering heat resistant characteristics can be determined by two methods. One is conventional approximate optimization method which uses the statistical design of experiments (DOE) and response surface method (RSM). Generally, approximated optimum results are obtained through the iterative process by a trial and error. The quality of results depends seriously on the factors and levels assigned by a designer. The other is a methodology derived from previous work by the authors, which is called sequential design of experiments (SDOE), to reduce a trial and error procedure and to find an appropriate condition for using artificial neural network (ANN) systematically. An appropriate condition is determined from the iterative process based on the analysis of means. With this new technique and ANN, it is possible to find an optimum design accurately and efficiently.

• Transactions of the Society of Information Storage Systems
• /
• v.3 no.4
• /
• pp.178-182
• /
• 2007

Topology optimization methods are classified into two methods such as the density method and the homogenization method. Those methods need to consider relationships between the material property and the density of each element in a design domain, the relaxation of the design space, etc. However, it is hard to apply on some cases due to the complexity to compose the design objective and its sensitivity analysis. In this paper, a modified topology optimization is proposed to assist designers who do not have mathematical or theoretical background of the topology optimization. In this study, optimal topology of structures can be achieved by the sequential design of experiment (DOE) and the sensitivity analysis. We conducted the DOE with an orthogonal array and the sensitivity analysis of design variables to determine sensitive variables used for connectivity between elements. The modified topology optimization method has advantages such as freedom from penalizing intermediate values and easy application with basic DOE concept.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.37 no.11
• /
• pp.1397-1405
• /
• 2013

The optimal rib pattern design of B-pillar trim considering occupant head protection can be determined by two methods. One is the conventional approximate optimization method that uses the statistical design of experiments (DOE) and response surface method (RSM). Generally, approximated optimum results are obtained through the iterative process by trial-and-error. The quality of results strongly depends on the factors and levels assigned by a designer. The other is a methodology derived from previous work by the authors, called the sequential design of experiments (SDOE), to reduce the trial-and-error procedure and to find an appropriate condition for using artificial neural network (ANN) systematically. An appropriate condition is determined from the iterative process based on the analysis of means. With this new technique and ANN, it is possible to find an optimum design accurately and efficiently.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.28 no.11
• /
• pp.1760-1767
• /
• 2004

Sequential sampling approaches of a metamodel that sampling points are updated sequentially become a significant consideration in metamodeling technique. Sequential sampling design is more effective than classical space filling design of all-at-once sampling because sequential sampling design is to add new sampling points by means of distance between sampling points or precdiction error obtained from metamodel. However, though the extremum points can strongly reflect the behaviors of responses, the existing sequential sampling designs are inefficient to approximate extremum points of original model. In this research, new sequential sampling approach using the sensitivity of Kriging model is proposed, so that new approach reflects the behaviors of response sequentially. Various sequential sampling designs are reviewed and the performances of the proposed approach are compared with those of existing sequential sampling approaches by using mean squared error. The accuracy of the proposed approach is investigated against optimization results of test problems so that superiority of the sensitivity approach is verified.

• Applied Chemistry for Engineering
• /
• v.32 no.6
• /
• pp.621-626
• /
• 2021

A sequential design of experiments was used to optimize MOF-801 synthesis process. For the initial screening, a general 2^k factorial design was selected followed by the central composition design, one of the response surface methods. A 2³ factorial design based on the molar ratio of fumaric acid, dimethylformamide (DMF), and formic acid was performed to select the more suitable response variable for the design of experimental method among the crystallinity and BET specific surface area of MOF-801. After performing 8 synthesis experiments designed by MINITAB 19 software, the characteristic analysis was performed using XRD analysis and nitrogen adsorption method. The crystallinity with R² = 0.999 was found to be more suitable for the experimental method than that of BET specific surface area. Based on analysis of variance (ANOVA), it was confirmed that the molar ratio of fumaric acid and formic acid was a major factor in determining the crystallinity of MOF-801. Through the response optimization and contour plot of two factors, the optimal molar ratio of ZrOCl₂·8H₂O : fumaric acid : DMF : formic acid was 1 : 1 : 39 : 35. In order to optimize the synthesis process, the central composition design on synthesis time and temperature was performed under the identical molar ratio of precursors. The results derived through the designed 9 synthesis experiments were calculated using the quadratic model equation. Thus, the maximum crystallinity of MOF-801 predicted under the synthesis time and temperature of 7.8 h and 123 ℃, respectively.

• Proceedings of the KIEE Conference
• /
• 2015.07a
• /
• pp.788-789
• /
• 2015

본 논문에서는 사이클로트론 전자석의 설계과정을 체계화하고, 자기장 최적화 과정을 순차적 근사화 기법을 이용하여 설계를 진행하였다. 설계하는 전자석은 방사성동위원소생산을 목적으로하는 PET(Positron Emission Tomography) 사이클로트론 이며, 크기를 줄이고 동위원소의 효율적인 생산을 위해 에너지대역은 10MeV로 선정하였다. 설계과정은 실험계획법 중 하나인 LHS(Latin Hypercube Sampling) 기법을 통해 샘플 데이터를 구성하고, 이를 바탕으로 크리깅을 이용해 근사모델을 구성한다. 근사 모델과 진화 알고리즘을 이용해 목적에 맞는 최적의 형상을 찾을 수 있다. 이러한 과정을 반복함으로써 점진적으로 목적에 부합하는 형상을 찾을 수 있다. 각각의 형상의 성능을 판단하는 목적함수를 단계별로 규칙을 정함으로써 결과의 신뢰도를 높인다. 이로써 시간적 효율을 증대시키고 전문지식이 부족한 설계자도 고성능의 형상을 얻을 수 있다. 최적화과정은 STEP1과 STEP2로 나누어 진행되며, STEP1에서는 초기사이클로트론 전자석을 설계하고, 자기장 최적화를 진행한다. STEP2에서는 빔 시뮬레이션 및 분석을 통하여 최적화를 진행하고, 최종적으로 전자석모델을 완성한다.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.35 no.9
• /
• pp.1007-1013
• /
• 2011

Because of their high flexibility and durability, multilayer bellows are manufactured for use in commercial vehicles, while single-layer bellows are manufactured for use in passenger vehicles. A study based on the finite element method (FEM) and shape optimization for the single-layer bellows has been actively performed; however, until now, a study based on the FEM has rarely been performed for the multilayer bellows with gaps between the layers. This paper presents a finite-element modeling scheme for the multilayer bellows to improve simulation reliability during the evaluation of stress and flexibility. For performing shape optimization for the multilayer bellows, DOE (design of experiment) and the Kriging metamodel followed by the D-optimal method are used.