• 응용통계연구
• /
• 제11권2호
• /
• pp.303-315
• /
• 1998

요인실험에서 어떤 처리조합은 조작상 또는 경제적인 이유로 실험할 수 없는 경우가 있다. 이러한 실험불가능한 처리조합을 포함하고 있는 일부실시법은 불균형적인 처리조합을 구성하게 되어 어떤 요인효과에 대해 추론할 수 없게 된다. 본 논문은 실험불가능한 처리조합을 포함하지 않는 3$^{n-p}$ 일부실시법을 실행하기 위한 정의 대비의 선택 방법을 논한다한다

• Korean Chemical Engineering Research
• /
• 제46권4호
• /
• pp.756-763
• /
• 2008

본 연구에서는 잉크젯용 전도성 금속 나노 잉크 개발을 목표로 통계적인 실험과 분석을 진행하여 재현성 있는 고품질의 은 나노 입자를 합성할 수 있는 기술을 개발하고자 하였다. 은 나노 입자는 상용 수계분산제 Daxad19를 이용한 용액 환원침전법을 통해 0.3 M의 고농도로 합성되었다. 합성에 주요한 영향을 주는 6개의 인자를 선정한 후 실험 계획법(Design-of-experiment)을 통해 실험을 수행하였다. 합성된 은 입자는 SEM, TEM, UV-Visible 등의 분석법을 이용하여 입자크기 및 분포와 분산도 등을 측정하였으며 통계 프로그램인 Minitab으로 이를 최적화하였다. 통계적인 실험계획 및 분석은 2차 부분요인분석법(2k-fractional factorial design)과 반응표면분석법인 박스-벤켄법(Box-Behnken design)으로 진행하였다. 이를 통한 합성 최적화로 평균입경 $30nm{\pm}10%$를 가진 구형의 은 나노 입자를 합성하였다. 또한 본 연구에서는 실험 결과 해석을 통해 환원침전법에서의 입자크기 및 형상 제어의 방식도 실험적으로 밝혀냈다.

• 한국도로학회:학술대회논문집
• /
• 한국도로학회 2004년도 학술발표회 논문집
• /
• pp.143-148
• /
• 2004

• 한국연초학회지
• /
• 제5권1호
• /
• pp.49-56
• /
• 1983

• Journal of the Korean Statistical Society
• /
• 제9권1호
• /
• pp.1-12
• /
• 1980

A parallel flats faraction for the $3^n$ factorial experiment is symbolically written as $At = C(r\timesf)$ where $A(r\timesn)$ is of rank r. The A-matrix partitions the nonnegligible effects into $(3^{n-r}-1)/2+1$ alias sets. The $U_i$ effects in the i-th alias set are related pairwise by elements from $S_3$, the symmetric group on three symbols. For each alias set the f flats produce an $f \times u_i$ alias componet permutation matrices (ACPM) with elements from $S_3$. All the information concerning the relationships among levels of the effects is contained in the ACPM.

• Tribology and Lubricants
• /
• 제23권4호
• /
• pp.175-179
• /
• 2007

The effect of manufacturing parameters on friction characteristics of motorcycle break system was studied using a design of experiment. Such parameters conditions have an effect on the frictional factor such as applied load, sliding speed, and number of ventilated disk hole. However, it is difficult to know the mutual relation of these factors. In this study, the friction characteristics using design of experiment containing 3 elements were investigated for an optimal condition for the best motorcycle break system employing full factorial design. From this study, the result was shown that the applied load in frictional factors was the most important, next to sliding speed, number of ventilated disk hole.

• 콘크리트학회논문집
• /
• 제16권2호
• /
• pp.269-275
• /
• 2004

Factorial design method is applied to investigate the effects of various factors simultaneously rather than to conduct a series of single-factor experiment. As the results, frost resistance of the concrete specimens, in both W/C ratio of 0.28 and 0.35, was highly affected by the type of coarse aggregate that is, andesite produced more durable concrete than the limestone. Durability factor of the specimens, with W/C ratio of 0.28, which were demolded after I day and transferred to the curing room was higher than those demolded after 2 days. This stated the efficiency of the high early curing in high strength concrete.

• 한국정밀공학회지
• /
• 제26권3호
• /
• pp.47-54
• /
• 2009

In the manufacturing industry, there has been a significant increase in the use of coordinate measuring machines(CMM). In this paper, the sources of CMM measurement performance are discussed. The effects of workpiece position, length and orientation are analyzed by using the design of experiments. Both a fractional factorial design and a factorial design are employed to conduct the experimental study. The analysis of variance is performed to determine the significance of factors in the experiment and regression analysis is applied to make the measurement approximate model. The results show that position along the Z axis, length and orientation affect the CMM measurement performance.

• 품질경영학회지
• /
• 제40권1호
• /
• pp.15-24
• /
• 2012

For the construction of fractional factorial designs, the various arrays can be widely used. In this paper we review the statistical properties of fractional designs constructed by two arrays such as orthogonal array and partially balanced array, and develop a quick and easy method for analyzing unreplicated saturated designs. The proposed method can be characterized that we control the error rate by experiment-wise way and exploit the multivariate Student $t$-distribution. Especially the proposed method can be used efficiently together with some exploratory analysis methods, such as half normal probability plot method.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1996년도 추계학술대회 학술발표 논문집
• /
• pp.234-238
• /
• 1996

In this paper, Plasma-Enhanced Chemical Vapor Deposition (PECVD) modeling using Polynomial Neural Networks (PNN) has been introduced. The deposition of SiO2 was characterized via a 25-1 fractional factorial experiment, was used to train PNNs using predicted squared error (PSE). The optimal neural network structure and learning parameters were determined by means of a second fractional factorial experiment. The optimized networks minimized both learning and prediction error. From these PNN process models, the effect of deposition conditions on film properties has been studied. The deposition experiments were carried out in a Plasma Therm 700 series PECVD system. The models obtained will ultimately be used for several other manufacturing applications, including recipe synthesis and process control.