• The Korean Journal of Applied Statistics
• /
• v.11 no.2
• /
• pp.303-315
• /
• 1998

In a factorial experiment, certain combinations of factor levels clay not be ruled out for operational or economical reason. A fractional factorial design that contains such infeasible combinations, called debarred combinations, becomes too unbalanced to estimate the required effects. This thesis presents a method of selecting defining contrasts for constructing regular $3^{n-p}$ fractional factorial design which does not contain a debarred combination. Consequently, the construction of the design is accomplished by choosing the defining contrasts so that one of defining contrasts is compatible with a debarred combination.

• Korean Chemical Engineering Research
• /
• v.46 no.4
• /
• pp.756-763
• /
• 2008

The aim of this work was to obtain uniform and well-dispersed spherical silver nanoparticles using statistical design-of-experiment methods. We performed the experiments using 2 k fractional factorial designs with respect to key factors of a general chemical reduction method. The nanoparticles prepared were characterized by SEM, TEM and UV-visible absorbance for particle size, distribution, aggregation and anisotropy. The data obtained were analyzed and optimized using a statistical software, Minitab. The design-of-experiment methods using quantified data enabled us to determine key factors and appreciate interactions between factors. The measured properties of nanoparticles were dominated not only by individual one or two main factors but also by interactions between factors. The appropriate combination of the factors produced small, narrow-distributed and non-aggregated silver nanoparticles of about 30 nm with approximately 10% standard deviation.

• 한국도로학회:학술대회논문집
• /
• 2004.10a
• /
• pp.143-148
• /
• 2004

• Journal of the Korean Society of Tobacco Science
• /
• v.5 no.1
• /
• pp.49-56
• /
• 1983

• Journal of the Korean Statistical Society
• /
• v.9 no.1
• /
• 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
• /
• v.23 no.4
• /
• 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.

• Journal of the Korea Concrete Institute
• /
• v.16 no.2 s.80
• /
• 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.

• Journal of the Korean Society for Precision Engineering
• /
• v.26 no.3
• /
• 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.

• Journal of Korean Society for Quality Management
• /
• v.40 no.1
• /
• 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.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1996.10a
• /
• 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.