• Communications for Statistical Applications and Methods
• /
• v.24 no.2
• /
• pp.129-142
• /
• 2017

In this paper we consider the problem of the model selection/discrimination among three different positively skewed lifetime distributions. Lindley, Weibull, and gamma distributions have been used to effectively analyze positively skewed lifetime data. This paper assesses how much closer the Lindley distribution gets to Weibull and gamma distributions. We consider three techniques that involve the likelihood ratio test, asymptotic likelihood ratio test, and minimum Kolmogorov distance as optimality criteria to diagnose the appropriate fitting model among the three distributions for a given data set. Monte Carlo simulation study is performed for computing the probability of correct selection based on the considered optimality criteria among these families of distributions for various choices of sample sizes and shape parameters. It is observed that overall, the Lindley distribution is closer to Weibull distribution in the sense of likelihood ratio and Kolmogorov criteria. A real data set is presented and analyzed for illustrative purposes.

• Proceedings of the Korea Concrete Institute Conference
• /
• 1996.10a
• /
• pp.440-446
• /
• 1996

In this study, a procedure for the economic design of reinforced concrete beams under several design constraints is outlined on the basis of discretized continuum-type optimality criteria (DCOC). The costs to be minimized involve those of concrete, reinforcing steel and formwork. The design constraints include limits on the maximum deflection in a given span, on bending and shear strengths, in addition to upper and lower bounds on design variables. An explicit mathematical derivation of optimality criteria is given based on the well known Kuhn-Tucker mecessary conditions, followed by an iterative procedure for designs when the design variables are the depth and the steel ratio. Self-weight of the spans is also included in the equilibrium equation of the real system and in the optimatlity criteria.

• The Korean Journal of Applied Statistics
• /
• v.13 no.2
• /
• pp.393-405
• /
• 2000

Box and Draper( 19(5) listed some properties of a design that should be considered in design selection. But it is impossible that one design criterion from optimal experimental design theory reflects many potential objectives of an experiment, because the theory was originally based on the underlying model and its strict assumption about the error structure. Therefore, when it is neces::;ary to implement multi-objective experimental design. it is common practice to balance out the several optimal design criteria so that each design criterion involved benefits in terms of its relative "high" efficiency. In this study, we proposed several composite design criteria taking the case of heteroscedastic model. WVhen the heteroscedasticity is present in the model. the well known equivalence theorem between 1)- and C-optimality no longer exists and furthermore their design characteristics are sometimes drastically different. We introduced three different design criteria for this purpose: constrained design, combined design, and minimax design criteria. While the first two methods do reflect the prior belief of experimenter, the last one does not take it into account. which is sometimes desirable. Also we extended this method to the case when there are uncertainties concerning the error structure in the model. A simple algorithm and concluslOn follow.On follow.

• The Korean Journal of Applied Statistics
• /
• v.28 no.3
• /
• pp.561-571
• /
• 2015

When we consider an optimal design to predict the response corresponding to the point outside the design region, we are extremely careful about choosing the design criteria for selecting the support points. The assumed model and its accompanying error structure should be assumed to extend beyond the design region for the selected design criteria to be valid. Thus, we modify the existing design criteria such as extrapolation-optimality to be suited to those situations. We propose some maximin approaches in this paper. Simple and quadratic regression models are tested to find the basic characteristics of such maximin approaches. Some main findings are discussed in the conclusion.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2000.04b
• /
• pp.379-388
• /
• 2000

This paper describes the application of discretized continuum-type optimality criteria (DCOC) for design of the reinforced concrete T-beams. The cost of construction as objective function which includes the costs of concrete, reinforced steel and formwork is minimized. The design constraints include limits on the maximum deflection in a given span on bending and shear strengths and optimality criteria is given based on the well blown Kuhn-Tucker necessary conditions, followed by an iterative procedure for designs when the design variables are the depth and the steel ratio. The versatility of the DCOC technique has been demonstrated by considering numerical examples which have one and five span RC T-beams.

• Proceedings of the KSME Conference
• /
• 2001.06c
• /
• pp.392-397
• /
• 2001

Topology optimization is applied to determine the layout of a structure whose eigenfrequency coincides with a specified frequency. The topology optimization problem is formulated to minimize the difference between the structural frequency and a given frequency using the homogenization method and the modified optimality criteria method. It turns out that the value of a weighting factor in the updating scheme plays an important role to achieve both a suitable speed and a stable convergence of an algorithm. Unlike a constant weighting factor in previous works, it is suggested that a weight factor is varied during the iteration to control the amount of the frequency change. To substantiate the proposed approach two-dimensional structural design problems are presented and the resulted topology layouts for the specified eigenfrequency are compared to layouts for maximizing the corresponding eigenfrequency.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1996.10a
• /
• pp.288-295
• /
• 1996

This work presents an optimality criteria method applicable io the design of plane frames with I-shape sections. All kinds of constraints are treated properly to ensure the mathematical rigour of the method as ever. Among the various properties of a section, the cross-sectional area is chosen as the design variable associated with the member. Then other properties, moment of inertia and depth, are determined from the cross-sectional area using relationships established in advance from the sectional data for AISC standard W shapes. The optimality criteria established in this work is perfect in mathematical terms provided that the relationships between properties of a section are correct. A redesign algorithm is derived relying heavily on the Newton-Raphson method to solve the system of nonlinear constraint equations. A worked example is also Presented.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2000.04a
• /
• pp.485-490
• /
• 2000

This paper describes the application of discretized continuum-type optimality criteria (DCOC) for minimum-cost design of the reinforced concrete frame structures consisting of beams and columns. The cost of construction as objective function which includes the costs of concrete, reinforced steel and formwork is minimized. The design constraints include limits on the maximum deflection at a prescribed node, bending and shear strengths in beams, uniaxial bending strength of columns according to design codes(CEB/FIP, 1990). In the first stage, only beams with uniform cross-sectional parameters per span are considered. But the steel ratio is allowed to vary freely. The cross-sectional parameters and steel ratio in each column are assumed to be uniform for practical reasons. Optimality criteria is given based on the well known Kuhn-Tucker necessary conditions, followed by an iterative procedure for designs when the design variables are the depth and the steel ratio. The versatility of the DCOC technique has been demonstrated by considering numerical examples which have one-bay four-storey frame.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.12 no.5
• /
• pp.85-93
• /
• 2004

Electric vehicle body has to be subjected to uniform load and requires auxiliary equipment such as air pipe and electric wire pipe. Especially, the cross beam supports the weight of passenger and electrical equipments. This need to use adaptive design in initial design stage to gain economy through interchangeability between many kinds of components. This study performs the topology optimization by the concept of homogenization based on optimality criteria method which is efficient for the problem with a number of boundary condition and design variable. Therefore this provides the method to determine the optimum position and the shape of circular hole in the cross beam and then can achieve the weight minimization of electric vehicle body.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2001.10a
• /
• pp.183-190
• /
• 2001

Topology optimization. has been evolved into a very efficient conceptual design tool and has been utilized into design engineering processes in many industrial parts. In recent years, topology optimization has become the focus of structural optimization design and has been researched and widely applied both in academy and industry. Traditional topology optimization has been using homogenization method and optimality criteria method. Homogenization method provides relationship equation between structure which includes many holes and stiffness matrix in FEM. Optimality criteria method is used to update design variables while maintaining that volume fraction is uniform. Traditional topology optimization has advantage of good convergence but has disadvantage of too much convergency time and additive checkerboard prevention algorithm is needed. In one way to solve this problem, element remove method is presented. Then, it is applied to many examples. From the results, it is verified that the time of convergence is very improved and optimal designed results is obtained very similar to the results of traditional topology using 8 nodes per element.