• Communications for Statistical Applications and Methods
• /
• 제6권1호
• /
• pp.193-205
• /
• 1999

An approximate Bayes criterion for Behrens-Fisher problem (testing equality of means of two normal populations with unequal variances) is proposed and examined. Development of the criterion involves derivation of approximate Bayes factor using the imaginary training sample approachintroduced by Spiegelhalter and Smith (1982). The proposed criterion is designed to develop a Bayesian test criterion having a closed form, so that it provides an alternative test to those based upon asymptotic sampling theory (such as Welch's t test). For the suggested Bayes criterion, numerical study gives comparisons with a couple of asymptotic classical test criteria.

• Journal of the Korean Statistical Society
• /
• 제28권1호
• /
• pp.107-124
• /
• 1999

An approximate Bayes criterion for multivariate Behrens-Fisher problem is proposed and examined. Development of the criterion involves derivation of approximate Bayes factor using the imaginary training sample approach introduced by Speigelhalter and Smith (1982). The criterion is designed to develop a Bayesian test, so that it provides an alternative test to other tests based upon asymptotic sampling theory (such as the tests suggested by Bennett(1951), James(1954) and Yao(1965). For the derived criterion, numerical studies demonstrate routine application and give comparisons with the classical tests.

• 대한기계학회논문집A
• /
• 제27권6호
• /
• pp.1041-1049
• /
• 2003

In this paper, a new local two-point approximation method which is based on the exponential intervening variable is proposed. This new algorithm, called the Two-Point Convex Approximation(TPCA), use the function and design sensitivity information from the current and previous design points of the sequential approximate optimization to generate a sequence of convex, separable subproblems. This paper describes the derivation of the parameters associated with the approximation and the numerical solution procedure. In order to show the numerical performance of the proposed method, a sequential approximate optimizer is developed and applied to solve several typical design problems. These optimization results are compared with those of other optimizers. Numerical results obtained from the test examples demonstrate the effectiveness of the proposed method.

• Steel and Composite Structures
• /
• 제44권4호
• /
• pp.531-543
• /
• 2022

An exact dynamic analytical method for free vibrations of continuous partial-interaction composite beams is proposed based on the Timoshenko beam theory. The main advantage of this method is that the independent shear deformations and rotary inertia of sub-beams are considered, which is more in line with the reality. Therefore, the accuracy of eigenfrequencies obtained by this method is significantly improved, especially for higher order modes, compared to the existing methods where the rotary angles of both sub-beams are assumed to be equal irrespective of the differences in the shear stiffness of each sub-beam. Furthermore, the solutions obtained by the proposed method are exact owing to no introduction of approximated displacement and force fields in the derivation. In addition, an exact analytical solution for the case of simply supported is obtained. Based on this, an approximate expression for the fundamental frequency of continuous partial-interaction composite beams is also proposed, which is useful for practical engineering applications. Finally, the practicability and effectiveness of the proposed method and the approximate expression are explored using numerical and experimental examples; The influence factors including the interfacial interaction, shear modulus ratio, span-to-depth ratio, and side-to-main span length ratio on the eigenfrequencies are presented and discussed in detail.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2000년도 가을 학술발표회논문집
• /
• pp.369-376
• /
• 2000

For the general loading condition and boundary condition, it is very difficult to obtain closed-form solutions for buckling loads and natural frequencies of thin-walled structures because its behaviour is very complex due to the coupling effect of bending and torsional behaviour. Consequently most of previous finite element formulations introduced approximate displacement fields using shape functions as Hermitian polynomials, isoparametric interpoation function, and so on. The purpose of this study is to calculate the exact displacement field of a thin-walled straight beam element with the non-symmetric cross section and present a consistent derivation of the exact dynamic stiffness matrix. An exact dynamic element stiffness matrix is established from Vlasov's coupled differential equations for a uniform beam element of non-symmetric thin-walled cross section. This numerical technique is accomplished via a generalized linear eigenvalue problem by introducing 14 displacement parameters and a system of linear algebraic equations with complex matrices. The natural frequencies are evaluated for the non-symmetric thin-walled straight beam structure, and the results are compared with available solutions in order to verify validity and accuracy of the proposed procedures.

• 소성∙가공
• /
• 제28권4호
• /
• pp.190-196
• /
• 2019

The capability of accurately predicting the roll force profile across a strip in the bite zone in cold rolling process is vital for the calculation of strip profile. This paper presents a derivation of a precision mathematical model for predicting variations in the roll force across a strip in cold rolling. While the derivation is based on an approximate 3-D theory of rolling, this mathematical model also considers plastic deformation in the pre-deformation region which is located close to the roll entrance before the strip enters the bite zone. Finally, the mathematical model is expressed as a boundary value problem, and it predicts the roll force profile and tension profile in addition to lateral plastic strain profile.

• 한국군사과학기술학회지
• /
• 제5권3호
• /
• pp.23-32
• /
• 2002

We predict the erosion rate of unknown cannon tubes by substituting measured values of the standard cannon, 155㎜ Howitzer M185 and ballistic data for the erosion equation. We know ten measured erosion values of the standard cannon at every 400 rounds. An approximate formula is derived to interpolate six values up to 2,000 rounds. Numerical example is presented and its results are analyzed. The new erosion equation is also suggested. This equation produces more accurate cannon tube erosion rate than the Rauf Imam's empirical approaches. Computer simulations are presented.

• Tribology and Lubricants
• /
• 제25권3호
• /
• pp.171-175
• /
• 2009

One of the critical issues associated with the 40mm long hollow cylinder's development and maintenance is the prediction of cylinder erosion. The actual firing test is the most accurate method to measure the cylinder erosion rate. But it costs a great deal and requires a long measurement time. Hence many empirical methods have been proposed to predict the erosion rate and life span of long hollow cylinders. An EFC formula is calculated. An approximate erosion formula for the ammunition type A is derived to interpolate 16 observation values up to 4,000 rounds. A new erosion equation and muzzle velocity formula are also suggested. Several numerical results are presented.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 1992년도 가을 학술발표회 논문집
• /
• pp.29-38
• /
• 1992

Approximate Constant Shear Angle Theory is usually used to take a transversal shear deformation of thick plate into consideration, which cannot be effectively considered the influence of transversal warping of cross-section with an increase of thickness. It right be the best way to represent the exact warping of cross-section. In this study, the derivation of warping function is attempted, and the effect of shear deformation and transversal warping is to be considered through the nolinear analysis of plate.

• 한국수학교육학회지시리즈B:순수및응용수학
• /
• 제22권4호
• /
• pp.389-401
• /
• 2015

We will show the general solution of the functional equation f(x + ay) + f(x − ay) + 2(a² − 1)f(x) = a²f(x + y) + a²f(x − y) + 2a²(a² − 1)f(y) and investigate the stability of quartic Lie *-derivations associated with the given functional equation.