• 품질경영학회지
• /
• 제23권2호
• /
• pp.91-102
• /
• 1995

For two independent random variables X and Y, the functional R=Pr[X>Y] is of practical importance in reliability. X can be interpreted as the strength of a component subjected to a stress Y, and R is the component's reliability. In this paper nonparametric approach to estimation of R based on censored observations in the strength variables is analyzed and compared by simulations in the moderate sample sizes.

• Journal of Welding and Joining
• /
• 제6권4호
• /
• pp.54-62
• /
• 1988

Major problems in welding Al-7020 include shrinkage, rpopositgy in welds and loss of strength in the heat affected zone. Thus it is important to examine the mechanical properties and reliability of welds. In this study, a series of experiments was carried out to determine the mechanical properties such as micro-hardness distribution, tensile strength, porosity and residual stress distribution of the Al-7020 weldment made by pulse-GMA welding. The resuts of the experiemnts are as folows. 1) The micro-hardness of weld metal and heat affected zone was lower than that of the base metal. 2) The tensile strength of the deposited metal was much lower than that of the base metal. 3) The porrosity in weld metal zone was negligible under the adopted conditsion of experiemnts. 4) The residual stress in the weld metal was lower than that of the heat affected zone, because the weld metal was softened. And the mciro-hardness distribution, the tensile strength and the residual stess distribution of the weldment in the as-welded condition were compared with those of the weldment after heat treatment.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2010년도 춘계학술대회 논문집
• /
• pp.621-626
• /
• 2010

According to development of method and device of Finite Element Analysis, the strength of welded joint is demonstrated by Finite Element Analysis not classical calculations. On the FEA, all of the joints for carbody are assumed to be ideal connections and the yield stress of welded joint is assumed to be the same to base metal. On these assumption, FEA is appropriate to evaluate the overall stability and strength of whole carbody. The classical calculation is appropriate to evaluate strength of specific welded joint and to determine the weld method and properties. Some project request strength calculation of the specific welded joints in addition to FEA, because of the demonstration of stability. The objective of this paper is the check of the consistency of the FEA result for the welded joints by the stress comparison between Detailed FE Model and classical calculation and the evaluation of the reliability of FEA result.

• Smart Structures and Systems
• /
• 제14권4호
• /
• pp.559-567
• /
• 2014

The model of unit dynamic reliability of repairable k/n (G) system with unit strength degradation under repeated random shocks has been developed according to the stress-strength interference theory. The unit failure number is obtained based on the unit failure probability which can be computed from the unit dynamic reliability. Then, the transfer probability function of the repairable k/n (G) system is given by its Markov property. Once the transfer probability function has been obtained, the probability density matrix and the steady-state probabilities of the system can be retrieved. Finally, the dynamic reliability of the repairable k/n (G) system is obtained by solving the differential equations. It is illustrated that the proposed method is practicable, feasible and gives reasonable prediction which conforms to the engineering practice.

• Journal of the Korean Data and Information Science Society
• /
• 제11권1호
• /
• pp.127-137
• /
• 2000

In this paper, we consider hierarchical Bayesian analysis for P(Y < X) using Gibbs sampler, where X and Y are independent normal distributions with unknown means and variances, respectively. Also numerical study using real data is provided.

• 한국산업정보학회:학술대회논문집
• /
• 한국산업정보학회 1999년도 춘계학술대회 발표논문집
• /
• pp.191-197
• /
• 1999

In this paper, we develop noninformative priors that are used for estimating the reliability of stress-strength system under the Burr-type X distribution. A class of priors is found by matching the coverage probabilities of one-sided Bayesian credible interval with the corresponding frequentist coverage probabilities. It turns out that the reference prior is a first order matching prior. The propriety of posterior under matching prior is provided. The frequentist coverage probabilities are given for small samples.

• 소성∙가공
• /
• 제7권6호
• /
• pp.530-538
• /
• 1998

Elimination of the heat treatment process is very important in automation of metal forming since controlling heat treatment by computer has many difficulties and it has bottle neck problem. non-heat-treated steels materials which are not in need of heat treatment have been developed for cold forging. However to apply non-heat-treated steel to structural parts. it is necessary to prove reliability of mechanical properties. In order to define the reliability of mechanical properties we have investigated microstructure, hardness, the tensile strength compressive strength and tensile fatigue strength for both steels. Considering the results of high cycle fatigue test for both specimen the characteristics of non-heat-treated steel are decided on the yield strength, It has same tendency for heat-treated steel. Therefore non-heat-treated steel which has the appropriate yield strength may be applied in cold forging.

• 품질경영학회지
• /
• 제22권2호
• /
• pp.69-78
• /
• 1994

We obtain the Bayes estimator(BE), the minimum variance unbiased estimator(MVUE) and maximun likelihood estimator(MLE) of the reliability when the distribution of the stress and the strength are Weibull with known shape parameters. The experiment is terminated before all of the items on the test have failed and the failed items are partially replaced. Performance of the three estimators for moderate size samples are compared through Monte Carlo simulation.

• Advances in concrete construction
• /
• 제3권3호
• /
• pp.161-185
• /
• 2015

FRP confining is a widely used method for seismic retrofitting of concrete columns. Several studies investigated the stress-strain behavior of FRP confined concrete prisms with square and rectangular sections both experimentally and analytically. In some studies, the monotonic stress-strain behavior of confined concrete was investigated and compressive strength models were developed. To study the reliability of these models, thorough statistical tests are required. This paper aims to investigate the reliability of the presented models using statistical tests including t-test, wilcoxon rank sum test, wilcoxon signed rank test and sign test with a level of significance of 5%. Wilk Shapiro test was also employed to evaluate the normality of the data distribution. The results were compared for different cross section and confinement types. To see the accuracy of the models when there were no significant differences between the results, the coefficient of confidence was used.

• 한국정밀공학회지
• /
• 제14권5호
• /
• pp.128-133
• /
• 1997

Due to their high strength and good wear resistance, nitro-carburizing materials have been used for many machine components. However, the nitro-carburizing materials are found to have one disadvantage ; that is, their strength and fatigue life show larger scatter than those of non-heated metals. In this paper, therfore, the statistical chracteristics of non-heated and nitro-carburized specimens for SCM415 are investi- gated under two different of stress levels 1.15 .sigma. /sub .omega. / .leq. / .sigma. / sub .alpha. / .leq. / 1.25 .sigma. /sub .omega. /. Seven specimens at each stress level are tested by using rotating bending fatigue tester. The relation between a crack length and fatigue cycles can be arranged for Weibull distribution, and S-N curve using 95% reliability function is obtalined for nitro-carburized specimen.