• 한국기계가공학회지
• /
• 제19권6호
• /
• pp.67-72
• /
• 2020

Life tests are essential in reducing the catastrophic damage caused by the accidents of large machinery such as aircraft and ships. However, life tests are challenging to implement due to the high costs and time required to test the life of large machinery parts. Therefore, it is advantageous and convenient to apply accelerated life test techniques for key components to reduce costs and time. In fact, extensive research has already been conducted on these techniques. However, recently, there have been cases in which an experimental value was applied to the shape parameter of the Weibull distribution used in the reliability test, but the test time was not significantly reduced. Therefore, in this paper, the shape parameters are estimated from the probability density function of the Weibull distribution for the analysis of an accelerated life test for bladder accumulators, which are core components of military helicopters. The test time was derived based on the number of samples and confidence level by substituting it into the test time equation. Next, the accelerated life test time was calculated using the steady-state test time with an acceleration factor obtained from the Arrhenius model. The steady-state life test required approximately 15,000 H, whereas the accelerated life test time for one sample at 100 ℃ was 34% shorter than that of the steady-state life test.

• Communications for Statistical Applications and Methods
• /
• 제19권6호
• /
• pp.837-847
• /
• 2012

Inverse Gaussian distribution is widely used in applications to analyze and model right-skewed data. To assess the appropriateness of the distribution prior to data analysis, Mudholkar and Tian (2002) proposed an entropy-based test of fit. The test is based on the entropy power fraction(EPF) index suggested by Gokhale (1983). The simulation results report that the power of the entropy-based test is superior compared to other goodness-of-fit tests; however, this observation is based on the small-scale simulation results on the standard exponential, Weibull W(1; 2) and lognormal LN(0:5; 1) distributions. A large-scale simulation should be performed against various alternative distributions to evaluate the power of the entropy-based test; however, the use of a theoretical method is more effective to investigate the powers. In this paper, utilizing the information discrimination(ID) index defined by Ehsan et al. (1995) as a mathematical tool, we scrutinize the power of the entropy-based test. The selected alternative distributions are the gamma, Weibull and lognormal distributions, which are widely used in data analysis as an alternative to inverse Gaussian distribution. The study results are provided and an illustrative example is analyzed.

• Journal of Forest and Environmental Science
• /
• 제34권6호
• /
• pp.451-456
• /
• 2018

The use of single component distribution to describe the irregular stand structure of degraded forest often lead to bias. Such biasness can be overcome by the application of finite mixture distribution. Therefore, in this study, finite mixture distribution was used to characterise the irregular stand structure of the Gmelina arborea plantation in Omo forest reserve. Thirty plots, ten each from the three stands established in 1984, 1990 and 2005 were used. The data were pooled per stand and fitted. Four finite mixture distributions including normal mixture, lognormal mixture, gamma mixture and Weibull mixture were considered. The method of maximum likelihood was used to fit the finite mixture distributions to the data. Model assessment was based on negative loglikelihood value ($-{\Lambda}{\Lambda}$), Akaike information criterion (AIC), Bayesian information criterion (BIC) and root mean square error (RMSE). The results showed that the mixture distributions provide accurate and precise characterisation of the irregular diameter distribution of the degraded Gmelina arborea stands. The $-{\Lambda}{\Lambda}$, AIC, BIC and RMSE values ranged from -715.233 to -348.375, 703.926 to 1433.588, 718.598 to 1451.334 and 3.003 to 7.492, respectively. Their performances were relatively the same. This approach can be used to describe other irregular forest stand structures, especially the multi-species forest.

• Transactions on Electrical and Electronic Materials
• /
• 제7권5호
• /
• pp.217-223
• /
• 2006

When only partial information is available about equipment failures (installation date and amount, as well as failure and replacement rates), data on sufficiently large number of yearly populations of the components can be combined, and estimation of model parameters may be possible. The parametric models may then be used for forecasting of the system's short term future failure and for formulation of replacement strategies. We employ the Weibull distribution and show how we estimate its parameters from past failure data. Using Monte Carlo simulations, it is possible to assess confidence ranges of the forecasted component performance data.

• 한국군사과학기술학회지
• /
• 제21권5호
• /
• pp.599-606
• /
• 2018

Failure data of systems in many field can be erroneous, which influences the reliability analysis of the systems. The general form of failure data is right censored data with accurate time information. But due to its nature of data collection in the military field, failure time of one-shot weapon systems can have errors which are related to the maintenance period. So this paper suggests a model that can reduce the error by utilizing interval censored data as an alternative to right censored data in weibull distribution.

• 대한안전경영과학회:학술대회논문집
• /
• 대한안전경영과학회 2006년도 춘계공동학술대회
• /
• pp.411-419
• /
• 2006

This paper aims at designing an accelerated life test sampling plan for bulk material and showing its application for an arc-welded gas pipe. It is an integrated model of the accelerated life test procedure and bulk sampling procedure. The accelerated life tests were performed by the regulation, RSD 0005 of ATS at KITECH and bulk sampling was used for acceptance. Design parameters might be total sample size(segments and increments), stress level and so on. We focus on deciding the sample size by minimizing the asymptotic variance of test statistic as well as satisfying consumer's risk under Weibull life time distribution with primary information on shape parameter.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 추계학술대회 논문집 전기물성,응용부문
• /
• pp.178-181
• /
• 2003

For many years, testing laboratories, research institutes and manufactures try to find a reliable water tree accelerated ageing test that is able to show whether a polymer Medium Voltage cable os susceptible to water treeing or not. Test on laboratory samples, model cable designs, and fell size cable are presented Apart form aging, another important aspect of any accelerated aging test is the right choice of th preconditioning method. This paper is the analysis of weibull distribution method after an accelerated aging test of MV(Medium Voltage) cable.

• 한국신뢰성학회:학술대회논문집
• /
• 한국신뢰성학회 2000년도 추계학술대회
• /
• pp.329-333
• /
• 2000

Delay time analysis is a pragmatic mathematical concept readily embraced by engineers which has been developed as a means to model maintenance decision problem. This paper considers an inspection period using delay time analysis for fishing vessel equipment. We assume that delay time distribution is Weibull and inspections are perfect. In this paper, we determine the optimal inspection period which minimize the expected downtime per unit time.

• 한국공작기계학회논문집
• /
• 제15권2호
• /
• pp.16-23
• /
• 2006

Recently the design of multi-stage gear drive is being highly concerned. Until now, since the researches of gear drive are focused on the design for satisfying safety factor, the reliability evaluation of multi-stage gear drive is not included. In this paper, the life and reliability models of multi-stage gear drive are proposed using methods of probability and statistics. The life and reliability of the multi-stage gear drive have been evaluated, which is based on the life and reliability of each stage gear drive. The pinion and gear lives of each stage are calculated using the Lundberg-Palmgren theory and the Weibull failure distribution. These lives are combined using methods of probability and statistics to produce a life and reliability model of multi-stage gear drive.

• 한국통신학회논문지
• /
• 제19권8호
• /
• pp.1446-1452
• /
• 1994

본 논문은 일반적으로 채택하고 있는 소자(device)의 수명분포인 와이블(Weibull) 분포를 적용하여 소자의 가속(accelerated) 수명 테스트에서 얻은 데이터, 즉 소자의 고정 시간을 이용하여 소자의 수명을 예측(prediction)하는데 필요한 보수(parameter)들을 추정 하는데 베이지안(Bayesian) 추정법을 이용하였다. 베이지안 추정법에서 모수를 추정하기 위해서는 사전정보가 있어야 하는데 본 논문에서는 사전정보 없이 현재의 정보만을 이용하여 모수를 추정하는 방법을 제안하였다. 스트레스가 온도인 경우, Arrhenius 모델을 적용하여 소자의 정상동작 상태에서의 수명을 예측 하는데 선형 추정을 하였다.