• Journal of Applied Reliability
• /
• v.14 no.1
• /
• pp.21-28
• /
• 2014

This paper presents an accelerated life test to estimate the lifetime of thermoelectric module for home water purifier. Clamping force and thermal cycle are selected as accelerating variables through the technical review about failure mechanism. It is assumed that its lifetime follows weibull distribution. The relationship, acceleration factor, and BP life at design condition are estimated by analyzing the accelerated life test data.

• Communications for Statistical Applications and Methods
• /
• v.21 no.4
• /
• pp.285-296
• /
• 2014

The quantile residual life function has been effectively used to interpret results from the analysis of the proportional hazards model for censored survival data; however, the quantile residual life function is not always estimable with currently available semi-parametric regression methods in the presence of heavy censoring. A parametric regression approach may circumvent the difficulty of heavy censoring, but parametric assumptions on a baseline hazard function can cause a potential bias. This article proposes a Bayesian semi-parametric regression approach for inference on an unknown baseline hazard function while adjusting for available covariates. We consider a model-based approach but the proposed method does not suffer from strong parametric assumptions, enjoying a closed-form specification of the parametric regression approach without sacrificing the flexibility of the semi-parametric regression approach. The proposed method is applied to simulated data and heavily censored survival data to estimate various quantile residual lifetimes and adjust for important prognostic factors.

• Journal of Korean Society for Quality Management
• /
• v.34 no.3
• /
• pp.19-30
• /
• 2006

For highly reliable products, it is difficult to assess the lifetime of the products with traditional life tests. Accordingly, a recent approach is to observe the performance degradation of product during the test rather than regular failure time. This study compares performances of three methods(i.e. the approximation, analytical and numerical methods) to estimate the parameters and quantiles of the lifetime when the time-to-failure distribution follows Weibull and lognormal distributions under a random coefficient degradation rate model. Numerical experiments are also conducted to investigate the effects of model error such as measurements in a random coefficient model.

• Communications for Statistical Applications and Methods
• /
• v.24 no.4
• /
• pp.397-419
• /
• 2017

A four-parameter extended fatigue lifetime model called the odd Birnbaum-Saunders geometric distribution is proposed. This model extends the odd Birnbaum-Saunders and Birnbaum-Saunders distributions. We derive some properties of the new distribution that include expressions for the ordinary moments and generating and quantile functions. The method of maximum likelihood and a Bayesian approach are adopted to estimate the model parameters; in addition, various simulations are performed for different parameter settings and sample sizes. We propose two new models with a cure rate called the odd Birnbaum-Saunders mixture and odd Birnbaum-Saunders geometric models by assuming that the number of competing causes for the event of interest has a geometric distribution. The applicability of the new models are illustrated by means of ethylene data and melanoma data with cure fraction.

• Proceedings of the Korean Reliability Society Conference
• /
• 2004.07a
• /
• pp.129-137
• /
• 2004

This paper presents an accelerated life test for burnout of tungsten filament of incandescent lamp. From failure analyses of field samples, it is shown that their root causes are local heating or hot sports in the filament caused by tungsten evaporation and wire sag. Finite element analysis is performed to evaluate the effect of vibration and impact for burnout, but any points of stress concentration or structural weakness are not found in the sample. To estimate the burnout life of lamp, an accelerated life test is planned by using quality function deployment and fractional factorial design, where voltage, vibration, and temperature are selected as accelerating variables. We assumed that Weibull lifetime distribution and a generalized linear model of life-stress relationship hold through goodness of fit test and test for common shape parameter of the distribution. Using accelerated life testing software, we estimated the common shape parameter of Weibull distribution, life-stress relationship, and accelerating factor.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.2
• /
• pp.308-313
• /
• 2009

This paper presents a reliability analysis of S-bonds for AF track circuits, which detect train movement and transmit a speed control signal to the train. Field survey shows that S-bonds are exposed to very large vibrations transferred from rail, and suffer from frequent failures when they were installed on ballasted track. We collected the time-to-failure data of S-bonds from the maintenance field of Seoul metro line 2, and made a parametric approach to estimate the statistical distribution that fits the time-to-failure data. The analysis shows that S-bonds have time-to-failure characteristics described by Weibull distribution. The estimated shape parameter of Weibull distribution is 1.1, which means the distribution has constant failure rate characteristics like exponential distribution. The reliability function, hazard function, percentiles and mean lifetime are derived for maintenance support.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 1999.05a
• /
• pp.222-225
• /
• 1999

Degradation diagnosis of XLPE insulated URD cables was accomplished through out new method. which was to be analyzed non-electrical experiments and synthesized by degradation points. To supplement this method, it was also carried out using several electrical analyses. Breakdown voltages were measured and breakdown lifetimes were Predicted appling for Weibull distribution function. As a result, breakdown lifetime in failure cables was shorted up to 1/3 times than that in general cables. It was very available to estimate cable degradation using above method, but it needs further study on XLPE insulated URD cables in order to improve reliability.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.36 no.3
• /
• pp.1-7
• /
• 2013

This paper is a case study of reliability assessment with field warranty data of Clutch Master Cylinder (CMC) in hydraulic clutch system. We estimate lifetime distribution using field warranty data which contain much useful information for understanding reliability of the system in the real-world environments. However, the estimated parameters are far from existing reference values, which seems to be caused right censored field warranty data. To modify the parameters, we use the information of the durability test which is performed to verify that the lifetime of the item meets the required level. After that, we can observe that the modified parameters are closer to the existing reference values. This case study shows a possible idea to supplement lack of right censored field warranty data and its applicability.

• Journal of the Korean Data Analysis Society
• /
• v.20 no.6
• /
• pp.2747-2757
• /
• 2018

We consider the MLE (maximum likelihood estimate) and Bayesian estimates of three-parameter bathtub-shaped lifetime distribution based on the progressive type II censoring with binomial removal. Jung, Chung (2018) proposed the three-parameter bathtub-shaped distribution which is the extension of the two-parameter bathtub-shaped distribution given by Zhang (2004). Jung, Chung (2018) investigated its properties and estimations. The maximum likelihood estimates are computed using Newton-Raphson algorithm. Also, Bayesian estimates are obtained under the balanced loss function using MCMC (Markov chain Monte Carlo) method. In particular, BSEL (balanced squared error loss) function is considered as a special form of balanced loss function given by Zellner (1994). For comparing theirs MLEs with the corresponding Bayes estimates, some simulations are performed. It shows that Bayes estimates is better than MLEs in terms of risks. Finally, concluding remarks are mentioned.

• The Journal of the Korea Contents Association
• /
• v.11 no.4
• /
• pp.244-252
• /
• 2011

This study was to estimate the radiation dose associated with 64-slice multidetector CT(MDCT) in clinical practice and quantify the potential cancer risk associated with these examinations. Lifetime attributable risks(LAR) were estimated with models developed in the national Academies' Biological Effects of Ionizing Radiation VII report. Mean effective dose were 1.48mSv in Brain axial scan, 7.66mSv in chest routine contrast, 12.17mSv in coronary angiogram, 24.52mSv in Dynamic abdomen scan. LAR estimates for brain routine varied from 1 in 7463 for man to 1 in 4926 for women. In chest routine with contrast, LAR varied from 1 in 1449 for men to 1 in 952. LAR of Abdomen dynamic CT varied from 1 in 453 for men to 1 in 298 for women. So, 64-slice MDCT scan is associated with non-negligible LAR of cancer. Doses can be reduced by careful attention to scanning protocol.