• Journal of the Korean Data and Information Science Society
• /
• v.15 no.4
• /
• pp.935-943
• /
• 2004

Most of the accelerated life tests deal with tests that use only one accelerating variable and no other explanatory variables. Frequently, however, there is a test to use more than one accelerating or other experimental variables, such as, for examples, a test of capacitors at higher than usual conditions of temperature and voltage, a test of circuit boards at higher than usual conditions of temperature, humidity and voltage. A accelerated life test is extended to M-level stress accelerated life test with k-stress variables. The optimal design for Weibull distribution is studied with k-stress variables.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.1
• /
• pp.281-288
• /
• 2015

In this paper, the maximum likelihood estimators and confidence intervals for parameters of Weibull distribution are derived under three level constant stress accelerated life tests and the assumption that a log quadratic relationship exits between stress and the scale parameter ${\theta}$. The compound linear plan proposed by Kim (2006) is used to allocate the test units at each stress level, which performed nearly as good as the optimum quadratic plan and had the advantage of simplicity. Some simulation studies are given.

• Journal of the Korean Statistical Society
• /
• v.35 no.3
• /
• pp.225-238
• /
• 2006

This paper considers noninformative priors for the scale parameter of exponential distribution when the data are collected in step stress accelerated life tests. We find the Jeffreys' and reference priors for this model and show that the reference prior satisfies first order matching criterion. Also, we show that there exists no second order matching prior in this problem. Some simulation results are given and we perform Bayesian analysis for proposed priors using some data.

• Journal of Korean Society for Quality Management
• /
• v.23 no.1
• /
• pp.41-49
• /
• 1995

This paper suggests optimal accelerated constant stress life tests in Exponential distribution. The relationship between the log-mean life and the loaded stress is assumed to be linear. Optimal plans considering mean square errors of maximum likelihood estimators of the log mean life and test costs are obtained. We consider accelerated life tests with two stress levels, and as data types, failure censoring( type II) and time censoring(type I) data are used. We propose the procedure to obtain the optimal plans for each case. Some examples are also included.

• Proceedings of the Korean Reliability Society Conference
• /
• 2005.06a
• /
• pp.75-82
• /
• 2005

In this paper, accelerated life testing(ALT) method and procedures for a are developed and applied to assess the reliability of the product. Relay is a device that can open and close the electric circuit electrically and is used for protecting and controlling the load. In this study, an accelerated life test method for predicting the mechanical life of a relay is developed using the relationship between stresses, failure mechanism and life characteristics of products. Using the ALT method, we performed life tests and analyzed the tests results. The proposed method and procedures may de extended and applied to testing similar kinds of products to reduce test times and costs of the tests remarkably.

• Journal of Applied Reliability
• /
• v.9 no.2
• /
• pp.71-80
• /
• 2009

This paper discusses the service life prediction methods for CFRP bar for concrete reinforcement using accelerated degradation tests. The relationship between performance degradation and the rate of a failure-causing chemical reaction is assumed for the temperature accelerated degradation tests. Methods of obtaining acceleration factors and predicting service life of the CFRP bar using the degradation model are presented.

• Journal of Applied Reliability
• /
• v.4 no.1
• /
• pp.1-14
• /
• 2004

Accelerated life test models and procedures are developed to assess the reliability of typical power relays. The main function of relays is to control high voltage circuits by operating low voltage circuits. The accelerated life test method and test equipments are developed using the relationship between stresses and life characteristics of the products. Using the developed accelerated life test method, the parameters of the ALT model and lifetime distribution are estimated and the reliability of the relays at use condition is assessed. The proposed accelerated life test method and procedure may be extended and applied to testing similar kinds of products to reduce test time and costs of the tests remarkably.

• Journal of Applied Reliability
• /
• v.3 no.2
• /
• pp.103-116
• /
• 2003

We carry out reliability tests and investigate the failure mechanisms. of the wafer level vacuum packaged MEMS gyroscope sensor using an accelerated degradation test. The accelerated degradation test (ADT) is used to evaluate reliability (and/or life) of the MEMS vacuum package and to select the accelerated test conditions, which reduce the reliability testing time. Using the failure distribution model and stress-life model, we are able to estimate the average life time of the vacuum package, which is well agreed with the measured data. After improving several package reliability issues such as prevention of gas diffusion through package, we carry out another set of accelerated tests at the chosen acceleration level. The results show that reliability of the vacuum packaged gyroscope has been greatly improved and can survive without degradation of performance, which is the Q-factor in gyroscope sensor, during environmental stress reliability tests.

• Journal of Korean Society for Quality Management
• /
• v.31 no.4
• /
• pp.194-202
• /
• 2003

In this paper, we propose goodness of fit test statistics for exponentiality in accelerated life tests data based on Kullback­Leibler information functions. This acceleration model is assumed to be a tampered random variable model. The procedure is applicable when the exponential parameter using the data from accelerated life tests is or is not specified under null hypothesis. And we compare the power of the proposed test statistics with Kolmogorov­Smirnov, Cramer von Mises and Anderson­Darling statistics in the small sample.

• Proceedings of the Safety Management and Science Conference
• /
• 2004.11a
• /
• pp.229-235
• /
• 2004

This paper treats accelerated life tests for automotive connector. The contact resistance of connector is explained by some factors; the use time(calender time, real cycle), stresses and loads adapted in auto test. The relationships between contact resistance and some factors are compared and analyzed by regression models in various test conditions; field use-environment, manufacturer's test environment, and accelerated test condition. The consistency between of manufacturer's test and field test is examined. Finally, the future study on accelerated test for automotive connector is presented.