Abstract: Reliability of long-term storage products is related to
the availability of the whole system, and the evaluation of storage life
is of great necessity. These products are usually highly reliable and
little failure information can be collected. In this paper, an analytical
method based on data from accelerated storage life test is proposed to
evaluate the reliability index of the long-term storage products. Firstly,
singularities are eliminated by data normalization and residual
analysis. Secondly, with the preprocessed data, the degradation path
model is built to obtain the pseudo life values. Then by life distribution
hypothesis, we can get the estimator of parameters in high stress levels
and verify failure mechanism consistency. Finally, the life distribution
under the normal stress level is extrapolated via the acceleration model
and evaluation of the actual average life is available. An application
example with the camera stabilization device is provided to illustrate
the methodology we proposed.
Abstract: This paper discusses the effects of using progressive Type-I right censoring on the design of the Simple Step Accelerated Life testing using Bayesian approach for Weibull life products under the assumption of cumulative exposure model. The optimization criterion used in this paper is to minimize the expected pre-posterior variance of the Pth percentile time of failures. The model variables are the stress changing time and the stress value for the first step. A comparison between the conventional and the progressive Type-I right censoring is provided. The results have shown that the progressive Type-I right censoring reduces the cost of testing on the expense of the test precision when the sample size is small. Moreover, the results have shown that using strong priors or large sample size reduces the sensitivity of the test precision to the censoring proportion. Hence, the progressive Type-I right censoring is recommended in these cases as progressive Type-I right censoring reduces the cost of the test and doesn't affect the precision of the test a lot. Moreover, the results have shown that using direct or indirect priors affects the precision of the test.
Abstract: This paper tries to represent a new method for
computing the reliability of a system which is arranged in series or
parallel model. In this method we estimate life distribution function
of whole structure using the asymptotic Extreme Value (EV)
distribution of Type I, or Gumbel theory. We use EV distribution in
minimal mode, for estimate the life distribution function of series
structure and maximal mode for parallel system. All parameters also
are estimated by Moments method. Reliability function and failure
(hazard) rate and p-th percentile point of each function are
determined. Other important indexes such as Mean Time to Failure
(MTTF), Mean Time to repair (MTTR), for non-repairable and
renewal systems in both of series and parallel structure will be
computed.