Acceptance sampling plans based on failure‐censored step‐stress accelerated tests for Weibull distributions

Abstract

PurposeThe paper aims to present acceptance sampling plans based on failure‐censored step‐stress accelerated life tests for items having Weibull lives.Design/methodology/approachThe model parameters are estimated by the method of maximum likelihood. Based on asymptotic distribution theory, the sample size and the acceptability constant are determined satisfying the producer's and consumer's risks. The step‐stress accelerated life test is optimized to have a minimum sample size by minimizing the asymptotic variance of test statistic. Two modes of step‐stress accelerated life test are considered, and a comparison between them is made. The proposed sampling plans are compared with the sampling plans based on constant stress accelerated life tests.FindingsAsymptotic variance is a dominating factor in determining the sample size required for a sampling plan to determine the acceptability of a lot. The sample size is minimized by optimally designing a step‐stress accelerated life test so that the asymptotic variance is minimized.Originality/valueThe sampling plans presented in this paper are particularly useful when items to be tested are so reliable and are useful to reliability engineers and life test planners.