A new plan for life-testing two-component parallel systems

Abstract

Although life-testing of parallel systems provides more information than testing series systems, it can be very time consuming, which limits its usage in practice. In this article, a new plan of life-testing two-component ( A and B) parallel systems is proposed. This plan terminates life-testing experiments at the rth smallest order statistics X ( r) of component A data. Our data type consists of type-II censored data ( i) , i = 1, 2, …, n from component A and their concomitants Y [ i] randomly censored at X ( r) from component B. Compared to the plan with complete samples, where the experiment is terminated until observing W ( n) , the maximum of W i = max( X i , Y i ), i = 1, 2, …, n, our new plan will shorten the test duration and save some unfailed components. General procedures of constructing the likelihood function and of deriving the expected number of failed components and testing duration are presented and illustrated under Marshall and Olkin's bivariate exponential distribution. A follow-up study shows that the loss of accuracy in maximum likelihood estimation is not severe compared with the gain of shortening the testing duration and saving some unfailed components.