Modeling and analysis of time-dependent stress accelerated life data

Abstract

The cumulative damage model is examined in this paper in two ways. First for analyzing data obtained from accelerated tests where the applied stress is time-dependent (for example step-stress) and second for making reliability predictions when the service stress is time-dependent (even when the test stress is not time-dependent). For example, the reliability of an aircraft engine, which operates under different stresses during take-off, cruising and landing, can be determined. The cumulative damage model is formulated by assuming the Weibull as the underlying life distribution, and the Arrhenius and inverse power law relationships are considered. The parameters of the model are estimated using maximum likelihood. An algorithm has been developed for the solution of this model, and implemented in a recently released software package, ALTA 6 PRO, specific to accelerated life data analysis. The solution to this model provides the engineers with an opportunity to expand their selection of test conditions when testing products, and to better model actual usage conditions.