Reliability Assessment by a Wiener Process that Integrates Different Degradation Datasets

Abstract

A Wiener process based on field degradation data is used to describe the product degradation process. By integrating the accelerated degradation data of similar products with target-product field-measured degradation data, a new reliability assessment method is proposed. Given the difference between field and laboratory stress environments, a Wiener process model with calibration factors is built. A degradation model for similar products and a target product is built to obtain estimates of the distribution parameters under each type of stress. An accelerated factor is used to convert the estimates obtained under accelerated stress into estimates representative of regular stress, which constitutes the data sample of the prior distribution’s parameters. A Bayesian inference method is used to obtain the posterior distribution parameters using the field degradation data of a target product. A Markov chain Monte Carlo algorithm is used to obtain the estimates of the posterior distribution parameters. The accuracy of the proposed method is verified by an example.