Step-stress accelerated degradation modeling based on nonlinear Wiener process

Abstract

Aiming at nonlinear degradation data in step-stress accelerated degradation test (SSADT), the reliability assessment method is put forward based on Wiener process. the process and degradation data model of SSADT is analyzed. The time scale model is used to convert nonlinear data into linear data. Draft coefficient of Wiener process is regarded as a random variable. Reliability model for nonlinear degradation data is built in consideration of individual variation. The two-step maximum likelihood estimation method (TSMLE) is used to derive the unknown parameters. An example is analyzed to show that presented model is correct.