Reliability Analysis based on Inverse Gauss Degradation Process and Evidence Theory

The degradation analysis of products has been demonstrated as a significant toolkit for reliability analysis. Data from the same batch of products in different working environments cannot be directly used to analyze product reliability. In this paper, motivated by this circumstance, we first assume that degradation data sets from different working environments are subject to different inverse Gaussian process models, and maximum likelihood estimation is used to obtain multiple model parameters. Secondly, we construct evidence by quantifying different information of products, apply the evidence theory to fuse model parameters, and then analyze the reliability of products from the same batch. Finally, we use performance degradation data of the laser to illustrate the method. © 2019 Totem Publisher, Inc. All rights reserved.