Bayesian Methods for Modeling Repeated Measures of Discrete Degradation
Résumé
Degradation modeling is an effective approach for reliability assessment and predicting of remaining useful life in order to investigate the relation between failure time and degradation of a system or unit. The possibility of association between degradation of unit during time and the effects of covariates on degradation processes should be take into account in the model to improve the explanatory capabilities of degradation models. Sometimes, the exact amount of degradation could not be observed because of time, cost and measurement tools limitations. Therefore, approximate degradation values can be compared with a critical threshold. In this paper, degradation process is modeled with a generalized linear mixed effect model in order to take in to account the correlation between times. Also, a Bayesian method is used to estimate parameters.