Search

Traditional reliability assessment methods are based on lifetime data. However, the lifetime data of high reliability product are difficult to obtain even by the accelerated life test. In this paper, a very effective method is presented to assess the reliability via the degradation data of product, where the degradation path of product is characterized by mixed effect wiener process model. Considering that the mixed effect degradation model is very complicated, the Bayesian Markov Chain Monte Carlo (MCMC) method is used to obtain the unknown parameters and the corresponding reliability assessment is carried out. At last, a numerical example about laser data is given to demonstrate that degradation data can provide more information about the product than lifetime data and pseudo lifetime data. [ABSTRACT FROM AUTHOR]

In this article, the population reliability modeling and individual residual life prediction are discussed. Firstly, three kinds of different Wiener process models are used to characterize the degradation data, and the unknown parameters are estimated by using the Markov Chain Monte Carlo (MCMC) method. Secondly, under those degradation models, the individual residual life prediction method is also obtained on the basis of current degradation quantity. Finally, a fatigue cracks data example is given to illustrate the usefulness and validity of the proposed model and method. Numerical results show that the random effect model is well fitted with the actual degradation data, and this model has smallest prediction error. Meanwhile the prediction accuracy is acceptable, and this prediction method provides a foundation for maintenance decision. [ABSTRACT FROM AUTHOR]