A prognostics approach to nuclear component degradation modeling based on Gaussian Process Regression. (January 2015)

• Record Type: Journal Article
• Authors: Baraldi, Piero; Mangili, Francesca; Zio, Enrico
• Is Part Of: Progress in nuclear energy. Volume 78(2015:Jan.)
• Page Start: 141
• Page End: 154
• Publication Date: 2015-01
• Subjects: Remaining useful life -- Prognostics -- Bayesian inference -- Gaussian Process Regression -- Creep -- Filter clogging; Nuclear energy -- Periodicals; Nuclear engineering -- Periodicals; 333.7924
• DOI: 10.1016/j.pnucene.2014.08.006
• Languages: English
• ISSNs: 0149-1970

Abstract

Abstract: Advanced diagnostics and prognostics tools are expected to play an important role in ensuring safe and long term operation in nuclear power plants. In this context, we use Gaussian Process Regression (GPR) to build a stochastic model of the equipment degradation evolution and apply it for prognostics. GPR is a probabilistic technique for non-linear non-parametric regression that estimates the distribution of the future equipment degradation states by constraining a prior distribution to fit the available training data, based on Bayesian inference. Training data are taken from sequences of degradation measures collected from a set of similar historical equipment which have undergone a similar degradation process. Given new degradation measures from a currently degrading equipment (test trajectory), the distribution of the Remaining Useful Life (RUL) before failure is estimated by comparing with a failure criterion the distribution of the future degradation states predicted by GPR. Applications are shown on simulated data concerning the evolution of creep damage in ferritic steel exposed to high stress and on real data concerning the clogging of sea water filters placed upstream the heat exchangers of a BWR condenser. Highlights: We tackle the prediction of the remaining useful life of degrading equipment. We face the problem of modeling the uncertain evolution of the degradation processes. We propose different modeling strategies based on Gaussian Process Regression (GPR). We evaluate these strategies on case studies with simulated and real data. GPR demonstrates to be a promising method for modeling degradation processes.