With the development of new maintenance techniques based on condition monitoring, diagnostic and prognostic methods are also being extended. In the process of estimating the remaining useful life (RUL) using the data-driven approach, it is difficult to determine the degradation state
of the equipment with several sources of information and to predict the remaining useful life with non-smooth data that have sudden changes inherent in the monitoring data. In this paper, a procedure is presented to address these two issues in which the degradation state of the equipment is
determined in the presence of several information sources using a combination of the fuzzy c-means clustering and the combination rules of the Dempster-Shafer theory, and the prediction of the data for the estimation of the remaining useful life is carried out using an autoregressive Markov
regime-switching (ARMRS) model that is capable of dealing with sudden changes in condition monitoring data. To evaluate the proposed model, the bearing dataset of the FEMTO-ST Institute is used. The experimental results show the high competitiveness of the proposed procedure compared to similar
methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.