Title :
A fault/anomaly system prognosis using a data-driven approach considering uncertainty
Author :
Escobet, Teresa ; Quevedo, Joseba ; Puig, Vicenç
Author_Institution :
DiPSE Dept., Univ. Politec. de Catalunya, Manresa, Spain
Abstract :
This paper presents a data-driven prognostic strategy for failure prediction and computing the remaining useful life (RUL) using an autoregressive (AR) model combined with the recursive least squares (RLS) algorithm. The proposed method not only provides an estimation of the remaining useful life (RUL), but also a confidence interval based on modeling the uncertainty as a probabilistic Gaussian variable. To illustrate the performance of the proposed approach, a conveyor belt system that uses an AC electric motor to move a cart from one end to the other is used.
Keywords :
AC motors; Gaussian processes; autoregressive processes; belts; conveyors; fault diagnosis; least squares approximations; probability; remaining life assessment; AC electric motor; anomaly system prognosis; autoregressive model; confidence interval; conveyor belt system; data-driven prognostic strategy; failure prediction; fault system prognosis; probabilistic Gaussian variable; recursive least squares algorithm; remaining useful life estimation; Belts; Degradation; Estimation; Mathematical model; Prediction algorithms; Predictive models; Uncertainty; data-driven approaches; prognosis; remaining useful life; uncertainty;
Conference_Titel :
Neural Networks (IJCNN), The 2012 International Joint Conference on
Conference_Location :
Brisbane, QLD
Print_ISBN :
978-1-4673-1488-6
Electronic_ISBN :
2161-4393
DOI :
10.1109/IJCNN.2012.6252688
