Prognosis of gear health using stochastic dynamical models with online parameter estimation

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Mar 26, 2021
Matej Gašperin Pavle Boškoski Dani Juričić

Abstract

In this paper we present a statistical approach to the estimation of the time in which an operating gear will achieve the critical stage. The approach relies on measured vibration signals. From these signals features are extracted first and then their evolution over time is predicted. This is done owing to the dynamic model that relates hidden degradation phenomena with measured outputs. The Expectation-Maximization algorithm is used to estimate the parameters of the underlying state- space model on-line. Time to reach safety alarm threshold is determined by making the prediction using the estimated linear model. The results obtained on a pilot testbed are presented.

How to Cite

Gašperin, M., Boškoski, P. ., & Juričić, D. . (2021). Prognosis of gear health using stochastic dynamical models with online parameter estimation. Annual Conference of the PHM Society, 1(1). Retrieved from https://papers.phmsociety.org/index.php/phmconf/article/view/1634
Abstract 223 | PDF Downloads 173

##plugins.themes.bootstrap3.article.details##

Keywords

damage detection, damage modeling, gears, materials damage prognostics, prognostics, remaining useful life (RUL)

References
(Dempster et al., 1977) A. Dempster, N. Lard, and D. Rubin. Maximum likelihood from incomplete data via the em algorithm. Journal of the Royal Statistical Society, Series B, 39:1–38, 1977.
(G. Niu, 2009) Bo-Suk Yang G. Niu. Dempstershafer regression for multi-step-ahead time-series prediction towards data-driven machinery prognosis. Mechanical Systems and Signal Processing, 23:740– 751, 2009.
(Gibson and Ninness, 2005) S. Gibson and B. Nin- ness. Robust maximum-likelihood estimation of multivariable dynamic systems. Automatica, 41:1667–1682, 2005.
(Ho and Randall, 2000) D. Ho and R. B. Randall. Optimisation of bearing diagnostic techniques using simulated and actual bearing fault signals. Mechanical Systems and Signal Processing, 14:763–788, 2000.
(Howard, 1994) I. Howard. A review of rolling element bearing vibration ”Detection, Diagnosis and Prognosis”. DSTO Aeronautical and Maritime Research Laboratory, 1994.
(Orchard and Vachtsevanos, 2009) M. E. Orchard and G. J. Vachtsevanos. A particle-filtering approachfor on-line fault diagnosis and failure prognosis. Transactions of the Institute of Measurement and Control, 31:221246, 2009.
(Rubini and Meneghetti, 2001) R. Rubini and U. Meneghetti. Application of the envelope and wavelet transform and analyses for the diagnosis of incipient faults in ball bearings. Mechanical Systems and Signal Processing, 15:287–302, 2001.
(W. Q. Wanga and Ismailb, 2004) M. F. Golnaraghib W. Q. Wanga and F. Ismailb. Prognosis of machine health condition using neuro-fuzzy systems. Mechanical Systems and Signal Processing, 18:813– 831, 2004.
(Wang et al., 2003) W. Q. Wang, M. F. Golnaragh, and F. Ismail. Prognosis of machine health condition using neuro-fuzzy systems. Mechanical Systems and Signal Processing, 18:813–831, 2003.
Section
Technical Research Papers