Model-Based Prognostics Under Non-stationary Operating Conditions

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

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

Matej Gasˇperin Pavle Bosˇkoski Dani Juricˇic ́

Abstract

The paper presents a novel approach for prognostics of faults in mechanical drives under non-stationary operating conditions. The feature time series is modeled as an output of a dynamical state-space model, where operating conditions are treated as known model inputs. An algorithm for on-line model estimation is adopted to find the optimal model at the current state of failure. This model is then used to determine the presence of the fault and predict the future behavior and remaining useful life of the system. The approach is validated using the experimental data on a single stage gearbox.

How to Cite

Gasˇperin, . M. ., Bosˇkoski, P. ., & Juricˇic ́ D. . (2011). Model-Based Prognostics Under Non-stationary Operating Conditions. Annual Conference of the PHM Society, 3(1). https://doi.org/10.36001/phmconf.2011.v3i1.2074
Abstract 5 | PDF Downloads 0

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

Keywords

model-based prognostics, dynamic linear model, expectation-maximization algorithm, non-stationary operating conditions

References
Combet, F., & Gelman, L. (2009). Optimal filtering of gearnext term signals for early damage detection based on the spectral kurtosis. Mechanical Systems and Signal Processing, 23, 652-668.

DeCastro, J. A., Liang, T., Kenneth, L. A., Goebel, K., & Vachtsevanos, G. (2009). Exact nonlinear Filtering and Prediction in Process Model-Based Prognostics. In Proceedings of the 1st Annual conference of the PHM Society, San Diego, USA, September 27 - October 1, 2009.

Edwards, D., Orchard, M. E., Tiang, L., Goebel, K., & Vachtsevanos, G. (2010). Impact of Input Uncertainty on Failure Prognostic Algorithms: Extending the Remaining Useful Life of Nonlinear Systems. In Annual Conference of the Prognostics and Health Management Society, 2010.

Gasˇperin, M., Juricˇic ́, D., Bosˇkoski, P., & Vizˇintin, J. (2011). Model-based prognostics of gear health using stochastic dynamical models. Mechanical Systems and Signal Processing, 25(2), 537-548.

Gibson, S., & Ninness, B. (2005). Robust Maximum- Likelihood Estimation of Multivariable Dynamic Systems. Automatica, 41, 1667-1682.

Haykin, S. (Ed.). (2001). Kalman Filtering and Neural Networks. John Wiley & Sons, New York, USA.

Heng, A., Zhang, S., Tan, A. C., & Mathew, J. (2009). Rotating machinery prognostics: State of the art, challenges and opportunities. Mechanical Systems and Signal Processing, 23, 724-739.

Howard, I., Jia, S., & Wang, J. (2001). The dynamic modeling of a spur gear in mesh including friction and crack. Mechanical Systems and Signal Processing, 15, 831-853.

Orchard, M., Kacprzynski, G., Goebel, K., Saha, B., & Vachtsevanos, G. (2008). Advances in uncertainty representation and management for particle filtering applied to prognostics. In International Conference on Prognostics and Health Management, 6-9 Oct. 2008, Denver, CO.

Orchard, M. E., & Vachtsevanos, G. J. (2009). A particle- filtering approach for on-line fault diagnosis and failure prognosis. Transactions of the Institute of Measurement and Control, 31, 221-246.

Randall, R. (1982). A New Method of Modeling Gear Faults. Journal of Mechanical Design, 104, 259-267.

Zhang, B., Khawaja, T., Patrick, R., Vachtsevanos, G., Orchard, M., & Saxena, A. (2009). A Novel Blind Deconvolution De-Noising Scheme in Failure Prognosis. In K. P. Valavanis (Ed.), Applications of Intelligent Control to Engineering Systems (Vol. 39, p. 37- 63). Springer Netherlands.
Section
Technical Papers