Improving Computational Efficiency of Prediction in Model-based Prognostics Using the Unscented Transform

Shared by Matthew Daigle, updated on Feb 07, 2012

Summary

Author(s) :
Matthew Daigle, Kai Goebel
Abstract

Model-based prognostics captures system knowledge in the form of physics-based models of components, and how they fail, in order to obtain accurate predictions of end of life (EOL). EOL is predicted based on the estimated current state distribution of a component and expected profiles of future usage. In general, this requires simulations of the component using the underlying models. In this paper, we develop a simulation-based prediction methodology that achieves computational efficiency by performing only the minimal number of simulations needed in order to accurately approximate the mean and variance of the complete EOL distribution. This is performed through the use of the unscented transform, which predicts the means and covariances of a distribution passed through a nonlinear transformation. In this case, the EOL simulation acts as that nonlinear transformation. In this paper, we review the unscented transform, and describe how this concept is applied to efficient EOL prediction. As a case study, we develop a physics-based model of a solenoid valve, and perform simulation experiments to demonstrate improved computational efficiency without sacrificing prediction accuracy.

show more info
Publication Name
Proceedings of the Annual Conference of the Prognostics and Health Management Society 2010
Publication Location
Portland, OR
Year Published
2010

Files

DaigleEtAl-PHM2010.pdf
777.6 KB 27 downloads

Discussions

Add New Comment