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

EOL is predicted based on the esti- mated current state distribution of a component and ex- pected profiles of future usage. In general, this requires simulations of the component using the underlying mod- els.

In this paper, we develop a simulation-based pre- diction methodology that achieves computational effi- ciency by performing only the minimal number of sim- ulations needed in order to accurately approximate the mean and variance of the complete EOL distribution. This is performed through the use of the unscented trans- form, which predicts the means and covariances of a distribution passed through a nonlinear transformation.