Process Monitoring and Parameter Estimation via Unscented Kalman Filtering

摘要

Extended Kalman filters (EKF) have found wide-spread use in nonlinear state and parameter estimation. Unlike EKF, where the first-order linearization is used for error covariance estimation, unscented Kalman filters (UKF), as proposed by Julier and Uhlman [1], pass the mean and covari-ances of estimated states through a nonlinear transformation. This is achieved by carefully choosing a set of sigma points, which capture the true mean and covariance of the given distribution and results in UKF being capable of estimating the posterior mean and covariances accurately to a high order. However, in theory, performance of UKF can exceed the one for EKF where only first-order accuracy is achieved. Despite UKF's potential for improved state and parameter estimation, only few applications in chemical engineering have been reported [2][3][4].