Filtering for Nonlinear Systems, Smoothing, Error Analysis/Model Design, and Measurement Preprocessing
Bruce P. Gibbs · 2011
This chapter covers extensions of Kalman filtering that are routinely used. Specific topics considered in this chapter are: Kalman filtering for nonlinear systems, Smoothing, Error analysis and model state selection, Measurement preprocessing. Options for linear covariance error analysis include perturbation analysis of independent error sources, error analysis for reduced - order models (ROMs), and error analysis for truth and filter models that are structurally different. Smoothers compute the minimum mean - squared error (MMSE) estimate of a state in past time based on measurements up to a later time. Smoothing options include fixed point, fixed lag, and fixed interval. Most Kalman filtering applications are for nonlinear systems. The EKF handles the nonlinearities by linearizing about the current estimate at each measurement update. The iterated linear filter - smoother works similarly, but iterates on both the time update and measurement update steps when both models are nonlinear. Controlled Vocabulary Terms Kalman filters; nonlinear filters