State estimation for linear systems with state equality constraints

This paper deals with state estimation problem for linear systems with state equality constraints. Using noisy measurements which are available from the observable system, we construct the optimal estimate which also satisfies linear equality constraints. For this purpose, after reviewing modeling problems in linear stochastic systems with state equality constraints, we formulate a projected system representation from a descriptor system form. By using the constrained Kalman filter for the projected system and comparing its filter Riccati Equation with those of the unconstrained and the projected Kalman filters, we reach the conclusion that the current constrained estimator outperforms other filters for estimating the constrained system. We extend the same procedures from discrete-time to the continuous-time case. Finally, a numerical example is presented, which demonstrates performance differences among those filters. Key words: Estimation; Constraints; Kalman filters; Projec...

• Type: Journal
• Year: 2007
• Where: AUTOMATICA
• Authors: Sangho Ko, Robert R. Bitmead
• Keywords: AUTOMATICA 2007, Equality Constraints, Linear Equality Constraints, State Equality Constraints