Generalized observability analysis and observer design for a class of systems with multiple uncertain dynamics and measurement biases

This paper is concerned with a systematic discussion on the problem of state estimation for a class of systems with multiple uncertain dynamics and multiple measurement biases. Instead of the traditional observability definition only for system state vector, we consider the generalized observability for the combinations of system state vector, uncertain dynamics and measurement bias. Firstly, a necessary and sufficient condition for the observability of system state vector is developed. Moreover, the set of all the observable combinations of system state vector, uncertain dynamics and measurement bias is presented. Correspondingly, an observer is constructed for estimating a special observable combination which is an approximation of system state vector. More importantly, the bound of the resulting estimation error for the system state vector is quantitatively discussed. Finally, the simulation study on a two-mass-spring system illustrates our theoretical results. (C) 2021 Elsevier B.V. All rights reserved.