A modelling approach to state estimation in systems with switching parameters

This paper describes a novel approach to the problems of state estimation in linear, discrete-time systems which switch randomly between two sets of parameters, indicated by a random switching variable. A non-linear approximate model for the switching variable is developed and used for the joint estimation of the state vector and the switching variable via a single extended Kalman filter. The performance of the filter is compared with that of other suboptimal filters known to date. The proposed approach provides comparable accuracy, and saves computational effort in systems of order three or more. In large systems the computational effort is halved.