ABSTRACT
This chapter addresses the gain-scheduled filtering problem for a class of discrete-time systems with missing measurements, nonlinear disturbances, and external stochastic noises. It summarizes the main contributions as follows: a new filtering problem is addressed for a class of discrete-time nonlinear stochastic systems with missing measurements via a gain-scheduling approach; and a sequence of stochastic variables satisfying Bernoulli distributions is exploited to reflect the time-varying features of the missing measurements in sensors. The main contributions also include: a time-varying Lyapunov function dependent on the missing probability is proposed and then applied to improve the performance of the gain-scheduled filters; and the filter parameters can be updated online according to the missing probabilities estimated through statistical tests. The chapter deals with the stability analysis and gain-scheduled filter design problems. It utilizes the parameter-dependent Lyapunov function and the convex optimization method. The chapter presents the numerical example to show the effectiveness of the proposed algorithm.
