Event-triggered set-membership filtering for discrete-time memristive neural networks subject to measurement saturation and fadings

Abstract

In this paper, the set-membership (SM) filtering problem is investigated for a class of discrete time-delayed memristive neural networks (MNNs) with unknown-but-bounded disturbances. The output measurements are subject to saturation, whose transmission is governed by a predetermined event-triggered strategy. In addition, the communication channel is usually fading, which is described by a set of stochastic variables taking different values in the interval [0,1]. The nonlinear activation function and the saturation function are assumed to satisfy the Lipschitz-like and sector conditions, respectively. The purpose of this paper is to design an event-triggered (ET) filter to estimate the certain region which includes the real states while guaranteeing the benefits of resource conservations. Via recursive linear matrix inequalities, some sufficient conditions are derived to optimize the estimation elliptic sets. Furthermore, the design of the optimal SM filter for MNNs is recast as solving a convex optimization problem via the semidefinite programming method. Finally, a persuasive simulation example is provided to verify the effectiveness of the designed filtering algorithm.