Robust H∞ state estimation for BAM neural networks with randomly occurring uncertainties and sensor saturations

In this paper, the robust H∞ state estimation problem is investigated for a class of discrete-time delayed bidirectional associative memory neural networks with randomly occurring uncertainties (ROUs) and sensor saturations. In order to more clearly reflect the reality in a networked environment, Bernoulli distributed white sequences with known probabilities are introduced to characterize the network-induced phenomena of the ROUs and the randomly occurring sensor saturations. The purpose of the addressed problem is to design a robust H∞ state estimator such that the dynamics of the estimation error is asymptotically stable in the mean square. By using matrix computation and stochastic analysis approaches, a sufficient condition is established to ensure the desired H∞ performance requirements, and the explicit form of the estimator gains can be obtained by solving some matrix inequalities. Finally, an illustrative example is provided to demonstrate the effectiveness of the proposed state estimation approach.