State estimation for discrete-time delayed neural networks with fractional uncertainties and sensor saturations

In this paper, the state estimation problem is investigated for a new class of discrete-time delayed neural networks with fractional uncertainties and sensor saturations. The activation functions are described by the sector-like nonlinearities that are more general than the commonly used Lipschitz ones. The purpose of the addressed problem is to design a state estimator to estimate the network states through available output measurements such that the dynamics of the estimation error is globally exponentially stable. An optimization method is employed to deal with the fractional uncertainties presented in the neural networks. The estimator is expected to be robust against parameter uncertainties and tolerant against the sensor saturations. It is shown that the estimator gains can be derived in terms of the delay bounds, uncertainty structures and saturation levels. The desired state estimator is designed via the semi-definite programme method that can be easily implemented by using available software. Finally, a numerical example is applied to demonstrate the effectiveness of the proposed state estimation approach.