Formula omitted] state estimation of the high-order inertial neural network with time-varying delay: Non-reduced order strategy

Abstract

As a first attempt, the L2-L∞ state estimation issue of the high-order inertial neural networks with time-varying delay is put forward in this paper. A more direct method, non-reduced order method, is adopted here rather than reducing the order of the original second-order dynamics via substitution of variables. Our main objective is to construct an appropriate state estimator, which can not only guarantee the global h-stability of the undisturbed error dynamics, but also ensure the peak value of the estimation error is kept within a certain range. Through utilizing Lyapunov theory and some simple matrix calculation, a delay-dependent criterion is presented to elaborate the state estimator conforms to the expectation. In the end, an illustrative simulation example shows the correctness of the estimation technique proposed in this paper.