This paper is concerned with the problem of the robust exponential passive filter design for uncertainneutral-type neural networks with time-varying mixed delays. Our aim is to design a Luenberger-type filter forestimating information about the neuron states, which is required in some applied areas. By constructing an appropriateLyapunov-Krasovskii functional and using the Wirtinger-based integral inequality to estimate its derivative,a delay-range-dependent and delay-rate-dependent criterion is presented to ensure the augmented filtering dynamicsystem to be robustly exponentially stable and passive with an expected dissipation. Since the criterion is presentedin the form of linear matrix inequalities with nonlinear constraints, a cone complementarity linearization algorithmis proposed to determine the filter gain from solution to the nonlinear problem. Finally, a numerical example isgiven to demonstrate the effectiveness of the proposed method.
This paper is concerned with the problem of the robust exponential passive filter design for uncertainneutral-type neural networks with time-varying mixed delays. Our aim is to design a Luenberger-type filter forestimating information about the neuron states, which is required in some applied areas. By constructing an appropriateLyapunov-Krasovskii functional and using the Wirtinger-based integral inequality to estimate its derivative,a delay-range-dependent and delay-rate-dependent criterion is presented to ensure the augmented filtering dynamicsystem to be robustly exponentially stable and passive with an expected dissipation. Since the criterion is presentedin the form of linear matrix inequalities with nonlinear constraints, a cone complementarity linearization algorithmis proposed to determine the filter gain from solution to the nonlinear problem. Finally, a numerical example isgiven to demonstrate the effectiveness of the proposed method.