Robust exponential stability and H_∞ control for switched neutral‐type neural networks

Abstract

In this paper, we consider the problem of robust exponential stability for a class of uncertain switched delayed neutral-type neural networks with an H 1 performance level > 0. Further, the result is extended to design an H 1 control law to ensure the robust exponential stabilization of the closed-loop neural networks about its equilibrium point with the guaranteed H 1 performance level , for all norm bounded parameter uncertainties. On the basis of a new set of Lyapunov-Krasovskii functional, linear matrix inequality technique, and average dwell time approach, a set of novel sufficient conditions is derived for the existence of H 1 performance and as well as existence of H 1 control problem. The obtained results are derived in the form of convex optimization problems, which can be solved easily by the standard Matlab control toolbox. Numerical examples with simulation results are provided to illustrate the effectiveness of the proposed method.

Stabilization of switched neural networks with time‐varying delay via bumpless transfer control

“…Up to now, the stabilization problem for switched neural networks by feedback control technique has been well discussed.In [12],thedelay-independentanddelay-dependent mean square exponential stabilization results for stochastic neural networks with Markovian switching are proposed. The H ∞ controller is designed for uncertain switched neural networks [13]. In [14], the researchers present a memoryless state feedback controller to stabilize stochastic Cohen-Grossbery neural networks with mode-dependent mixed time delay and Markovian switching.…”

Observer‐based tracking control for switched stochastic systems based on a hybrid 2‐D model

“…Lemma For any positive symmetric constant matrix , a scalar τ >0 and a vector function such that the integrations are concerned are well defined, then …”

NovelH∞state estimation of static neural networks with interval time-varying delays via augmented Lyapunov–Krasovskii functional

“…The problem of delay-dependent H ∞ state estimation and H ∞ control for delayed neural networks have received substantial observation among control community for the past years [19]- [20]. H ∞ control of switched neutral-type neural networks were presented in [21] to estimate the robust exponential stability. Taking into account the information in system equations, H ∞ state estimation of static neural networks with time-varying delay were studied in [22]- [24].…”