Finite-time L2-gain analysis for switched neural networks with time-varying delay.

This paper considers the finite-time stability and finite-time boundedness problems for switched neural networks subject to L2<inline-graphic></inline-graphic>-gain disturbances. Sufficient conditions for the switched neural networks to be finite-time stable and finite-time bounded are derived. These conditions are delay-dependent and are given in terms of linear matrix inequalities. Average dwell time of switching signals is also given such that switched neural networks are finite-time stable or finite-time bounded. By resorting to the average dwell time approach and Lyapunov–Krasovskii functional technology, some new delay-dependent criteria guaranteeing finite-time boundedness and stabilizability with L2<inline-graphic></inline-graphic>-gain analysis performance are developed. An illustrative example is given to demonstrate the effectiveness of the proposed state estimator. [ABSTRACT FROM AUTHOR]