Multiple integral Lyapunov approach to mixed-delay-dependent stability of neutral neural networks

Abstract

Abstract This work studies the robust stability for a class of uncertain neutral neural networks with mixed time-varying delays. Through utilizing some novel Wirtinger-based integral inequalities and extending the convex combination technique, the upper bound on derivative of Lyapunov–Krasovskii (L–K) functional can be estimated more tightly and two mixed-delay-dependent criteria are proposed in terms of linear matrix inequalities (LMIs), in which some previously ignored information can be utilized. Different from those existent works, based on interconnected relationship between the neutral delay and neural one, some multiple integral Lyapunov terms are constructed and the conservatism can be effectively reduced. Finally, two numerical examples are given to show the benefits of the proposed criteria.