Novel delay-dependent H<inf>∞</inf> state estimation for static neural networks with time-varying delay

Abstract

In this paper, the problem of delay-dependent H ∞ state estimation for static neural networks with time-varying delay is investigated. By introducing a new double-integral inequality and constructing a more general Lyapunov-Krasovskii functional (LKF) including a triple integral term, an improved delay-dependent design condition is established so that the error system is globally exponentially stable with a decay rate k and a guaranteed H ∞ performance index γ. Moreover, in order to get less conservative results, new activation function conditions are proposed by bringing in an adjustable parameter δ. The desired estimator gain matrix and optimal performance index γ are achieved by solving a convex optimization problem subject to linear matrix inequalities (LMIs). Finally, two numerical examples are given to demonstrate the effectiveness and the advantage of the proposed method.