Delay-dependent robust stabilization andH∞control for neural networks with various activation functions
Rathinasamy Sakthivel, Kalidass Mathiyalagan, Selvaraj Marshal Anthoni · Physica Scripta · 2012
This paper considers the problem of robust stabilization for a class of uncertain neural networks with various activation functions and mixed time delays. The aim is to derive a H ∞ control law to ensure the robust stability of the closed-loop system about its equilibrium with parameter uncertainties. By employing the Lyapunov stability theory and the matrix inequality technique, a new set of sufficient conditions is presented for the existence of the H ∞ control problem. The stability criteria are derived in terms of linear matrix inequalities (LMIs) which can be solved easily by the Matlab LMI toolbox. In addition to the requirement of global robust stabilization, for a prescribed H ∞ performance level the stabilizing controller gain matrices for all delays to satisfy the upper bound of the time-varying delay are required to be obtained. Numerical examples are presented to illustrate the effectiveness of the proposed method.