Exponential stability criteria for neural network based control of nonlinear systems

This paper investigates the problem of exponential stability of neural network controlled sampled-data systems. The stability of the closed loop system is formulated using Lyapunov-Krasovskii approach. Using a time-dependent Lyapunov function, novel conditions are proposed to guarantee the exponential stability of a continuous aperiodically sampled nonlinear system. The stability conditions are derived in terms of solvable Linear Matrix Inequalities. Numerical results are provided to illustrate the effectiveness of the proposed approach.