Stochastic sampled-data stabilization of neural-network-based control systems

摘要: This paper addresses the problem of stochastic sampled-data stabilization for neural-network-based control systems (NNBCSs) with an optimal guaranteed cost. In order to stabilize closed-loop system, continuous-time nonlinear plant and three-layer fully connected feed-forward neural networks based on sampling are closed loop. By introducing new Lyapunov–Krasovskii functional triple integral terms by using second-order reciprocal convex technique, stability criteria NNBCSs derived in linear matrix inequalities (LMIs). The desired controllers can be calculated solving these LMIs. Finally, physical example is given verify effectiveness usefulness obtained results.