Neural network-based H∞ sliding mode control for nonlinear systems with actuator faults and unmatched disturbances

By combining integral sliding mode control with nonlinear H-infinity optimal control theory, a novel nonlinear control scheme is proposed for uncertain nonlinear systems with actuator faults and unmatched disturbances. The effect of the actuator faults and the separated matched disturbance component can be reduced by a properly designed discontinuous sliding mode controller, while unmatched disturbance component is attenuated by a nonlinear H-infinity control obtained by approximately solving HJI equations for equivalent sliding mode dynamics. An adaptive dynamic program (ADP) algorithm based on three neural networks (NNs) is applied to solve the HJI equation. Lyapunov techniques are used to demonstrate the convergence of the NN weight errors in the sense of uniform ultimate bounded. Some simulation results are presented to verify the feasibility of the proposed control scheme. (C) 2017 Elsevier B.V. All rights reserved.