Adaptive Neural Network Dynamic Surface Control of Uncertain Nonlinear Systems with Unknown Control Direction and Unknown Actuator Fault

This paper investigated the tracking control problem of a class of uncertain nonlinear systems with unknown control direction and unknown actuator fault. By using the neural network control approach and dynamic surface control technique, an adaptive neural network dynamic surface control (NNDSC) law is designed. Based on the neural network approximator, the uncertain nonlinear dynamics are approximated. To solve the unknown control direction problem and deal with the unknown actuator fault, a type of Nussbaum gain function is incorporated into the recursive design of dynamic surface control. Under the designed adaptive control law, it can be proved that all of the signals in the closed-loop system are semiglobal bounded and the tracking error can be guaranteed to converge to the specified small neighborhood of the origin by adjusting the designing parameters. The effectiveness of the designed control law is proved by a given numerical example.