Neural network modeling-based anti-disturbance tracking control for complex systems with input saturation

![CDATA[In this paper, the anti-disturbance tracking control arithmetic for a class of MIMO nonlinear systems with input saturation is discussed. In order to better characterize unknown disturbances, the exogenous systems with neural network adjustable parameters are employed and the disturbance-observer-based-control (DOBC) framework is also established with appropriate systematic rules. Via using the polytopic representation of saturation function, and combining the state feedback with the estimates of disturbance, the composite controller is designed to guarantee the tracking error of output can tend to zero. Meanwhile, two Lyapunov functions are modelled to proof the related theorem. A simulation example eventually for the A4D aircraft models is included to explain the effectiveness of the presumptive consequence.]]