Active Disturbance Rejection Control for a Class of Non-affine Nonlinear Systems via Neural Networks

Wen-tao LIU, Tong ZHAO


An active disturbance rejection controller based on radial basis function (RBF) neural network is proposed for a class of non-affine nonlinear systems in this paper. In which, the active disturbance rejection control (ADRC) is utilized to estimate the full system state and RBF neural network is used to approximate the reference signal. It is proved that, the composite controller has faster response speed and higher tracking accuracy, which effectively improves the control performance of the system and alleviates the adverse effects caused by strong coupling in the nonlinear dynamic system. Effectiveness of the proposed method is verified by MATLAB simulation.


RBF neural network, Active disturbance rejection control, RBF-ADRC composite controller.


Full Text:



  • There are currently no refbacks.