Active Disturbance Rejection Control Based on Radial Basis Function Neural Network

Abstract

There are two disadvantages in Active Disturbance Rejection Control (ADRC): indeterminate parameters are included in Tracking - Differentiator (TD); and there are interferences between the parameters. For these, an Active Disturbance Rejection Control based on Radial Basis Function (RBF) Neural Network is proposed to solve the above two disadvantages for improving the algorithm. Nonlinear functions can be approached accurately by RBF Neural Network, that can be used to improve the TD. The simulation results show that the Active Disturbance Rejection Control based on Radial Basis Function (RBF) Neural Network's robustness is better, and Its anti-interference ability is stronger.