Active Disturbance Rejection Control based on RBF Neural Network for Active Power Filter

Abstract

This paper presents an active disturbance rejection control (ADRC) method based on radial basis function (RBF) neural network applied to current tracking control of active power filter (APF). It is difficult to accurately model the active power filter system, and the uncertainty of the nonlinear system brings difficulties to the system analysis and control. In this paper, under the ADRC framework, a tracking differentiator (TD) is introduced to obtain the differential information of the reference signal and a nonlinear extended state observer (ESO) is constructed to estimate the state variables and the total disturbance. The nonlinear ESO realizes the feedforward compensation of disturbance, and the state feedback adopts the PD form. Further, the RBF neural network is designed to estimate the unknown parameter b of the system. The simulation results show that the proposed control method has good steady-state and dynamic performance.