Linear active disturbance rejection control for hysteresis compensation based on backpropagation neural networks adaptive control

Abstract

This paper proposes a compound control framework for non-affine nonlinear systems facing hysteresis disturbance. The controller consists of linear active disturbance rejection control (LADRC) and backpropagation (BP) neural networks adaptive control. BP neural networks are utilized to arbitrarily approximate the uncertainty nonlinear caused by the deviation of control parameter from its nominal value and LADRC is designed to real-time estimate and compensate the disturbance with vast matched and mismatched uncertainties including unknown internal system dynamic uncertainty and external hysteresis disturbance therein. Combining the adaptive neural networks design with LADRC design techniques, a new dual-channel composite controller scheme is developed herein whereby adaptive neural networks are used as feed-forward inverse control and LADRC as closed-loop feedback control. Furthermore, as compared with a traditional control algorithm, the proposed BP-LADRC dual-channel composite controller can guarantee that the desired signal can be tracked with a small domain of the origin and it is confirmed to be effective under Lyapunov stability theory and MATLAB simulations.