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.

Adaptive-based linear active disturbance rejection attitude control for quadrotor with external disturbances

“…All uncertainties of the system are regarded as the total disturbance (Liu et al, 2021), which is defined as…”

Feedback error learning neural network for stable control of nonlinear nonaffine systems

“…Many research studies have demonstrated NNs approximation capability (Nassajian and Balochian, 2021), and parallel structure, learning capability, approximation of nonlinear functions, and fault tolerance cause NNs to be considered in identification and control applications. The backpropagation algorithm revolutionized the use of NNs in the 1980s and led to the development of neural controllers (Liu et al, 2020). In the field of NNs, several creative ideas and advances have been developed, but the study of stability, robustness, and convergence of the closed-loop system are essential issues concerning the neural controllers.…”

Inverse‐compensation‐based DETC for nonlinear hysteresis system with disturbance

“…It often limits the system performance-for example, by giving rise to undesirable inaccuracies or oscillations-and can even lead to instability [2][3][4][5]. In addition to hysteresis, disturbances widely exist in industrial systems and can degrade control performance and system stability [6,7].…”