Disturbance Estimation and Compensation in Exoskeleton Electric Drive Control with Neural Network

Abstract

The article proposes a method to evaluate and compensate uncertain disturbance in exoskeleton electric drive control system. The mathematical model for exoskeleton electric drive system with taking into account the nonlinear components and the interaction force between exoskeleton and lower extremities is developed. The PD control combined with the RBF adaptive neural network is investigated with linear-quadratic regulator as the basic foundation of the feedback design to evaluate and compensate the unknown disturbances in control system. The PD ingredient is applied to stabilize the dominant model. The simulation results in Matlab/Simulink indicate that the proposed PD-linear quadratic regulator with adaptive neural network compensation is more efficiency in compared with the conventional PD-linear quadratic regulator.