The control method of adaptive backstepping and neural network in the application of a parallel robot

Abstract

Considering the unknown nonlinearities and external disturbances for a 2-DOF redundant parallel robot, a novel control method based on adaptive backstepping control and neural network approximation is proposed. In the controller, a RBF NN is used to approximate the uncertain function in order to make the adaptive backstepping control have a strong robustness for the unknown nonlinearities and external disturbances. The simulation results show that the control method has a good performance of tracking and a strong robustness, which can improve the control performance of a parallel robot with a strong coupling and high non-linearity. They also confirm the correctness and effectiveness of the proposed control strategy.