Fuzzy Sliding Mode Control of Manipulator Based on Disturbance Observer and RBF Neural Network

Aiming at the nonlinear and uncertain manipulator system, this paper proposes a fuzzy sliding mode control method based on disturbance observer and radial basis function (RBF) neural network, so that the manipulator can track a given trajectory with ideal dynamic quality. First, the nonlinear disturbance observer can accurately estimate the unknown disturbance, realize the feedforward compensation of the controller, and improve the accuracy of the controller, and then use the RBF neural network to approximate the uncertainty of the modelling and improve the robustness of the control system. At the same time, the fuzzy logic system is used to adaptively adjust the switching gain of sliding mode control, which effectively solves the chattering problem in sliding mode control. Finally, the Lyapunov stability theory is used to prove the stability of the control system, and the simulation verification is carried out. The simulation results show that the control algorithm effectively improves the tracking accuracy and tracking speed of the trajectory, and enhances the robustness to external disturbance.