Fast Fractional-Order Terminal Sliding Mode Control With RBFNN Based Sliding Perturbation Observer for 7-DOF Robot Manipulator

A new perturbation estimator, using radial basis function (RBF) neural networks (RBFNN) to modify the sliding observer (SPO), is proposed with fast fractional-order terminal mode control (FFOTSMC). It aims a seven-degree-of-freedom (7-DOF) robot manipulator. The estimator applies data-driven method RBFNN compensate for estimation error in conventional SPO first time. modified estimates perturbation, which contains disturbance, dynamic uncertainties, and modeling errors. estimated used design FFOTSMC, improves tracking accuracy reduces chattering. FFOTSMC was designed derivative surface reaching/law reaching surface. In experiments on robot, has been evaluated by comparing or only same controller, FFOTSMC. asymptotic stability of controller proved Lyapunov functions systems.