Robust-Adaptive Neural Network Finite-Time Control and Vibration Suppression for Flexible-Base Flexible-Joint Space Manipulator

This paper investigates the robust-adaptive neural network finite-time control and vibration suppression for a two-link flexible-base flexible-joint space manipulator with uncertain dynamics. Based on the dynamic equations, a slow subsystem and a fast subsystem of flexible space manipulator are derived by the singular perturbation method. For the slow subsystem, a robust-adaptive neural network finite-time motion control scheme is proposed to achieve the trajectory tracking of the manipulator, taking into account both parameter uncertainties and external disturbances. This control scheme consists of a finite-time controller used to guarantee the finite-time convergence of system errors, an adaptive neural network controller utilized to approximate uncertain dynamics and a robust controller added to eliminate the approximation error of the neural network. For the fast subsystem, a linear quadratic optimal controller is introduced to suppress the vibration caused by flexible joints and the flexible base, respectively. The effectiveness and the superiority of the presented hybrid controller are indicated by the simulations with a planar two-link flexible-base flexible-joint space manipulator.