Adaptive neural control of a rotating flexible manipulator

Abstract

The motion control of a planar manipulator with a flexible arm is studied. Dynamics are developed in Lagrangepsilas formulation. A novel control system structure is proposed to control the joint position and velocity as well as deflection of the tip of the arm. First, a neural network controller based on the equations of motion of the robot is elaborated. Its aim is to produce a fast and stable control. Then, an adaptive neural controller is added to compensate structured and unstructured uncertainties. Efficiency of the new controller obtained by combining the two control laws is tested facing an important variation of the dynamic parameters of the flexible manipulator and compared to a classical nonlinear controller. Simulation results show the effectiveness of the control strategy proposed.