Trajectory control of flexible plate using neural network

Modeling and control problems for a three-joint robot handling a flexible plate in the vertical plane under gravity are treated. The dynamical model is obtained using Hamilton´s principle, and the ordinary differential equations are obtained using modal analysis. Given the tip position, an iterative algorithm for solving the inverse kinematics is presented. The control torque is obtained using the feedback error learning method and the desired trajectory of the static bending deflection curve. Four three-layer neural networks are used to reduce the joint-angle feedback errors and bending vibration. Simulation results are given