Self-tuning control of a translational flexible arm using neural networks

The self-tuning control of a translational flexible arm using neural networks is presented. The control scheme consists of a gain tuning neural network and a variable-gain feedback controller. This neural network is trained so as to make the error between the root shear force and the reference root shear force zero. In the process, the neural network learns the optimal gain of the feedback controller. The feedback controller is designed based on Lyapunov's direct method. The feedback control of the motion of the flexible system is derived by considering the time rate of change of the total energy of the system. This approach has the advantage over conventional methods in that it allows one to deal directly with the system's partial differential equations without resorting to approximations. Numerical and experimental results for the tracking control of a translational flexible arm are presented and verify that the proposed control system is effective at controlling flexible dynamical systems.