Neural network feedforward control for mechanical systems with external disturbances

In this paper, a novel feedforward control based on accelerometer measurements is proposed for mechanical systems with external disturbances. The control scheme includes a feedback controller and a neural network feedforward compensator. The feedback controller is employed to guarantee the stability of the mechanical systems, while the neural network is used to provide the required feedforward compensation input for trajectory tracking with the help of a sensor to detect external vibrations. Dynamics knowledge of the plant, disturbances and the sensor is not required. The stability of the proposed scheme is analyzed by the Lyapunov criterion. Simulation results show that the proposed controller performs well for a hard disk drive system and a two-link manipulator.