Artificial neural network for identification and tracking control of a flexible joint single-link robot

Abstract

An artificial neural network for identification and tracking control of a nonlinear flexible joint robot with model reference adaptive control structure is developed. Neural network identification (NNI) is used to obtain a dynamic model of a flexible joint robot to be controlled. Once NNI has closely matched the dynamic model of a flexible joint robot, neural network control (NNC) of tracking trajectory of a flexible joint robot is designed. Both tasks are completed using the backpropagation neural network. The method is shown to be a more simple, robust and adaptive learning control system than traditional control design for tracking control of a flexible joint single-link robot.