Hidden control neural network identification-based tracking control of a flexible joint robot

In this paper we present a new artificial neural network (ANN) structure to compensate for the convergence problem associated with training the identification of a complex nonlinear flexible joint robot for trajectory tracking problem. The tracking control of a MIMO flexible joint robot with high velocity is complicated due to the joint flexibilities, nonlinearities, and couplings. Our scheme consists of three ANN structures. The neural network identification (NNI) is used to obtain a dynamic model of a flexible joint robot to be controlled. Once the NNI has not closely learned the dynamic model of a flexible joint robot, the other new ANN structure, called hidden control neural network identification (HCNNI), is designed to overcoming the identification convergence problem in this paper. This HCNNI allows learning to compensate for poor identification and external disturbance. A third ANN control is designed for tracking control of a flexible joint robot based upon the identification. These tasks are completed using the backpropagation neural network.