Robust backpropagation training algorithm for multilayered neural trackingcontroller

A robust backpropagation training algorithm with a dead zone scheme is used for the online tuning of the neural-network (NN) tracking control system. This assures the convergence of the multilayered NN in the presence of dist urbance. It is proved in this paper that the selection of a smaller range o f the dead zone leads to a smaller estimate error of the NN, and hence a sm aller tracking error of the NN tracking controller. The proposed algorithm is applied to a three-layered network with adjustable weights and a complet e convergence proof is provided, The results can also be extended to the ne twork with more hidden layers.