Adaptive neural network control for nonlinear output-feedback systems under disturbances with unknown bounds

This paper is concerned with the problem of adaptive backstepping neural network tracking control for a class of output feedback systems with unknown functions under bounded disturbances whose boundaries is unknown. Unknown functions are approximated via online radial basis function (RBF) neural network, high order continuous differentiable functions are introduced into Lyapunov function to realize the estimation of unknown parameters and unknown boundary, and a new dead zone function is designed to replace symbolic function to realize the continuity of virtual control. During the design process, the backstepping design method is applied to deal with the cross terms generated by the tuning function. Barbalat's lemma proves that all the signals of closed-loop system are bounded and the output tracking error converges to an arbitrarily small neighborhood of the origin. A simulation example are given to illustrate the effectiveness of the control scheme. Copyright (C) 2020 The Authors.