This paper is concerned with the tracking control problem of a class of non-strict-feedback nonlinear systems with unmodeled dynamics and time-delay. In the backstepping procedure, a dynamic signal is designed to handle the unmodeled dynamics and the Lyapunov–Krasovskii functions are applied to compensate for the effect of time delay. Meanwhile, a neural network-based approximator is used to approximate the unknown nonlinear functions in the system. It is proved by the theoretical analysis that the presented controller guarantees the semi-global boundedness of all signals in the closed-loop systems, and the output tracking error eventually converges to a small area around zero. Simulation results are presented to illustrate the validity of the proposed approach.

Backstepping, Neural networks, Time delay, Unmodeled dynamics
Department of Systems and Computer Engineering

Wang, H. (Huanqing), Zou, Y. (Yuchun), Liu, P, Zhao, X. (Xudong), Bao, J. (Jialei), & Zhou, Y. (Yucheng). (2019). Neural-network-based tracking Control for a Class of time-delay nonlinear systems with unmodeled dynamics. Neurocomputing. doi:10.1016/j.neucom.2018.10.091