An adaptive neural network (NN)-based output feedback controller is proposed to deliver a desired tracking performance for a class of discrete-time nonlinear systems, which is represented in non-strict feedback form. The NN backstepping approach is utilized to design the adaptive output feedback controller consisting of: 1) a NN observer to estimate the system states with the input-output data, and 2) two NNs to generate the virtual and actual control inputs, respectively. The non-causal problem in the discrete-time backstepping design is avoided by using the universal NN approximator. The persistence excitation (PE) condition is relaxed both in the NN observer and NN controller design. The uniformly ultimate boundedness (UUB) of the closed-loop tracking error, the state estimation errors and the NN weight estimates is shown.

Meeting Name

2004 American Control Conference, 2004


Electrical and Computer Engineering

Second Department

Computer Science


National Science Foundation (U.S.)

Keywords and Phrases

Closed Loop Systems; Control System Synthesis; Neurocontrollers; Non-Linear Control Systems; Adaptive control systems; Discrete-time systems

Document Type

Article - Conference proceedings

Document Version

Final Version

File Type





© 2004 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Publication Date

01 Jan 2004