Neural networks for tracking of unknown SISO discrete-time nonlinear dynamic systems.

Journal: ISA transactions
Published Date:

Abstract

This article presents a Lyapunov function based neural network tracking (LNT) strategy for single-input, single-output (SISO) discrete-time nonlinear dynamic systems. The proposed LNT architecture is composed of two feedforward neural networks operating as controller and estimator. A Lyapunov function based back propagation learning algorithm is used for online adjustment of the controller and estimator parameters. The controller and estimator error convergence and closed-loop system stability analysis is performed by Lyapunov stability theory. Moreover, two simulation examples and one real-time experiment are investigated as case studies. The achieved results successfully validate the controller performance.

Authors

  • Muhammad Saleheen Aftab
    Department of Electrical & Computer Engineering, Sultan Qaboos University, Muscat, Oman. Electronic address: saleheen.aftab@gmail.com.
  • Muhammad Shafiq
    Department of Electrical & Computer Engineering, Sultan Qaboos University, Muscat, Oman. Electronic address: mshafiq@squ.edu.om.