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

Muhammad Saleheen Aftab; Muhammad Shafiq

doi:10.1016/j.isatra.2015.09.003

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

ISA Trans. 2015 Nov:59:363-74. doi: 10.1016/j.isatra.2015.09.003. Epub 2015 Oct 9.

Authors

Muhammad Saleheen Aftab¹, Muhammad Shafiq²

Affiliations

¹ Department of Electrical & Computer Engineering, Sultan Qaboos University, Muscat, Oman. Electronic address: saleheen.aftab@gmail.com.
² Department of Electrical & Computer Engineering, Sultan Qaboos University, Muscat, Oman. Electronic address: mshafiq@squ.edu.om.

PMID: 26456201
DOI: 10.1016/j.isatra.2015.09.003

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.

Keywords: Decentralized control; Direct adaptive inverse control; Indirect adaptive Inverse control; Lyapunov function Neural tracking; Stable adaptive tracking.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms
Arm / physiology
Calibration
Computer Simulation
Computer Systems
Equipment Design
Humans
Machine Learning
Neural Networks, Computer*
Nonlinear Dynamics*
Robotics
User-Computer Interface