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

Muhammad Saleheen Aftab, Muhammad Shafiq

Research output: Contribution to journalArticle

9 Citations (Scopus)

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.

Original languageEnglish
Pages (from-to)363-374
Number of pages12
JournalISA Transactions
Volume59
DOIs
Publication statusPublished - Nov 1 2015

Fingerprint

Nonlinear Dynamic System
controllers
Dynamical systems
Discrete-time
estimators
Neural Networks
Neural networks
Controller
Liapunov functions
Unknown
Controllers
output
Output
Lyapunov functions
Lyapunov Function
tracking networks
Estimator
systems stability
Back-propagation Algorithm
Error Estimator

Keywords

  • Decentralized control
  • Direct adaptive inverse control
  • Indirect adaptive Inverse control
  • Lyapunov function Neural tracking
  • Stable adaptive tracking

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Applied Mathematics
  • Instrumentation

Cite this

Neural networks for tracking of unknown SISO discrete-time nonlinear dynamic systems. / Aftab, Muhammad Saleheen; Shafiq, Muhammad.

In: ISA Transactions, Vol. 59, 01.11.2015, p. 363-374.

Research output: Contribution to journalArticle

@article{124c2c496e68418998faa15e251e97b2,
title = "Neural networks for tracking of unknown SISO discrete-time nonlinear dynamic systems",
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",
author = "Aftab, {Muhammad Saleheen} and Muhammad Shafiq",
year = "2015",
month = "11",
day = "1",
doi = "10.1016/j.isatra.2015.09.003",
language = "English",
volume = "59",
pages = "363--374",
journal = "ISA Transactions",
issn = "0019-0578",
publisher = "ISA - Instrumentation, Systems, and Automation Society",

}

TY - JOUR

T1 - Neural networks for tracking of unknown SISO discrete-time nonlinear dynamic systems

AU - Aftab, Muhammad Saleheen

AU - Shafiq, Muhammad

PY - 2015/11/1

Y1 - 2015/11/1

N2 - 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.

AB - 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.

KW - Decentralized control

KW - Direct adaptive inverse control

KW - Indirect adaptive Inverse control

KW - Lyapunov function Neural tracking

KW - Stable adaptive tracking

UR - http://www.scopus.com/inward/record.url?scp=84947584344&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84947584344&partnerID=8YFLogxK

U2 - 10.1016/j.isatra.2015.09.003

DO - 10.1016/j.isatra.2015.09.003

M3 - Article

VL - 59

SP - 363

EP - 374

JO - ISA Transactions

JF - ISA Transactions

SN - 0019-0578

ER -