A new neural network and pole placement based adaptive composite controller

A. Hussain; A. S. Zayed; L. S. Smith

doi:10.1109/INMIC.2001.995349

A new neural network and pole placement based adaptive composite controller

A. Hussain^*
, A. S. Zayed
, L. S. Smith

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

13 Scopus citations

Abstract

The paper describes a new composite control method combining a neural network estimator with a conventional pole-placement based adaptive controller. The neural network estimation technique presented by Hussain (2000) is particularly effective when there is no complete plant information, or when considering a controlled plant as a 'black box'. In the proposed composite controller, the neural network estimator weights are adapted online to minimise the identification error, and these weights are fed into a robust self-tuning PID controller which provides an adaptive mechanism to ensure that the closed loop poles are placed at the desired positions. Simulation results show that the proposed method applies to general linear or nonlinear control systems.

Original language	English
Title of host publication	Proceedings - IEEE lnternational Multi Topic Conference 2001
Subtitle of host publication	Technology for the 21st Century, IEEE INMIC 2001
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	267-271
Number of pages	5
ISBN (Electronic)	0780374061, 9780780374065
DOIs	https://doi.org/10.1109/INMIC.2001.995349
State	Published - 2001
Externally published	Yes
Event	1st IEEE lnternational Multi Topic Conference, IEEE INMIC 2001 - Lahore, Pakistan Duration: 28 Dec 2001 → 30 Dec 2001

Publication series

Name	Proceedings - IEEE lnternational Multi Topic Conference 2001: Technology for the 21st Century, IEEE INMIC 2001

Conference

Conference	1st IEEE lnternational Multi Topic Conference, IEEE INMIC 2001
Country/Territory	Pakistan
City	Lahore
Period	28/12/01 → 30/12/01

Bibliographical note

Publisher Copyright:
© 2001 IEEE.

ASJC Scopus subject areas

Control and Systems Engineering
Computer Science Applications
Computer Networks and Communications
Software

Access to Document

10.1109/INMIC.2001.995349

Cite this

Hussain, A., Zayed, A. S., & Smith, L. S. (2001). A new neural network and pole placement based adaptive composite controller. In Proceedings - IEEE lnternational Multi Topic Conference 2001: Technology for the 21st Century, IEEE INMIC 2001 (pp. 267-271). Article 995349 (Proceedings - IEEE lnternational Multi Topic Conference 2001: Technology for the 21st Century, IEEE INMIC 2001). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/INMIC.2001.995349

Hussain, A. ; Zayed, A. S. ; Smith, L. S. / A new neural network and pole placement based adaptive composite controller. Proceedings - IEEE lnternational Multi Topic Conference 2001: Technology for the 21st Century, IEEE INMIC 2001. Institute of Electrical and Electronics Engineers Inc., 2001. pp. 267-271 (Proceedings - IEEE lnternational Multi Topic Conference 2001: Technology for the 21st Century, IEEE INMIC 2001).

@inproceedings{036359895cd741dfa6ec7820a679be0b,

title = "A new neural network and pole placement based adaptive composite controller",

abstract = "The paper describes a new composite control method combining a neural network estimator with a conventional pole-placement based adaptive controller. The neural network estimation technique presented by Hussain (2000) is particularly effective when there is no complete plant information, or when considering a controlled plant as a 'black box'. In the proposed composite controller, the neural network estimator weights are adapted online to minimise the identification error, and these weights are fed into a robust self-tuning PID controller which provides an adaptive mechanism to ensure that the closed loop poles are placed at the desired positions. Simulation results show that the proposed method applies to general linear or nonlinear control systems.",

author = "A. Hussain and Zayed, \{A. S.\} and Smith, \{L. S.\}",

note = "Publisher Copyright: {\textcopyright} 2001 IEEE.; 1st IEEE lnternational Multi Topic Conference, IEEE INMIC 2001 ; Conference date: 28-12-2001 Through 30-12-2001",

year = "2001",

doi = "10.1109/INMIC.2001.995349",

language = "English",

series = "Proceedings - IEEE lnternational Multi Topic Conference 2001: Technology for the 21st Century, IEEE INMIC 2001",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "267--271",

booktitle = "Proceedings - IEEE lnternational Multi Topic Conference 2001",

address = "United States",

}

Hussain, A, Zayed, AS & Smith, LS 2001, A new neural network and pole placement based adaptive composite controller. in Proceedings - IEEE lnternational Multi Topic Conference 2001: Technology for the 21st Century, IEEE INMIC 2001., 995349, Proceedings - IEEE lnternational Multi Topic Conference 2001: Technology for the 21st Century, IEEE INMIC 2001, Institute of Electrical and Electronics Engineers Inc., pp. 267-271, 1st IEEE lnternational Multi Topic Conference, IEEE INMIC 2001, Lahore, Pakistan, 28/12/01. https://doi.org/10.1109/INMIC.2001.995349

A new neural network and pole placement based adaptive composite controller. / Hussain, A.; Zayed, A. S.; Smith, L. S.
Proceedings - IEEE lnternational Multi Topic Conference 2001: Technology for the 21st Century, IEEE INMIC 2001. Institute of Electrical and Electronics Engineers Inc., 2001. p. 267-271 995349 (Proceedings - IEEE lnternational Multi Topic Conference 2001: Technology for the 21st Century, IEEE INMIC 2001).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A new neural network and pole placement based adaptive composite controller

AU - Hussain, A.

AU - Zayed, A. S.

AU - Smith, L. S.

PY - 2001

Y1 - 2001

N2 - The paper describes a new composite control method combining a neural network estimator with a conventional pole-placement based adaptive controller. The neural network estimation technique presented by Hussain (2000) is particularly effective when there is no complete plant information, or when considering a controlled plant as a 'black box'. In the proposed composite controller, the neural network estimator weights are adapted online to minimise the identification error, and these weights are fed into a robust self-tuning PID controller which provides an adaptive mechanism to ensure that the closed loop poles are placed at the desired positions. Simulation results show that the proposed method applies to general linear or nonlinear control systems.

AB - The paper describes a new composite control method combining a neural network estimator with a conventional pole-placement based adaptive controller. The neural network estimation technique presented by Hussain (2000) is particularly effective when there is no complete plant information, or when considering a controlled plant as a 'black box'. In the proposed composite controller, the neural network estimator weights are adapted online to minimise the identification error, and these weights are fed into a robust self-tuning PID controller which provides an adaptive mechanism to ensure that the closed loop poles are placed at the desired positions. Simulation results show that the proposed method applies to general linear or nonlinear control systems.

UR - https://www.scopus.com/pages/publications/84968531499

U2 - 10.1109/INMIC.2001.995349

DO - 10.1109/INMIC.2001.995349

M3 - Conference contribution

AN - SCOPUS:84968531499

T3 - Proceedings - IEEE lnternational Multi Topic Conference 2001: Technology for the 21st Century, IEEE INMIC 2001

SP - 267

EP - 271

BT - Proceedings - IEEE lnternational Multi Topic Conference 2001

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 1st IEEE lnternational Multi Topic Conference, IEEE INMIC 2001

Y2 - 28 December 2001 through 30 December 2001

ER -

Hussain A, Zayed AS, Smith LS. A new neural network and pole placement based adaptive composite controller. In Proceedings - IEEE lnternational Multi Topic Conference 2001: Technology for the 21st Century, IEEE INMIC 2001. Institute of Electrical and Electronics Engineers Inc. 2001. p. 267-271. 995349. (Proceedings - IEEE lnternational Multi Topic Conference 2001: Technology for the 21st Century, IEEE INMIC 2001). doi: 10.1109/INMIC.2001.995349

A new neural network and pole placement based adaptive composite controller

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this