Control relevant long-range plant identification using recurrent neural networks

Jennie Si, Guian Zhou

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In adaptive critic control systems design as well as other control systems design schemes, e.g., model-based predictive control, the plant model has to be iterated to predict many time steps ahead into the future. A commonly used implementation is to employ a parallel identification structure. It has been justified for linear estimation that (assume that estimates to the real plant are biased) long-range prediction models are less sensitive to high frequency noise, whether actual noise or caused by model-plant mismatch. We address feasibilities of using recurrent neural networks for long-range plant identification. We examine the existence, training and performance of such recurrent neural network identifiers.

Original languageEnglish (US)
Title of host publicationProceedings of the American Control Conference
Pages857-861
Number of pages5
Volume1
StatePublished - 1995
EventProceedings of the 1995 American Control Conference. Part 1 (of 6) - Seattle, WA, USA
Duration: Jun 21 1995Jun 23 1995

Other

OtherProceedings of the 1995 American Control Conference. Part 1 (of 6)
CitySeattle, WA, USA
Period6/21/956/23/95

Fingerprint

Recurrent neural networks
Identification (control systems)
Systems analysis
Adaptive control systems
Control systems

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Si, J., & Zhou, G. (1995). Control relevant long-range plant identification using recurrent neural networks. In Proceedings of the American Control Conference (Vol. 1, pp. 857-861)

Control relevant long-range plant identification using recurrent neural networks. / Si, Jennie; Zhou, Guian.

Proceedings of the American Control Conference. Vol. 1 1995. p. 857-861.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Si, J & Zhou, G 1995, Control relevant long-range plant identification using recurrent neural networks. in Proceedings of the American Control Conference. vol. 1, pp. 857-861, Proceedings of the 1995 American Control Conference. Part 1 (of 6), Seattle, WA, USA, 6/21/95.
Si J, Zhou G. Control relevant long-range plant identification using recurrent neural networks. In Proceedings of the American Control Conference. Vol. 1. 1995. p. 857-861
Si, Jennie ; Zhou, Guian. / Control relevant long-range plant identification using recurrent neural networks. Proceedings of the American Control Conference. Vol. 1 1995. pp. 857-861
@inproceedings{09e9ef30a4754ed8956556bef240ecaf,
title = "Control relevant long-range plant identification using recurrent neural networks",
abstract = "In adaptive critic control systems design as well as other control systems design schemes, e.g., model-based predictive control, the plant model has to be iterated to predict many time steps ahead into the future. A commonly used implementation is to employ a parallel identification structure. It has been justified for linear estimation that (assume that estimates to the real plant are biased) long-range prediction models are less sensitive to high frequency noise, whether actual noise or caused by model-plant mismatch. We address feasibilities of using recurrent neural networks for long-range plant identification. We examine the existence, training and performance of such recurrent neural network identifiers.",
author = "Jennie Si and Guian Zhou",
year = "1995",
language = "English (US)",
volume = "1",
pages = "857--861",
booktitle = "Proceedings of the American Control Conference",

}

TY - GEN

T1 - Control relevant long-range plant identification using recurrent neural networks

AU - Si, Jennie

AU - Zhou, Guian

PY - 1995

Y1 - 1995

N2 - In adaptive critic control systems design as well as other control systems design schemes, e.g., model-based predictive control, the plant model has to be iterated to predict many time steps ahead into the future. A commonly used implementation is to employ a parallel identification structure. It has been justified for linear estimation that (assume that estimates to the real plant are biased) long-range prediction models are less sensitive to high frequency noise, whether actual noise or caused by model-plant mismatch. We address feasibilities of using recurrent neural networks for long-range plant identification. We examine the existence, training and performance of such recurrent neural network identifiers.

AB - In adaptive critic control systems design as well as other control systems design schemes, e.g., model-based predictive control, the plant model has to be iterated to predict many time steps ahead into the future. A commonly used implementation is to employ a parallel identification structure. It has been justified for linear estimation that (assume that estimates to the real plant are biased) long-range prediction models are less sensitive to high frequency noise, whether actual noise or caused by model-plant mismatch. We address feasibilities of using recurrent neural networks for long-range plant identification. We examine the existence, training and performance of such recurrent neural network identifiers.

UR - http://www.scopus.com/inward/record.url?scp=0029202785&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029202785&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0029202785

VL - 1

SP - 857

EP - 861

BT - Proceedings of the American Control Conference

ER -