Neurocontrol II

High precision control achieved using approximate inverse dynamics models

Csaba Szepesvari, A. Lőrincz

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

It is common that artificial neural networks (ANNs) are used for approximating the inverse dynamics of a plant. In the accompanying paper a self-organizing ANN model for associative identification of the inverse dynamics was introduced. Here we proposed the use of approximate inverse dynamic models for both Static and Dynamic State (SDS) feedback control. This compound controller is capable of high-precision control even when the inverse dynamics is just qualitatively modeled or the plant's dynamics is perturbed. Properties of SDS Feedback Controller in learning the inverse dynamics as well as comparisons with other methods are discussed. An example is presented when a chaotic plant, a bioreactor, is controlled using the SDS Controller. We found that the SDS Controller can compensate model mismatches that otherwise would lead to an untolerably large error if a tradition controller were used.

Original languageEnglish
Pages (from-to)897-920
Number of pages24
JournalNeural Network World
Volume6
Issue number6
Publication statusPublished - 1996

Fingerprint

Dynamic models
Neural Networks (Computer)
Bioreactors
Controllers
Learning
State feedback
Neural networks
Feedback control
Identification (control systems)

ASJC Scopus subject areas

  • Software

Cite this

Neurocontrol II : High precision control achieved using approximate inverse dynamics models. / Szepesvari, Csaba; Lőrincz, A.

In: Neural Network World, Vol. 6, No. 6, 1996, p. 897-920.

Research output: Contribution to journalArticle

@article{2ee8a6bd012346bea1feeb635d30be89,
title = "Neurocontrol II: High precision control achieved using approximate inverse dynamics models",
abstract = "It is common that artificial neural networks (ANNs) are used for approximating the inverse dynamics of a plant. In the accompanying paper a self-organizing ANN model for associative identification of the inverse dynamics was introduced. Here we proposed the use of approximate inverse dynamic models for both Static and Dynamic State (SDS) feedback control. This compound controller is capable of high-precision control even when the inverse dynamics is just qualitatively modeled or the plant's dynamics is perturbed. Properties of SDS Feedback Controller in learning the inverse dynamics as well as comparisons with other methods are discussed. An example is presented when a chaotic plant, a bioreactor, is controlled using the SDS Controller. We found that the SDS Controller can compensate model mismatches that otherwise would lead to an untolerably large error if a tradition controller were used.",
author = "Csaba Szepesvari and A. Lőrincz",
year = "1996",
language = "English",
volume = "6",
pages = "897--920",
journal = "Neural Network World",
issn = "1210-0552",
publisher = "Institute of Computer Science",
number = "6",

}

TY - JOUR

T1 - Neurocontrol II

T2 - High precision control achieved using approximate inverse dynamics models

AU - Szepesvari, Csaba

AU - Lőrincz, A.

PY - 1996

Y1 - 1996

N2 - It is common that artificial neural networks (ANNs) are used for approximating the inverse dynamics of a plant. In the accompanying paper a self-organizing ANN model for associative identification of the inverse dynamics was introduced. Here we proposed the use of approximate inverse dynamic models for both Static and Dynamic State (SDS) feedback control. This compound controller is capable of high-precision control even when the inverse dynamics is just qualitatively modeled or the plant's dynamics is perturbed. Properties of SDS Feedback Controller in learning the inverse dynamics as well as comparisons with other methods are discussed. An example is presented when a chaotic plant, a bioreactor, is controlled using the SDS Controller. We found that the SDS Controller can compensate model mismatches that otherwise would lead to an untolerably large error if a tradition controller were used.

AB - It is common that artificial neural networks (ANNs) are used for approximating the inverse dynamics of a plant. In the accompanying paper a self-organizing ANN model for associative identification of the inverse dynamics was introduced. Here we proposed the use of approximate inverse dynamic models for both Static and Dynamic State (SDS) feedback control. This compound controller is capable of high-precision control even when the inverse dynamics is just qualitatively modeled or the plant's dynamics is perturbed. Properties of SDS Feedback Controller in learning the inverse dynamics as well as comparisons with other methods are discussed. An example is presented when a chaotic plant, a bioreactor, is controlled using the SDS Controller. We found that the SDS Controller can compensate model mismatches that otherwise would lead to an untolerably large error if a tradition controller were used.

UR - http://www.scopus.com/inward/record.url?scp=0030411818&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030411818&partnerID=8YFLogxK

M3 - Article

VL - 6

SP - 897

EP - 920

JO - Neural Network World

JF - Neural Network World

SN - 1210-0552

IS - 6

ER -