Two-stage neural network architecture for feedback control of dynamic systems

Stephen Phillips, Christoph Mueller-Dott

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper we investigate system identification and the design of a controller using neural networks. A two-stage neural network design for controllers using single-layer structures with functional enhancements is introduced. This neural network architecture allows the design of a controller with less a priori knowledge about the plant as well as allowing for nonlinear plants. The paper also addresses the special characteristics and problems concerning the use of neural networks in control and demonstrates their performance by showing the successful implementation of a nonlinear control example via simulation.

Original languageEnglish (US)
Pages (from-to)353-365
Number of pages13
JournalAnalog Integrated Circuits and Signal Processing
Volume2
Issue number4
StatePublished - Nov 1992
Externally publishedYes

Fingerprint

Network architecture
Feedback control
Dynamical systems
Neural networks
Controllers
Identification (control systems)

ASJC Scopus subject areas

  • Hardware and Architecture
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Two-stage neural network architecture for feedback control of dynamic systems. / Phillips, Stephen; Mueller-Dott, Christoph.

In: Analog Integrated Circuits and Signal Processing, Vol. 2, No. 4, 11.1992, p. 353-365.

Research output: Contribution to journalArticle

@article{901be3e80ce44ba2a09f2305d3a81c4d,
title = "Two-stage neural network architecture for feedback control of dynamic systems",
abstract = "In this paper we investigate system identification and the design of a controller using neural networks. A two-stage neural network design for controllers using single-layer structures with functional enhancements is introduced. This neural network architecture allows the design of a controller with less a priori knowledge about the plant as well as allowing for nonlinear plants. The paper also addresses the special characteristics and problems concerning the use of neural networks in control and demonstrates their performance by showing the successful implementation of a nonlinear control example via simulation.",
author = "Stephen Phillips and Christoph Mueller-Dott",
year = "1992",
month = "11",
language = "English (US)",
volume = "2",
pages = "353--365",
journal = "Analog Integrated Circuits and Signal Processing",
issn = "0925-1030",
publisher = "Springer Netherlands",
number = "4",

}

TY - JOUR

T1 - Two-stage neural network architecture for feedback control of dynamic systems

AU - Phillips, Stephen

AU - Mueller-Dott, Christoph

PY - 1992/11

Y1 - 1992/11

N2 - In this paper we investigate system identification and the design of a controller using neural networks. A two-stage neural network design for controllers using single-layer structures with functional enhancements is introduced. This neural network architecture allows the design of a controller with less a priori knowledge about the plant as well as allowing for nonlinear plants. The paper also addresses the special characteristics and problems concerning the use of neural networks in control and demonstrates their performance by showing the successful implementation of a nonlinear control example via simulation.

AB - In this paper we investigate system identification and the design of a controller using neural networks. A two-stage neural network design for controllers using single-layer structures with functional enhancements is introduced. This neural network architecture allows the design of a controller with less a priori knowledge about the plant as well as allowing for nonlinear plants. The paper also addresses the special characteristics and problems concerning the use of neural networks in control and demonstrates their performance by showing the successful implementation of a nonlinear control example via simulation.

UR - http://www.scopus.com/inward/record.url?scp=0026954993&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026954993&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0026954993

VL - 2

SP - 353

EP - 365

JO - Analog Integrated Circuits and Signal Processing

JF - Analog Integrated Circuits and Signal Processing

SN - 0925-1030

IS - 4

ER -