A critical review of the most popular types of neuro control

Morteza Mohammadzaheri, Lei Chen, Steven Grainger

Research output: Contribution to journalReview article

26 Citations (Scopus)

Abstract

In this review article, the most popular types of neural network control systems are briefly introduced and their main features are reviewed. Neuro control systems are defined as control systems in which at least one artificial neural network (ANN) is directly involved in generating the control command. Initially, neural networks were mostly used to model system dynamics inversely to produce a control command which pushes the system towards a desired or reference value of the output (1989). At the next stage, neural networks were trained to track a reference model, and ANN model reference control appeared (1990). In that method, ANNs were used to extend the application of adaptive reference model control, which was a well-known control technique. This attitude towards the extension of the application of well-known control methods using ANNs was followed by the development of ANN model-predictive (1991), ANN sliding mode (1994) and ANN feedback linearization (1995) techniques. As the first category of neuro controllers, inverse dynamics ANN controllers were frequently used to form a control system together with other controllers, but this attitude faded as other types of ANN control systems were developed. However, recently, this approach has been revived. In the last decade, control system designers started to use ANNs to compensate/cancel undesired or uncertain parts of systems' dynamics to facilitate the use of well-known conventional control systems. The resultant control system usually includes two or three controllers. In this paper, applications of different ANN control systems are also addressed.

Original languageEnglish
Pages (from-to)1-11
Number of pages11
JournalAsian Journal of Control
Volume14
Issue number1
DOIs
Publication statusPublished - Jan 2012

Fingerprint

Neural networks
Control systems
Controllers
Dynamical systems
Model reference adaptive control
Feedback linearization

Keywords

  • adaptive
  • Control
  • feedback linearization
  • model reference
  • neural network
  • perceptron
  • predictive
  • radial basis

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

A critical review of the most popular types of neuro control. / Mohammadzaheri, Morteza; Chen, Lei; Grainger, Steven.

In: Asian Journal of Control, Vol. 14, No. 1, 01.2012, p. 1-11.

Research output: Contribution to journalReview article

Mohammadzaheri, Morteza ; Chen, Lei ; Grainger, Steven. / A critical review of the most popular types of neuro control. In: Asian Journal of Control. 2012 ; Vol. 14, No. 1. pp. 1-11.
@article{d81d383ed78240e492db223cb27728f6,
title = "A critical review of the most popular types of neuro control",
abstract = "In this review article, the most popular types of neural network control systems are briefly introduced and their main features are reviewed. Neuro control systems are defined as control systems in which at least one artificial neural network (ANN) is directly involved in generating the control command. Initially, neural networks were mostly used to model system dynamics inversely to produce a control command which pushes the system towards a desired or reference value of the output (1989). At the next stage, neural networks were trained to track a reference model, and ANN model reference control appeared (1990). In that method, ANNs were used to extend the application of adaptive reference model control, which was a well-known control technique. This attitude towards the extension of the application of well-known control methods using ANNs was followed by the development of ANN model-predictive (1991), ANN sliding mode (1994) and ANN feedback linearization (1995) techniques. As the first category of neuro controllers, inverse dynamics ANN controllers were frequently used to form a control system together with other controllers, but this attitude faded as other types of ANN control systems were developed. However, recently, this approach has been revived. In the last decade, control system designers started to use ANNs to compensate/cancel undesired or uncertain parts of systems' dynamics to facilitate the use of well-known conventional control systems. The resultant control system usually includes two or three controllers. In this paper, applications of different ANN control systems are also addressed.",
keywords = "adaptive, Control, feedback linearization, model reference, neural network, perceptron, predictive, radial basis",
author = "Morteza Mohammadzaheri and Lei Chen and Steven Grainger",
year = "2012",
month = "1",
doi = "10.1002/asjc.449",
language = "English",
volume = "14",
pages = "1--11",
journal = "Asian Journal of Control",
issn = "1561-8625",
publisher = "National Taiwan University (IEEB)",
number = "1",

}

TY - JOUR

T1 - A critical review of the most popular types of neuro control

AU - Mohammadzaheri, Morteza

AU - Chen, Lei

AU - Grainger, Steven

PY - 2012/1

Y1 - 2012/1

N2 - In this review article, the most popular types of neural network control systems are briefly introduced and their main features are reviewed. Neuro control systems are defined as control systems in which at least one artificial neural network (ANN) is directly involved in generating the control command. Initially, neural networks were mostly used to model system dynamics inversely to produce a control command which pushes the system towards a desired or reference value of the output (1989). At the next stage, neural networks were trained to track a reference model, and ANN model reference control appeared (1990). In that method, ANNs were used to extend the application of adaptive reference model control, which was a well-known control technique. This attitude towards the extension of the application of well-known control methods using ANNs was followed by the development of ANN model-predictive (1991), ANN sliding mode (1994) and ANN feedback linearization (1995) techniques. As the first category of neuro controllers, inverse dynamics ANN controllers were frequently used to form a control system together with other controllers, but this attitude faded as other types of ANN control systems were developed. However, recently, this approach has been revived. In the last decade, control system designers started to use ANNs to compensate/cancel undesired or uncertain parts of systems' dynamics to facilitate the use of well-known conventional control systems. The resultant control system usually includes two or three controllers. In this paper, applications of different ANN control systems are also addressed.

AB - In this review article, the most popular types of neural network control systems are briefly introduced and their main features are reviewed. Neuro control systems are defined as control systems in which at least one artificial neural network (ANN) is directly involved in generating the control command. Initially, neural networks were mostly used to model system dynamics inversely to produce a control command which pushes the system towards a desired or reference value of the output (1989). At the next stage, neural networks were trained to track a reference model, and ANN model reference control appeared (1990). In that method, ANNs were used to extend the application of adaptive reference model control, which was a well-known control technique. This attitude towards the extension of the application of well-known control methods using ANNs was followed by the development of ANN model-predictive (1991), ANN sliding mode (1994) and ANN feedback linearization (1995) techniques. As the first category of neuro controllers, inverse dynamics ANN controllers were frequently used to form a control system together with other controllers, but this attitude faded as other types of ANN control systems were developed. However, recently, this approach has been revived. In the last decade, control system designers started to use ANNs to compensate/cancel undesired or uncertain parts of systems' dynamics to facilitate the use of well-known conventional control systems. The resultant control system usually includes two or three controllers. In this paper, applications of different ANN control systems are also addressed.

KW - adaptive

KW - Control

KW - feedback linearization

KW - model reference

KW - neural network

KW - perceptron

KW - predictive

KW - radial basis

UR - http://www.scopus.com/inward/record.url?scp=84863011314&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863011314&partnerID=8YFLogxK

U2 - 10.1002/asjc.449

DO - 10.1002/asjc.449

M3 - Review article

AN - SCOPUS:84863011314

VL - 14

SP - 1

EP - 11

JO - Asian Journal of Control

JF - Asian Journal of Control

SN - 1561-8625

IS - 1

ER -