Controller design using parametric neural networks

M. HashemiNejad, Junichi Murata, K. Hirasawa

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

Reducing the tracking error and finding a good arrangement for the control components such as a system's model and a controller have been the main topics of many recent papers. In this relation lack of attention to use internal structure of the Neural Network(NN) is apparently sensible; NNs have been treated as black boxes. The main objective of this article is to use more flexible NN, or parametric NN, to design a better controller. A PNN(parametric NN) can represent both of linear and nonlinear relationships explicitly and simultaneously by setting its parameters appropriately. In many cases we have some information about the system which enable us to build a linear controller for it. But of course this is not enough for treating nonlinear plants. Using PNN we could make a complimentary linearized controller and then, after starting the learning, in an online manner it will be extended to a nonlinear dominant controller.

Original languageEnglish
Pages1275-1280
Number of pages6
Publication statusPublished - Dec 1 1995
EventProceedings of the 34th SICE Annual Conference - Hokkaido, Jpn
Duration: Jul 26 1995Jul 28 1995

Other

OtherProceedings of the 34th SICE Annual Conference
CityHokkaido, Jpn
Period7/26/957/28/95

Fingerprint

Neural networks
Controllers

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

HashemiNejad, M., Murata, J., & Hirasawa, K. (1995). Controller design using parametric neural networks. 1275-1280. Paper presented at Proceedings of the 34th SICE Annual Conference, Hokkaido, Jpn, .

Controller design using parametric neural networks. / HashemiNejad, M.; Murata, Junichi; Hirasawa, K.

1995. 1275-1280 Paper presented at Proceedings of the 34th SICE Annual Conference, Hokkaido, Jpn, .

Research output: Contribution to conferencePaper

HashemiNejad, M, Murata, J & Hirasawa, K 1995, 'Controller design using parametric neural networks', Paper presented at Proceedings of the 34th SICE Annual Conference, Hokkaido, Jpn, 7/26/95 - 7/28/95 pp. 1275-1280.
HashemiNejad M, Murata J, Hirasawa K. Controller design using parametric neural networks. 1995. Paper presented at Proceedings of the 34th SICE Annual Conference, Hokkaido, Jpn, .
HashemiNejad, M. ; Murata, Junichi ; Hirasawa, K. / Controller design using parametric neural networks. Paper presented at Proceedings of the 34th SICE Annual Conference, Hokkaido, Jpn, .6 p.
@conference{fc2cf81226604beba8997c140432fa3c,
title = "Controller design using parametric neural networks",
abstract = "Reducing the tracking error and finding a good arrangement for the control components such as a system's model and a controller have been the main topics of many recent papers. In this relation lack of attention to use internal structure of the Neural Network(NN) is apparently sensible; NNs have been treated as black boxes. The main objective of this article is to use more flexible NN, or parametric NN, to design a better controller. A PNN(parametric NN) can represent both of linear and nonlinear relationships explicitly and simultaneously by setting its parameters appropriately. In many cases we have some information about the system which enable us to build a linear controller for it. But of course this is not enough for treating nonlinear plants. Using PNN we could make a complimentary linearized controller and then, after starting the learning, in an online manner it will be extended to a nonlinear dominant controller.",
author = "M. HashemiNejad and Junichi Murata and K. Hirasawa",
year = "1995",
month = "12",
day = "1",
language = "English",
pages = "1275--1280",
note = "Proceedings of the 34th SICE Annual Conference ; Conference date: 26-07-1995 Through 28-07-1995",

}

TY - CONF

T1 - Controller design using parametric neural networks

AU - HashemiNejad, M.

AU - Murata, Junichi

AU - Hirasawa, K.

PY - 1995/12/1

Y1 - 1995/12/1

N2 - Reducing the tracking error and finding a good arrangement for the control components such as a system's model and a controller have been the main topics of many recent papers. In this relation lack of attention to use internal structure of the Neural Network(NN) is apparently sensible; NNs have been treated as black boxes. The main objective of this article is to use more flexible NN, or parametric NN, to design a better controller. A PNN(parametric NN) can represent both of linear and nonlinear relationships explicitly and simultaneously by setting its parameters appropriately. In many cases we have some information about the system which enable us to build a linear controller for it. But of course this is not enough for treating nonlinear plants. Using PNN we could make a complimentary linearized controller and then, after starting the learning, in an online manner it will be extended to a nonlinear dominant controller.

AB - Reducing the tracking error and finding a good arrangement for the control components such as a system's model and a controller have been the main topics of many recent papers. In this relation lack of attention to use internal structure of the Neural Network(NN) is apparently sensible; NNs have been treated as black boxes. The main objective of this article is to use more flexible NN, or parametric NN, to design a better controller. A PNN(parametric NN) can represent both of linear and nonlinear relationships explicitly and simultaneously by setting its parameters appropriately. In many cases we have some information about the system which enable us to build a linear controller for it. But of course this is not enough for treating nonlinear plants. Using PNN we could make a complimentary linearized controller and then, after starting the learning, in an online manner it will be extended to a nonlinear dominant controller.

UR - http://www.scopus.com/inward/record.url?scp=0029532133&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029532133&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0029532133

SP - 1275

EP - 1280

ER -