Controller design using parametric neural networks

M. HashemiNejad, Junichi Murata, K. Hirasawa

Research output: Contribution to conferencePaperpeer-review

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

All Science Journal Classification (ASJC) codes

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

Fingerprint Dive into the research topics of 'Controller design using parametric neural networks'. Together they form a unique fingerprint.

Cite this