Publication detail

Simple Neural Network-Based Adaptive Controller for Heating System

PIVOŇKA, P., VELEBA, V.

Original Title

Simple Neural Network-Based Adaptive Controller for Heating System

Type

conference paper

Language

English

Original Abstract

The algorithm for the semi-inversion controller has been designed for adaptive control based on neural networks. This controller originally designed for linear systems proved to have favorable characteristics also for considerably non-linear systems. The algorithm deals with extreme inversion controlling actions occurring in inversion control. We used the semi-inversion controller for control a real system – laboratory hot-air system model. The efficient of control algorithm we demonstrate by control MIMO system with two parameters – the airflow and the temperature inside the tunnel. The hot-air system displays negative effects commonly occurring in industrial applications – different static amplifications at different operating points, large offset increasing with time, dead zone and noise.

Keywords

Adaptive Control, Neural Networks, Simple Neural Controller

Authors

PIVOŇKA, P., VELEBA, V.

RIV year

2004

Released

8. 9. 2004

Publisher

Rektor der Hochschule Zitttau/Görlitz

Location

Zittau, Germany

ISBN

3-9808089-5-5

Book

Proceedings East West Fuzzy Colloquium 2004

Pages from

163

Pages to

168

Pages count

6

BibTex

@inproceedings{BUT11409,
  author="Petr {Pivoňka} and Václav {Veleba}",
  title="Simple Neural Network-Based Adaptive Controller for Heating System",
  booktitle="Proceedings East West Fuzzy Colloquium 2004",
  year="2004",
  pages="6",
  publisher="Rektor der Hochschule Zitttau/Görlitz",
  address="Zittau, Germany",
  isbn="3-9808089-5-5"
}