18th International Conference on Process Control

Piecewise-Linear Neural Models for Process Control

P. Doležel, I. Taufer, J. Mareš
University of Pardubice

Abstract

There is introduced an algorithm which provides piecewise-linear model of nonlinear plant using artificial neural networks, in this paper. That piecewise-linear model is precise and each linear submodel is valid in some neighbourhood of actual plant state. This model can be used for plant control design. There is presented an example at the end of this paper, where defined nonlinear plant is controlled via Pole Assignment technique using piecewise-linear neural model and control response is compared to data obtained by common PI controller.

Full paper

043.pdf

Session

Linear and Non-linear Control System Design (Poster)

Reference

Doležel, P.; Taufer, I.; Mareš, J.: Piecewise-Linear Neural Models for Process Control. Editors: Fikar, M. and Kvasnica, M., In Proceedings of the 18th International Conference on Process Control, Tatranská Lomnica, Slovakia, June 14 – 17, 296–300, 2011.

BibTeX
@inProceedings{pc2011-043,
author = {Dole\v{z}el, P. and Taufer, I. and Mare\v{s}, J.},
title = {Piecewise-Linear Neural Models for Process Control},
booktitle = {Proceedings of the 18th International Conference on Process Control},
year = {2011},
pages = {296-300},
editor = {Fikar, M. and Kvasnica, M.},
address = {Tatransk\'a Lomnica, Slovakia},
publisher = {Slovak University of Technology in Bratislava},
url = {http://www.kirp.chtf.stuba.sk/pc11/data/papers/043.pdf}}
© 2011 Institute of Information Engineering, Automation and Mathematics, FCFT STU in Bratislava. All rights reserved.