Detail publikace

Adaptive Constrained Generalized Predictive Control Based on Neural Network

NEPEVNÝ, P.

Originální název

Adaptive Constrained Generalized Predictive Control Based on Neural Network

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

This paper presents solution of constrained Generalized Predictive Control (GPC) with autoregressive model based on neural network. Neural model is able to observe system changes and adapt itself. Algorithm was implemented in MATLAB-Simulink with aspect of future implementation to Programmable Logic Controller (PLC) B&R. The usage possibilities of this approach were tested on mathematical and physical models in soft-real-time realization. Constrained GPC algorithm was compared with classical PSD controller and advantages and disadvantages of predictive control are shown.

Klíčová slova

predictive, MPC, GPC, neural network, adaptive

Autoři

NEPEVNÝ, P.

Rok RIV

2005

Vydáno

1. 1. 2005

Nakladatel

Ing. Zdeněk Novotný CSc., Ondráčkova 105 Brno

Místo

Brno

ISBN

80-214-2889-9

Kniha

Proceedings of the 11th conference student EEICT 2005

Strany od

51

Strany do

55

Strany počet

5

BibTex

@inproceedings{BUT16289,
  author="Petr {Nepevný}",
  title="Adaptive Constrained Generalized Predictive Control Based on Neural Network",
  booktitle="Proceedings of the 11th conference student EEICT 2005",
  year="2005",
  pages="5",
  publisher="Ing. Zdeněk Novotný CSc., Ondráčkova 105 Brno",
  address="Brno",
  isbn="80-214-2889-9"
}