Artificial Neural Networks for On-Line Trained Controllers

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F01%3APU21008" target="_blank" >RIV/00216305:26220/01:PU21008 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Artificial Neural Networks for On-Line Trained Controllers

Popis výsledku v původním jazyce

This paper deals with the use of artificial neural networks employed as an on-line trained controller for a real process and simulation model control. Well-known back-propagation method is used as a learning algorithm intended to minimize the differencebetween the plant?s actual response and the desired reference signal. The influence of neural network?s parameters on a controlled plant output is discussed. We also attempted to find the rules of these parameters adjustment in view of the type of a trannsfer function in Laplace transform and tested the robustness of our controller burdened with the error signal. Some simulation and real process control results are also presented to evaluate the proposed design. Discussed in the last chapter are the possibilities of creating an adaptive neural controller.

Název v anglickém jazyce

Artificial Neural Networks for On-Line Trained Controllers

Popis výsledku anglicky

This paper deals with the use of artificial neural networks employed as an on-line trained controller for a real process and simulation model control. Well-known back-propagation method is used as a learning algorithm intended to minimize the differencebetween the plant?s actual response and the desired reference signal. The influence of neural network?s parameters on a controlled plant output is discussed. We also attempted to find the rules of these parameters adjustment in view of the type of a trannsfer function in Laplace transform and tested the robustness of our controller burdened with the error signal. Some simulation and real process control results are also presented to evaluate the proposed design. Discussed in the last chapter are the possibilities of creating an adaptive neural controller.

Druh

C - Kapitola v odborné knize

CEP obor

JB - Senzory, čidla, měření a regulace

OECD FORD obor

—

Projekt

<a href="/cs/project/GA102%2F01%2F1485" target="_blank" >GA102/01/1485: Prostředí pro vývoj, modelování a aplikaci heterogenních systémů</a><br>

Návaznosti

Z - Vyzkumny zamer (s odkazem do CEZ)

Rok uplatnění

2001

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název knihy nebo sborníku

Advances in Systems Science: Measurement, Circuits and Control

ISBN

960-8052-39-4

Počet stran výsledku

6

Strana od-do

189-194

Počet stran knihy

—

Název nakladatele

Published by WSES Press, http://www.worldses.org

Místo vydání

http://www.worldses.org

Kód UT WoS kapitoly

—