Hybridized GA-optimization of Neural Dynamic Model for Nonlinear Process

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21220%2F12%3A00198066" target="_blank" >RIV/68407700:21220/12:00198066 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/CarpathianCC.2012.6228644" target="_blank" >http://dx.doi.org/10.1109/CarpathianCC.2012.6228644</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CarpathianCC.2012.6228644" target="_blank" >10.1109/CarpathianCC.2012.6228644</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Hybridized GA-optimization of Neural Dynamic Model for Nonlinear Process

Popis výsledku v původním jazyce

Neural networks as universal approximators possess capability to model complex nonlinear phenomena. However, when almost nothing is known about the modeled dynamic process it is difficult to determine important parameters like the number of neurons or the size of regressor vector (dynamic order). In order to avoid suboptimal settings for a dynamic model using trial-and-error method, genetic algorithm is used for optimizing the neural dynamic model. To improve the results even more, the genetic optimization is hybridized with a local optimizer in the form of Levenberg-Marquardt algorithm commonly used for neural network training. Here a neural model of biomass-fired boiler emissions is considered, which is eventually intended for predictive control. Series-parallel NARX model is used with two hidden layer neural network and tansigmoid transfer functions. The simpler neural model structure will be computationally less expensive what is important for online predictive control. The results

Název v anglickém jazyce

Hybridized GA-optimization of Neural Dynamic Model for Nonlinear Process

Popis výsledku anglicky

Neural networks as universal approximators possess capability to model complex nonlinear phenomena. However, when almost nothing is known about the modeled dynamic process it is difficult to determine important parameters like the number of neurons or the size of regressor vector (dynamic order). In order to avoid suboptimal settings for a dynamic model using trial-and-error method, genetic algorithm is used for optimizing the neural dynamic model. To improve the results even more, the genetic optimization is hybridized with a local optimizer in the form of Levenberg-Marquardt algorithm commonly used for neural network training. Here a neural model of biomass-fired boiler emissions is considered, which is eventually intended for predictive control. Series-parallel NARX model is used with two hidden layer neural network and tansigmoid transfer functions. The simpler neural model structure will be computationally less expensive what is important for online predictive control. The results

Druh

D - Stať ve sborníku

CEP obor

JB - Senzory, čidla, měření a regulace

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2012

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 13th International Carpathian Control Conference

ISBN

978-1-4577-1866-3

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

227-232

Název nakladatele

Technical University of Košice

Místo vydání

Košice

Místo konání akce

Podbánské

Datum konání akce

28. 5. 2012

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—