Model Structure Optimization for Fuel Cell Polarization Curves

Model Structure Optimization for Fuel Cell Polarization Curves

The applications of evolutionary optimizers such as genetic algorithms, differential evolution, and various swarm optimizers to the parameter estimation of the fuel cell polarization curve models have increased. This study takes a novel approach on utilizing evolutionary optimization in fuel cell mo...

Full description

Bibliographic Details
Main Authors: Markku Ohenoja, Aki Sorsa, Kauko Leiviskä
Format: Article
Language:English
Published: MDPI AG 2018-11-01
Series:Computers
Subjects:
model identification
genetic algorithms
fuel cell
Online Access:https://www.mdpi.com/2073-431X/7/4/60
id doaj-ac1c727aa14a4c5dbbb72263523c5f57
record_format Article
spelling doaj-ac1c727aa14a4c5dbbb72263523c5f572020-11-25T00:32:58ZengMDPI AGComputers2073-431X2018-11-01746010.3390/computers7040060computers7040060Model Structure Optimization for Fuel Cell Polarization CurvesMarkku Ohenoja0Aki Sorsa1Kauko Leiviskä2Control Engineering, University of Oulu, P.O. Box 4300, FI-90014 Oulu, FinlandControl Engineering, University of Oulu, P.O. Box 4300, FI-90014 Oulu, FinlandControl Engineering, University of Oulu, P.O. Box 4300, FI-90014 Oulu, FinlandThe applications of evolutionary optimizers such as genetic algorithms, differential evolution, and various swarm optimizers to the parameter estimation of the fuel cell polarization curve models have increased. This study takes a novel approach on utilizing evolutionary optimization in fuel cell modeling. Model structure identification is performed with genetic algorithms in order to determine an optimized representation of a polarization curve model with linear model parameters. The optimization is repeated with a different set of input variables and varying model complexity. The resulted model can successfully be generalized for different fuel cells and varying operating conditions, and therefore be readily applicable to fuel cell system simulations.https://www.mdpi.com/2073-431X/7/4/60model identificationgenetic algorithmsfuel cell
collection DOAJ
language English
format Article
sources DOAJ
author Markku Ohenoja
Aki Sorsa
Kauko Leiviskä
spellingShingle Markku Ohenoja
Aki Sorsa
Kauko Leiviskä
Model Structure Optimization for Fuel Cell Polarization Curves
Computers
model identification
genetic algorithms
fuel cell
author_facet Markku Ohenoja
Aki Sorsa
Kauko Leiviskä
author_sort Markku Ohenoja
title Model Structure Optimization for Fuel Cell Polarization Curves
title_short Model Structure Optimization for Fuel Cell Polarization Curves
title_full Model Structure Optimization for Fuel Cell Polarization Curves
title_fullStr Model Structure Optimization for Fuel Cell Polarization Curves
title_full_unstemmed Model Structure Optimization for Fuel Cell Polarization Curves
title_sort model structure optimization for fuel cell polarization curves
publisher MDPI AG
series Computers
issn 2073-431X
publishDate 2018-11-01
description The applications of evolutionary optimizers such as genetic algorithms, differential evolution, and various swarm optimizers to the parameter estimation of the fuel cell polarization curve models have increased. This study takes a novel approach on utilizing evolutionary optimization in fuel cell modeling. Model structure identification is performed with genetic algorithms in order to determine an optimized representation of a polarization curve model with linear model parameters. The optimization is repeated with a different set of input variables and varying model complexity. The resulted model can successfully be generalized for different fuel cells and varying operating conditions, and therefore be readily applicable to fuel cell system simulations.
topic model identification
genetic algorithms
fuel cell
url https://www.mdpi.com/2073-431X/7/4/60
work_keys_str_mv AT markkuohenoja modelstructureoptimizationforfuelcellpolarizationcurves
AT akisorsa modelstructureoptimizationforfuelcellpolarizationcurves
AT kaukoleiviska modelstructureoptimizationforfuelcellpolarizationcurves
_version_ 1725318031662383104

Similar Items