Gas composition modeling in a reformed methanol fuel cell system using adaptive neuro-fuzzy inference systems

Kristian Kjær Justesen*, Søren Juhl Andreasen, Hamid Reza Shaker, Mikkel Præstholm Ehmsen, John Andersen

*Kontaktforfatter for dette arbejde

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

Resumé

This work presents a method for modeling the gas composition in a Reformed Methanol Fuel Cell system. The method is based on Adaptive Neuro-Fuzzy- Inference-Systems which are trained on experimental data. The developed models are of the H2, CO2, CO and CH3OH mass flows of the reformed gas. The ANFIS models are able to predict the mass flows with mean absolute errors for the H2 and CO2 models of less than 1% and 6.37% for the CO model and 4.56% for the CH3OH model. The models have a wide range of applications such as dynamic modeling, stoichiometry observation and control, advanced control algorithms, or fuel cell diagnostics systems.

OriginalsprogEngelsk
TidsskriftInternational Journal of Hydrogen Energy
Vol/bind38
Udgave nummer25
Sider (fra-til)10577-10584
Antal sider8
ISSN0360-3199
DOI
StatusUdgivet - 21. aug. 2013
Udgivet eksterntJa

Fingeraftryk

Methanol fuels
gas composition
Adaptive systems
Fuzzy inference
inference
fuel cells
Fuel cells
methyl alcohol
Chemical analysis
Gases
mass flow
Stoichiometry
stoichiometry
gases

Citer dette

Justesen, Kristian Kjær ; Andreasen, Søren Juhl ; Shaker, Hamid Reza ; Ehmsen, Mikkel Præstholm ; Andersen, John . / Gas composition modeling in a reformed methanol fuel cell system using adaptive neuro-fuzzy inference systems. I: International Journal of Hydrogen Energy. 2013 ; Bind 38, Nr. 25. s. 10577-10584.
@article{5119323626484a3e9cefcb92bc7259ad,
title = "Gas composition modeling in a reformed methanol fuel cell system using adaptive neuro-fuzzy inference systems",
abstract = "This work presents a method for modeling the gas composition in a Reformed Methanol Fuel Cell system. The method is based on Adaptive Neuro-Fuzzy- Inference-Systems which are trained on experimental data. The developed models are of the H2, CO2, CO and CH3OH mass flows of the reformed gas. The ANFIS models are able to predict the mass flows with mean absolute errors for the H2 and CO2 models of less than 1{\%} and 6.37{\%} for the CO model and 4.56{\%} for the CH3OH model. The models have a wide range of applications such as dynamic modeling, stoichiometry observation and control, advanced control algorithms, or fuel cell diagnostics systems.",
keywords = "ANFIS, Fuzzy-logic and neural networks, Gas composition modeling, HTPEM fuel cell, Methanol, Reformed Methanol Fuel Cell",
author = "Justesen, {Kristian Kj{\ae}r} and Andreasen, {S{\o}ren Juhl} and Shaker, {Hamid Reza} and Ehmsen, {Mikkel Pr{\ae}stholm} and John Andersen",
year = "2013",
month = "8",
day = "21",
doi = "10.1016/j.ijhydene.2013.06.013",
language = "English",
volume = "38",
pages = "10577--10584",
journal = "International Journal of Hydrogen Energy",
issn = "0360-3199",
publisher = "Elsevier",
number = "25",

}

Gas composition modeling in a reformed methanol fuel cell system using adaptive neuro-fuzzy inference systems. / Justesen, Kristian Kjær; Andreasen, Søren Juhl; Shaker, Hamid Reza; Ehmsen, Mikkel Præstholm; Andersen, John .

I: International Journal of Hydrogen Energy, Bind 38, Nr. 25, 21.08.2013, s. 10577-10584.

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

TY - JOUR

T1 - Gas composition modeling in a reformed methanol fuel cell system using adaptive neuro-fuzzy inference systems

AU - Justesen, Kristian Kjær

AU - Andreasen, Søren Juhl

AU - Shaker, Hamid Reza

AU - Ehmsen, Mikkel Præstholm

AU - Andersen, John

PY - 2013/8/21

Y1 - 2013/8/21

N2 - This work presents a method for modeling the gas composition in a Reformed Methanol Fuel Cell system. The method is based on Adaptive Neuro-Fuzzy- Inference-Systems which are trained on experimental data. The developed models are of the H2, CO2, CO and CH3OH mass flows of the reformed gas. The ANFIS models are able to predict the mass flows with mean absolute errors for the H2 and CO2 models of less than 1% and 6.37% for the CO model and 4.56% for the CH3OH model. The models have a wide range of applications such as dynamic modeling, stoichiometry observation and control, advanced control algorithms, or fuel cell diagnostics systems.

AB - This work presents a method for modeling the gas composition in a Reformed Methanol Fuel Cell system. The method is based on Adaptive Neuro-Fuzzy- Inference-Systems which are trained on experimental data. The developed models are of the H2, CO2, CO and CH3OH mass flows of the reformed gas. The ANFIS models are able to predict the mass flows with mean absolute errors for the H2 and CO2 models of less than 1% and 6.37% for the CO model and 4.56% for the CH3OH model. The models have a wide range of applications such as dynamic modeling, stoichiometry observation and control, advanced control algorithms, or fuel cell diagnostics systems.

KW - ANFIS

KW - Fuzzy-logic and neural networks

KW - Gas composition modeling

KW - HTPEM fuel cell

KW - Methanol

KW - Reformed Methanol Fuel Cell

U2 - 10.1016/j.ijhydene.2013.06.013

DO - 10.1016/j.ijhydene.2013.06.013

M3 - Journal article

VL - 38

SP - 10577

EP - 10584

JO - International Journal of Hydrogen Energy

JF - International Journal of Hydrogen Energy

SN - 0360-3199

IS - 25

ER -