Artificial neural network models for biomass gasification in fluidized bed gasifiers

Maria Puig Arnavat, J. Alfredo Hernández, Joan Carles Bruno, Alberto Coronas

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

Artificial neural networks (ANNs) have been applied for modeling biomass gasification process in fluidized bed reactors. Two architectures of ANNs models are presented; one for circulating fluidized bed gasifiers (CFB) and the other for bubbling fluidized bed gasifiers (BFB). Both models determine the producer gas composition (CO, CO2, H2, CH4) and gas yield. Published experimental data from other authors has been used to train the ANNs. The obtained results show that the percentage composition of the main four gas species in producer gas (CO, CO2, H2, CH4) and producer gas yield for a biomass fluidized bed gasifier can be successfully predicted by applying neural networks. ANNs models use in the input layer the biomass composition and few operating parameters, two neurons in the hidden layer and the backpropagation algorithm. The results obtained by these ANNs show high agreement with published experimental data used R2 > 0.98. Furthermore a sensitivity analysis has been applied in each ANN model showing that all studied input variables are important.
Original languageEnglish
JournalBiomass & Bioenergy
Volume49
Pages (from-to)279-289
ISSN0961-9534
DOIs
Publication statusPublished - 2013

Keywords

  • Biomass
  • Gasification
  • Artificial neural network
  • Simulation
  • Fluidized bed

Cite this

Puig Arnavat, Maria ; Hernández, J. Alfredo ; Bruno, Joan Carles ; Coronas, Alberto. / Artificial neural network models for biomass gasification in fluidized bed gasifiers. In: Biomass & Bioenergy. 2013 ; Vol. 49. pp. 279-289.
@article{10fb481cad264ac7bf623c4c6f2c2a6a,
title = "Artificial neural network models for biomass gasification in fluidized bed gasifiers",
abstract = "Artificial neural networks (ANNs) have been applied for modeling biomass gasification process in fluidized bed reactors. Two architectures of ANNs models are presented; one for circulating fluidized bed gasifiers (CFB) and the other for bubbling fluidized bed gasifiers (BFB). Both models determine the producer gas composition (CO, CO2, H2, CH4) and gas yield. Published experimental data from other authors has been used to train the ANNs. The obtained results show that the percentage composition of the main four gas species in producer gas (CO, CO2, H2, CH4) and producer gas yield for a biomass fluidized bed gasifier can be successfully predicted by applying neural networks. ANNs models use in the input layer the biomass composition and few operating parameters, two neurons in the hidden layer and the backpropagation algorithm. The results obtained by these ANNs show high agreement with published experimental data used R2 > 0.98. Furthermore a sensitivity analysis has been applied in each ANN model showing that all studied input variables are important.",
keywords = "Biomass, Gasification, Artificial neural network, Simulation, Fluidized bed",
author = "{Puig Arnavat}, Maria and Hern{\'a}ndez, {J. Alfredo} and Bruno, {Joan Carles} and Alberto Coronas",
year = "2013",
doi = "10.1016/j.biombioe.2012.12.012",
language = "English",
volume = "49",
pages = "279--289",
journal = "Biomass & Bioenergy",
issn = "0961-9534",
publisher = "Pergamon Press",

}

Artificial neural network models for biomass gasification in fluidized bed gasifiers. / Puig Arnavat, Maria; Hernández, J. Alfredo; Bruno, Joan Carles; Coronas, Alberto.

In: Biomass & Bioenergy, Vol. 49, 2013, p. 279-289.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Artificial neural network models for biomass gasification in fluidized bed gasifiers

AU - Puig Arnavat, Maria

AU - Hernández, J. Alfredo

AU - Bruno, Joan Carles

AU - Coronas, Alberto

PY - 2013

Y1 - 2013

N2 - Artificial neural networks (ANNs) have been applied for modeling biomass gasification process in fluidized bed reactors. Two architectures of ANNs models are presented; one for circulating fluidized bed gasifiers (CFB) and the other for bubbling fluidized bed gasifiers (BFB). Both models determine the producer gas composition (CO, CO2, H2, CH4) and gas yield. Published experimental data from other authors has been used to train the ANNs. The obtained results show that the percentage composition of the main four gas species in producer gas (CO, CO2, H2, CH4) and producer gas yield for a biomass fluidized bed gasifier can be successfully predicted by applying neural networks. ANNs models use in the input layer the biomass composition and few operating parameters, two neurons in the hidden layer and the backpropagation algorithm. The results obtained by these ANNs show high agreement with published experimental data used R2 > 0.98. Furthermore a sensitivity analysis has been applied in each ANN model showing that all studied input variables are important.

AB - Artificial neural networks (ANNs) have been applied for modeling biomass gasification process in fluidized bed reactors. Two architectures of ANNs models are presented; one for circulating fluidized bed gasifiers (CFB) and the other for bubbling fluidized bed gasifiers (BFB). Both models determine the producer gas composition (CO, CO2, H2, CH4) and gas yield. Published experimental data from other authors has been used to train the ANNs. The obtained results show that the percentage composition of the main four gas species in producer gas (CO, CO2, H2, CH4) and producer gas yield for a biomass fluidized bed gasifier can be successfully predicted by applying neural networks. ANNs models use in the input layer the biomass composition and few operating parameters, two neurons in the hidden layer and the backpropagation algorithm. The results obtained by these ANNs show high agreement with published experimental data used R2 > 0.98. Furthermore a sensitivity analysis has been applied in each ANN model showing that all studied input variables are important.

KW - Biomass

KW - Gasification

KW - Artificial neural network

KW - Simulation

KW - Fluidized bed

U2 - 10.1016/j.biombioe.2012.12.012

DO - 10.1016/j.biombioe.2012.12.012

M3 - Journal article

VL - 49

SP - 279

EP - 289

JO - Biomass & Bioenergy

JF - Biomass & Bioenergy

SN - 0961-9534

ER -