Investigation of artificial neural network topologies to predict biomass gasification and comparison with a thermodynamic equilibrium model

Fernanda da Silva Pimentel, Brunno Ferreira dos Santos and Florian Pradelle

Energy, 2024, vol. 308, issue C

Abstract: Extensive research has been conducted in the field of biomass gasification, driven by global concerns about energy security and the environment, since the syngas production has the advantage of reducing greenhouse gas emissions. So, an Artificial Neural Network (ANN) model was developed in the present study as a robust tool to predict the syngas composition (CO2, CO, CH4 and H2), wherein the model considered different types of biomasses, gasification agents and gasifiers. Data collected from the literature, totaling 718 records, underwent preprocessing through a data mining process to construct a robust database. Several artificial neural network topologies were investigated and, in a screening of 33 ANN topologies, the best topology presented R2 values greater than 0.70 for test and greater than 0.88 for training, for each output gas. Regions of higher reliability were explored to enhance model interpretations, achieved through an analysis of distances between the training database and test data. Then, a qualitative comparison between the ANN model (considering a reliable region) and the results from the minimization of Gibbs free energy was performed and the consistency of the ANN model was confirmed, since, at higher temperatures, the gases production levels were similar for both models.

Keywords: Artificial neural network model; Syngas; Database construction; Optimization; Minimization of Gibbs free energy (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544224025362
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:308:y:2024:i:c:s0360544224025362

DOI: 10.1016/j.energy.2024.132762

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().