TU Darmstadt / ULB / TUbiblio

A Dynamic Recurrent Neural Network for Predicting Higher Heating Value of Biomass

Aghel, Babak ; Yahya, Salah I. ; Rezaei, Abbas ; Alobaid, Falah (2023)
A Dynamic Recurrent Neural Network for Predicting Higher Heating Value of Biomass.
In: International Journal of Molecular Sciences, 2023, 24 (6)
doi: 10.26083/tuprints-00023649
Artikel, Zweitveröffentlichung, Verlagsversion

Kurzbeschreibung (Abstract)

The higher heating value (HHV) is the main property showing the energy amount of biomass samples. Several linear correlations based on either the proximate or the ultimate analysis have already been proposed for predicting biomass HHV. Since the HHV relationship with the proximate and ultimate analyses is not linear, nonlinear models might be a better alternative. Accordingly, this study employed the Elman recurrent neural network (ENN) to anticipate the HHV of different biomass samples from both the ultimate and proximate compositional analyses as the model inputs. The number of hidden neurons and the training algorithm were determined in such a way that the ENN model showed the highest prediction and generalization accuracy. The single hidden layer ENN with only four nodes, trained by the Levenberg–Marquardt algorithm, was identified as the most accurate model. The proposed ENN exhibited reliable prediction and generalization performance for estimating 532 experimental HHVs with a low mean absolute error of 0.67 and a mean square error of 0.96. In addition, the proposed ENN model provides a ground to clearly understand the dependency of the HHV on the fixed carbon, volatile matter, ash, carbon, hydrogen, nitrogen, oxygen, and sulfur content of biomass feedstocks.

Typ des Eintrags: Artikel
Erschienen: 2023
Autor(en): Aghel, Babak ; Yahya, Salah I. ; Rezaei, Abbas ; Alobaid, Falah
Art des Eintrags: Zweitveröffentlichung
Titel: A Dynamic Recurrent Neural Network for Predicting Higher Heating Value of Biomass
Sprache: Englisch
Publikationsjahr: 2023
Ort: Darmstadt
Publikationsdatum der Erstveröffentlichung: 2023
Verlag: MDPI
Titel der Zeitschrift, Zeitung oder Schriftenreihe: International Journal of Molecular Sciences
Jahrgang/Volume einer Zeitschrift: 24
(Heft-)Nummer: 6
Kollation: 13 Seiten
DOI: 10.26083/tuprints-00023649
URL / URN: https://tuprints.ulb.tu-darmstadt.de/23649
Zugehörige Links:
Herkunft: Zweitveröffentlichung DeepGreen
Kurzbeschreibung (Abstract):

The higher heating value (HHV) is the main property showing the energy amount of biomass samples. Several linear correlations based on either the proximate or the ultimate analysis have already been proposed for predicting biomass HHV. Since the HHV relationship with the proximate and ultimate analyses is not linear, nonlinear models might be a better alternative. Accordingly, this study employed the Elman recurrent neural network (ENN) to anticipate the HHV of different biomass samples from both the ultimate and proximate compositional analyses as the model inputs. The number of hidden neurons and the training algorithm were determined in such a way that the ENN model showed the highest prediction and generalization accuracy. The single hidden layer ENN with only four nodes, trained by the Levenberg–Marquardt algorithm, was identified as the most accurate model. The proposed ENN exhibited reliable prediction and generalization performance for estimating 532 experimental HHVs with a low mean absolute error of 0.67 and a mean square error of 0.96. In addition, the proposed ENN model provides a ground to clearly understand the dependency of the HHV on the fixed carbon, volatile matter, ash, carbon, hydrogen, nitrogen, oxygen, and sulfur content of biomass feedstocks.

Freie Schlagworte: biomass sample, higher heating value, Elman neural network, topology tuning, training algorithm
Status: Verlagsversion
URN: urn:nbn:de:tuda-tuprints-236497
Zusätzliche Informationen:

This article belongs to the Collection Feature Papers in Physical Chemistry and Chemical Physics

Sachgruppe der Dewey Dezimalklassifikatin (DDC): 600 Technik, Medizin, angewandte Wissenschaften > 620 Ingenieurwissenschaften und Maschinenbau
Fachbereich(e)/-gebiet(e): 16 Fachbereich Maschinenbau
16 Fachbereich Maschinenbau > Institut für Energiesysteme und Energietechnik (EST)
Hinterlegungsdatum: 11 Apr 2023 11:37
Letzte Änderung: 12 Apr 2023 05:02
PPN:
Zugehörige Links:
Export:
Suche nach Titel in: TUfind oder in Google
Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen