Application of artificial neural network and response surface methodology for modelling of hydrogen production using nickel loaded zeolite

Fazureen Azaman, Azman Azid, Hafizan Juahir, Mahadhir Mohamed, Kamaruzzaman Yunus, Mohd. Ekhwan Toriman, Ahmad Dasuki Mustafa, Mohammad Azizi Amran, Che Noraini Che Hasnam, Roslan Umar, Norsyuhada Hairoma

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Hydrogen gas production via glycerol steam reforming using nickel (Ni) loaded zeolite (HZSM-5) catalyst was focused on this research. 15 wt % Ni(HZSM-5) catalyst loading has been investigated based on the parameter of different range of catalyst weight (0.3-0.5g) and glycerol flow rate (0.2-0.4mL/min) at 600 ºC and atmospheric pressure. The products were analyzed by using gas-chromatography with thermal conductivity detector (GC-TCD), where it used to identify the yield of hydrogen. The data of the experiment were analyzed by using Response Surface Methodology (RSM) and Artificial Neural Network (ANN) in order to predict the production of hydrogen. The results show that the condition for maximum hydrogen yield was obtained at 0.4 ml/min of glycerol flow rate and 0.3 g of catalyst weight resulting in 88.35 % hydrogen yield. 100 % glycerol conversion was achieved at 0.4 of glycerol flow rates and 0.3 g catalyst weight. After predicting the model using RSM and ANN, both models provided good quality predictions. The ANN showed a clear superiority with R2 was almost to 1 compared to the RSM model.

Original languageEnglish
Pages (from-to)109-118
Number of pages10
JournalJurnal Teknologi
Volume77
Issue number1
DOIs
Publication statusPublished - 1 Nov 2015
Externally publishedYes

Fingerprint

Hydrogen production
Glycerol
Nickel
Neural networks
Hydrogen
Catalysts
Flow rate
Steam reforming
Gas chromatography
Atmospheric pressure
Thermal conductivity
Detectors
Gases
Experiments

Keywords

  • Artificial neural network
  • Glycerol steam reforming
  • Hydrogen gas
  • Ni-HZSM-5
  • Response surface methodology

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Application of artificial neural network and response surface methodology for modelling of hydrogen production using nickel loaded zeolite. / Azaman, Fazureen; Azid, Azman; Juahir, Hafizan; Mohamed, Mahadhir; Yunus, Kamaruzzaman; Toriman, Mohd. Ekhwan; Mustafa, Ahmad Dasuki; Amran, Mohammad Azizi; Hasnam, Che Noraini Che; Umar, Roslan; Hairoma, Norsyuhada.

In: Jurnal Teknologi, Vol. 77, No. 1, 01.11.2015, p. 109-118.

Research output: Contribution to journalArticle

Azaman, F, Azid, A, Juahir, H, Mohamed, M, Yunus, K, Toriman, ME, Mustafa, AD, Amran, MA, Hasnam, CNC, Umar, R & Hairoma, N 2015, 'Application of artificial neural network and response surface methodology for modelling of hydrogen production using nickel loaded zeolite', Jurnal Teknologi, vol. 77, no. 1, pp. 109-118. https://doi.org/10.11113/jt.v77.4265
Azaman, Fazureen ; Azid, Azman ; Juahir, Hafizan ; Mohamed, Mahadhir ; Yunus, Kamaruzzaman ; Toriman, Mohd. Ekhwan ; Mustafa, Ahmad Dasuki ; Amran, Mohammad Azizi ; Hasnam, Che Noraini Che ; Umar, Roslan ; Hairoma, Norsyuhada. / Application of artificial neural network and response surface methodology for modelling of hydrogen production using nickel loaded zeolite. In: Jurnal Teknologi. 2015 ; Vol. 77, No. 1. pp. 109-118.
@article{e9beb6744a664024bad927b578977acc,
title = "Application of artificial neural network and response surface methodology for modelling of hydrogen production using nickel loaded zeolite",
abstract = "Hydrogen gas production via glycerol steam reforming using nickel (Ni) loaded zeolite (HZSM-5) catalyst was focused on this research. 15 wt {\%} Ni(HZSM-5) catalyst loading has been investigated based on the parameter of different range of catalyst weight (0.3-0.5g) and glycerol flow rate (0.2-0.4mL/min) at 600 ºC and atmospheric pressure. The products were analyzed by using gas-chromatography with thermal conductivity detector (GC-TCD), where it used to identify the yield of hydrogen. The data of the experiment were analyzed by using Response Surface Methodology (RSM) and Artificial Neural Network (ANN) in order to predict the production of hydrogen. The results show that the condition for maximum hydrogen yield was obtained at 0.4 ml/min of glycerol flow rate and 0.3 g of catalyst weight resulting in 88.35 {\%} hydrogen yield. 100 {\%} glycerol conversion was achieved at 0.4 of glycerol flow rates and 0.3 g catalyst weight. After predicting the model using RSM and ANN, both models provided good quality predictions. The ANN showed a clear superiority with R2 was almost to 1 compared to the RSM model.",
keywords = "Artificial neural network, Glycerol steam reforming, Hydrogen gas, Ni-HZSM-5, Response surface methodology",
author = "Fazureen Azaman and Azman Azid and Hafizan Juahir and Mahadhir Mohamed and Kamaruzzaman Yunus and Toriman, {Mohd. Ekhwan} and Mustafa, {Ahmad Dasuki} and Amran, {Mohammad Azizi} and Hasnam, {Che Noraini Che} and Roslan Umar and Norsyuhada Hairoma",
year = "2015",
month = "11",
day = "1",
doi = "10.11113/jt.v77.4265",
language = "English",
volume = "77",
pages = "109--118",
journal = "Jurnal Teknologi",
issn = "0127-9696",
publisher = "Penerbit Universiti Teknologi Malaysia",
number = "1",

}

TY - JOUR

T1 - Application of artificial neural network and response surface methodology for modelling of hydrogen production using nickel loaded zeolite

AU - Azaman, Fazureen

AU - Azid, Azman

AU - Juahir, Hafizan

AU - Mohamed, Mahadhir

AU - Yunus, Kamaruzzaman

AU - Toriman, Mohd. Ekhwan

AU - Mustafa, Ahmad Dasuki

AU - Amran, Mohammad Azizi

AU - Hasnam, Che Noraini Che

AU - Umar, Roslan

AU - Hairoma, Norsyuhada

PY - 2015/11/1

Y1 - 2015/11/1

N2 - Hydrogen gas production via glycerol steam reforming using nickel (Ni) loaded zeolite (HZSM-5) catalyst was focused on this research. 15 wt % Ni(HZSM-5) catalyst loading has been investigated based on the parameter of different range of catalyst weight (0.3-0.5g) and glycerol flow rate (0.2-0.4mL/min) at 600 ºC and atmospheric pressure. The products were analyzed by using gas-chromatography with thermal conductivity detector (GC-TCD), where it used to identify the yield of hydrogen. The data of the experiment were analyzed by using Response Surface Methodology (RSM) and Artificial Neural Network (ANN) in order to predict the production of hydrogen. The results show that the condition for maximum hydrogen yield was obtained at 0.4 ml/min of glycerol flow rate and 0.3 g of catalyst weight resulting in 88.35 % hydrogen yield. 100 % glycerol conversion was achieved at 0.4 of glycerol flow rates and 0.3 g catalyst weight. After predicting the model using RSM and ANN, both models provided good quality predictions. The ANN showed a clear superiority with R2 was almost to 1 compared to the RSM model.

AB - Hydrogen gas production via glycerol steam reforming using nickel (Ni) loaded zeolite (HZSM-5) catalyst was focused on this research. 15 wt % Ni(HZSM-5) catalyst loading has been investigated based on the parameter of different range of catalyst weight (0.3-0.5g) and glycerol flow rate (0.2-0.4mL/min) at 600 ºC and atmospheric pressure. The products were analyzed by using gas-chromatography with thermal conductivity detector (GC-TCD), where it used to identify the yield of hydrogen. The data of the experiment were analyzed by using Response Surface Methodology (RSM) and Artificial Neural Network (ANN) in order to predict the production of hydrogen. The results show that the condition for maximum hydrogen yield was obtained at 0.4 ml/min of glycerol flow rate and 0.3 g of catalyst weight resulting in 88.35 % hydrogen yield. 100 % glycerol conversion was achieved at 0.4 of glycerol flow rates and 0.3 g catalyst weight. After predicting the model using RSM and ANN, both models provided good quality predictions. The ANN showed a clear superiority with R2 was almost to 1 compared to the RSM model.

KW - Artificial neural network

KW - Glycerol steam reforming

KW - Hydrogen gas

KW - Ni-HZSM-5

KW - Response surface methodology

UR - http://www.scopus.com/inward/record.url?scp=84945275614&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84945275614&partnerID=8YFLogxK

U2 - 10.11113/jt.v77.4265

DO - 10.11113/jt.v77.4265

M3 - Article

VL - 77

SP - 109

EP - 118

JO - Jurnal Teknologi

JF - Jurnal Teknologi

SN - 0127-9696

IS - 1

ER -