Artificial Neural Network Modeling of Thermo-catalytic Methane Decomposition for Hydrogen Production
Bayesian networks; Calcination; Catalysts; Knowledge based systems; Mean square error; Methane; Multilayer neural networks; Predictive analytics; Sensitivity analysis; Specific surface area; Topology; Artificial neural network modeling; Bayesian regularization; Calcination temperature; Catalytic met...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Springer
2023
|
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my.uniten.dspace-26233 |
|---|---|
| record_format |
dspace |
| spelling |
my.uniten.dspace-262332023-05-29T17:08:03Z Artificial Neural Network Modeling of Thermo-catalytic Methane Decomposition for Hydrogen Production Alsaffar M.A. Ghany M.A.R.A. Ali J.M. Ayodele B.V. Mustapa S.I. 57210601717 57220782481 57197302318 56862160400 36651549700 Bayesian networks; Calcination; Catalysts; Knowledge based systems; Mean square error; Methane; Multilayer neural networks; Predictive analytics; Sensitivity analysis; Specific surface area; Topology; Artificial neural network modeling; Bayesian regularization; Calcination temperature; Catalytic methane decompositions; Coefficient of determination; Multi-layer perceptron neural networks; Non-linear relationships; Trained neural networks; Hydrogen production Thermo-catalytic methane decomposition is a prospective route for producing COx free hydrogen. In this study, Bayesian regularization and Levenberg-Marquardt trained multilayer perceptron neural networks were employed in predictive modeling of hydrogen production by thermo-catalytic methane decomposition. Based on the non-linear relationship between the reaction temperature, weight of the catalysts, time of stream, calcination temperature, calcination time, specific volume, and the hydrogen yield, the various topology was configured for the neural network and tested to determine the artificial neuron that would result in the best model performance. The Levenberg-Marquardt trained neural network displayed the best performance with the model topology of 7�16-1 compared with the Bayesian regularization trained network. The model topology of 7�16-1 represents the input units, hidden neuron, and the output unit. The predicted hydrogen yield by the 7�16-1 configured neural network was in strong agreement with the observed value, evidenced by the coefficient of determination (R2) of 0.953 and mean square error of 0.03. A predicted hydrogen yield of 86.56�vol.% was obtained at the reaction temperature of 700��C, 0.5�g catalyst weight, calcination temperature of 600��C, calcination time of 240�min, catalyst specific surface area of 24.1�m2/g, the pore volume of 0.03�cm3/g, and 160�min time on stream which is at proximity with the observed value of 84�vol.%. The sensitivity analysis revealed that all the input parameters have varying levels of importance on the model output. However, the intrinsic properties of the catalysts (specific surface area, and the pore volume) have the most significant influence on the predicted hydrogen yield. � 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC part of Springer Nature. Final 2023-05-29T09:08:03Z 2023-05-29T09:08:03Z 2021 Article 10.1007/s11244-020-01409-6 2-s2.0-85098732239 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85098732239&doi=10.1007%2fs11244-020-01409-6&partnerID=40&md5=103e06a454b9a49f9f9e7a3abb550e72 https://irepository.uniten.edu.my/handle/123456789/26233 64 5-Jun 456 464 Springer Scopus |
| institution |
Universiti Tenaga Nasional |
| building |
UNITEN Library |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Tenaga Nasional |
| content_source |
UNITEN Institutional Repository |
| url_provider |
http://dspace.uniten.edu.my/ |
| description |
Bayesian networks; Calcination; Catalysts; Knowledge based systems; Mean square error; Methane; Multilayer neural networks; Predictive analytics; Sensitivity analysis; Specific surface area; Topology; Artificial neural network modeling; Bayesian regularization; Calcination temperature; Catalytic methane decompositions; Coefficient of determination; Multi-layer perceptron neural networks; Non-linear relationships; Trained neural networks; Hydrogen production |
| author2 |
57210601717 |
| author_facet |
57210601717 Alsaffar M.A. Ghany M.A.R.A. Ali J.M. Ayodele B.V. Mustapa S.I. |
| format |
Article |
| author |
Alsaffar M.A. Ghany M.A.R.A. Ali J.M. Ayodele B.V. Mustapa S.I. |
| spellingShingle |
Alsaffar M.A. Ghany M.A.R.A. Ali J.M. Ayodele B.V. Mustapa S.I. Artificial Neural Network Modeling of Thermo-catalytic Methane Decomposition for Hydrogen Production |
| author_sort |
Alsaffar M.A. |
| title |
Artificial Neural Network Modeling of Thermo-catalytic Methane Decomposition for Hydrogen Production |
| title_short |
Artificial Neural Network Modeling of Thermo-catalytic Methane Decomposition for Hydrogen Production |
| title_full |
Artificial Neural Network Modeling of Thermo-catalytic Methane Decomposition for Hydrogen Production |
| title_fullStr |
Artificial Neural Network Modeling of Thermo-catalytic Methane Decomposition for Hydrogen Production |
| title_full_unstemmed |
Artificial Neural Network Modeling of Thermo-catalytic Methane Decomposition for Hydrogen Production |
| title_sort |
artificial neural network modeling of thermo-catalytic methane decomposition for hydrogen production |
| publisher |
Springer |
| publishDate |
2023 |
| _version_ |
1806426302649991168 |
| score |
13.214268 |