Publication:
Process intensification of hydrogen production by catalytic steam methane reforming: Performance analysis of multilayer perceptron-artificial neural networks and nonlinear response surface techniques

Simple item page
dc.citedby7
dc.contributor.authorAyodele B.V.en_US
dc.contributor.authorAlsaffar M.A.en_US
dc.contributor.authorMustapa S.I.en_US
dc.contributor.authorAdesina A.en_US
dc.contributor.authorKanthasamy R.en_US
dc.contributor.authorWitoon T.en_US
dc.contributor.authorAbdullah S.en_US
dc.contributor.authorid56862160400en_US
dc.contributor.authorid57210601717en_US
dc.contributor.authorid36651549700en_US
dc.contributor.authorid35564888500en_US
dc.contributor.authorid56070146400en_US
dc.contributor.authorid23487511100en_US
dc.contributor.authorid57188753785en_US
dc.date.accessioned2023-05-29T09:05:22Z
dc.date.available2023-05-29T09:05:22Z
dc.date.issued2021
dc.descriptionChemical activation; Errors; Gradient methods; Hydrogen production; Hyperbolic functions; Mean square error; Methane; Nonlinear analysis; Sensitivity analysis; Steam; Steam reforming; Surface properties; Activation functions; Artificial neurons; Gradient-descent; Multilayers perceptrons; Network response; Non-linear response; Nonlinear response surface technique; Performance; Process intensification; Response surface techniques; Multilayer neural networksen_US
dc.description.abstractUncertainty about how process factors affect output might lead to waste of resources in laboratory experiments. To address this constraint, a data-driven method might be used to describe the non-linear connection between process parameters and desired output. A Multi-Layer Perceptron-Artificial Neural Network (MLP-ANN) and non-linear response surface method are used to predict hydrogen generation by catalytic steam methane reforming. The impact of training methods (scaled conjugate and gradient descent), hidden layer variation, artificial neuron variation, and activation functions were studied in 80 MLP-ANN combinations (hyperbolic tangent function and sigmoid function). The performance of MLP-ANN models was affected by the training techniques, activation functions, layer count, and number of artificial neurons. The model with the sigmoid function and 3 input layers, 17 artificial neurons in the first layer, 15 artificial neurons in the second layer, and 2 output nodes had the greatest performance among the 40 configurations of scaled conjugate trained ANNs. It projected an 89.55% maximal hydrogen yield with a coefficient of determination (R2) of 0.997 and reduced errors with Mean absolute percentage error (MAPE) and mean squared error (MSE) of 0.199 and 0.121, respectively. Similarly, the gradient descent ANN model with hyperbolic tangent activation function had the greatest performance among the 40 gradient descent trained-ANN configurations. The 3�15�7�2 gradient descent trained ANN model projected a maximum hydrogen output of 89.73% compared to the experimental results of 89.51%. The MLP-ANN models outperformed nonlinear response surface methods, with R2, MAPE, and MSE of 0.231, 0.191, and 0.988, respectively. The updated Garson algorithm indicated that the input parameters impacted the hydrogen production in the sequence reaction temperature>methane partial pressure>steam partial pressure. The sensitivity analysis might assist identify how resources should be spent. � 2021 The Institution of Chemical Engineersen_US
dc.description.natureFinalen_US
dc.identifier.doi10.1016/j.psep.2021.10.016
dc.identifier.epage329
dc.identifier.scopus2-s2.0-85118362159
dc.identifier.spage315
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85118362159&doi=10.1016%2fj.psep.2021.10.016&partnerID=40&md5=7cd7a431cfab2f0b09265f8a6129894d
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/25871
dc.identifier.volume156
dc.publisherInstitution of Chemical Engineersen_US
dc.sourceScopus
dc.sourcetitleProcess Safety and Environmental Protection
dc.titleProcess intensification of hydrogen production by catalytic steam methane reforming: Performance analysis of multilayer perceptron-artificial neural networks and nonlinear response surface techniquesen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS