Solution and Parameter Identification of a Fixed-Bed Reactor Model for Catalytic CO<sub>2</sub> Methanation Using Physics-Informed Neural Networks
In this study, we develop physics-informed neural networks (PINNs) to solve an isothermal fixed-bed (IFB) model for catalytic CO<sub>2</sub> methanation. The PINN includes a feed-forward artificial neural network (FF-ANN) and physics-informed constraints, such as governing equations, bou...
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
MDPI AG
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/8254ad25d9df4ed28af83cf6d35c0818 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:8254ad25d9df4ed28af83cf6d35c0818 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:8254ad25d9df4ed28af83cf6d35c08182021-11-25T17:05:40ZSolution and Parameter Identification of a Fixed-Bed Reactor Model for Catalytic CO<sub>2</sub> Methanation Using Physics-Informed Neural Networks10.3390/catal111113042073-4344https://doaj.org/article/8254ad25d9df4ed28af83cf6d35c08182021-10-01T00:00:00Zhttps://www.mdpi.com/2073-4344/11/11/1304https://doaj.org/toc/2073-4344In this study, we develop physics-informed neural networks (PINNs) to solve an isothermal fixed-bed (IFB) model for catalytic CO<sub>2</sub> methanation. The PINN includes a feed-forward artificial neural network (FF-ANN) and physics-informed constraints, such as governing equations, boundary conditions, and reaction kinetics. The most effective PINN structure consists of 5–7 hidden layers, 256 neurons per layer, and a hyperbolic tangent (<i>tanh</i>) activation function. The forward PINN model solves the plug-flow reactor model of the IFB, whereas the inverse PINN model reveals an unknown effectiveness factor involved in the reaction kinetics. The forward PINN shows excellent extrapolation performance with an accuracy of 88.1% when concentrations outside the training domain are predicted using only one-sixth of the entire domain. The inverse PINN model identifies an unknown effectiveness factor with an error of 0.3%, even for a small number of observation datasets (e.g., 20 sets). These results suggest that forward and inverse PINNs can be used in the solution and system identification of fixed-bed models with chemical reaction kinetics.Son Ich NgoYoung-Il LimMDPI AGarticlecatalytic CO<sub>2</sub> methanationfixed-bed reactorreaction kineticssystem identificationmachine learningphysics-informed neural networkChemical technologyTP1-1185ChemistryQD1-999ENCatalysts, Vol 11, Iss 1304, p 1304 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
catalytic CO<sub>2</sub> methanation fixed-bed reactor reaction kinetics system identification machine learning physics-informed neural network Chemical technology TP1-1185 Chemistry QD1-999 |
| spellingShingle |
catalytic CO<sub>2</sub> methanation fixed-bed reactor reaction kinetics system identification machine learning physics-informed neural network Chemical technology TP1-1185 Chemistry QD1-999 Son Ich Ngo Young-Il Lim Solution and Parameter Identification of a Fixed-Bed Reactor Model for Catalytic CO<sub>2</sub> Methanation Using Physics-Informed Neural Networks |
| description |
In this study, we develop physics-informed neural networks (PINNs) to solve an isothermal fixed-bed (IFB) model for catalytic CO<sub>2</sub> methanation. The PINN includes a feed-forward artificial neural network (FF-ANN) and physics-informed constraints, such as governing equations, boundary conditions, and reaction kinetics. The most effective PINN structure consists of 5–7 hidden layers, 256 neurons per layer, and a hyperbolic tangent (<i>tanh</i>) activation function. The forward PINN model solves the plug-flow reactor model of the IFB, whereas the inverse PINN model reveals an unknown effectiveness factor involved in the reaction kinetics. The forward PINN shows excellent extrapolation performance with an accuracy of 88.1% when concentrations outside the training domain are predicted using only one-sixth of the entire domain. The inverse PINN model identifies an unknown effectiveness factor with an error of 0.3%, even for a small number of observation datasets (e.g., 20 sets). These results suggest that forward and inverse PINNs can be used in the solution and system identification of fixed-bed models with chemical reaction kinetics. |
| format |
article |
| author |
Son Ich Ngo Young-Il Lim |
| author_facet |
Son Ich Ngo Young-Il Lim |
| author_sort |
Son Ich Ngo |
| title |
Solution and Parameter Identification of a Fixed-Bed Reactor Model for Catalytic CO<sub>2</sub> Methanation Using Physics-Informed Neural Networks |
| title_short |
Solution and Parameter Identification of a Fixed-Bed Reactor Model for Catalytic CO<sub>2</sub> Methanation Using Physics-Informed Neural Networks |
| title_full |
Solution and Parameter Identification of a Fixed-Bed Reactor Model for Catalytic CO<sub>2</sub> Methanation Using Physics-Informed Neural Networks |
| title_fullStr |
Solution and Parameter Identification of a Fixed-Bed Reactor Model for Catalytic CO<sub>2</sub> Methanation Using Physics-Informed Neural Networks |
| title_full_unstemmed |
Solution and Parameter Identification of a Fixed-Bed Reactor Model for Catalytic CO<sub>2</sub> Methanation Using Physics-Informed Neural Networks |
| title_sort |
solution and parameter identification of a fixed-bed reactor model for catalytic co<sub>2</sub> methanation using physics-informed neural networks |
| publisher |
MDPI AG |
| publishDate |
2021 |
| url |
https://doaj.org/article/8254ad25d9df4ed28af83cf6d35c0818 |
| work_keys_str_mv |
AT sonichngo solutionandparameteridentificationofafixedbedreactormodelforcatalyticcosub2submethanationusingphysicsinformedneuralnetworks AT youngillim solutionandparameteridentificationofafixedbedreactormodelforcatalyticcosub2submethanationusingphysicsinformedneuralnetworks |
| _version_ |
1718412723674415104 |