Simulating and Comparing CO<sub>2</sub>/CH<sub>4</sub> Separation Performance of Membrane–Zeolite Contactors by Cascade Neural Networks
Separating carbon dioxide (CO<sub>2</sub>) from gaseous streams released into the atmosphere is becoming critical due to its greenhouse effect. Membrane technology is one of the promising technologies for CO<sub>2</sub> capture. SAPO-34 filler was incorporated in polymeric me...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Membranes |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0375/13/5/526 |
| _version_ | 1797599165982703616 |
|---|---|
| author | Seyyed Amirreza Abdollahi AmirReza Andarkhor Afham Pourahmad Ali Hosin Alibak Falah Alobaid Babak Aghel |
| author_facet | Seyyed Amirreza Abdollahi AmirReza Andarkhor Afham Pourahmad Ali Hosin Alibak Falah Alobaid Babak Aghel |
| author_sort | Seyyed Amirreza Abdollahi |
| collection | DOAJ |
| description | Separating carbon dioxide (CO<sub>2</sub>) from gaseous streams released into the atmosphere is becoming critical due to its greenhouse effect. Membrane technology is one of the promising technologies for CO<sub>2</sub> capture. SAPO-34 filler was incorporated in polymeric media to synthesize mixed matrix membrane (MMM) and enhance the CO<sub>2</sub> separation performance of this process. Despite relatively extensive experimental studies, there are limited studies that cover the modeling aspects of CO<sub>2</sub> capture by MMMs. This research applies a special type of machine learning modeling scenario, namely, cascade neural networks (CNN), to simulate as well as compare the CO<sub>2</sub>/CH<sub>4</sub> selectivity of a wide range of MMMs containing SAPO-34 zeolite. A combination of trial-and-error analysis and statistical accuracy monitoring has been applied to fine-tune the CNN topology. It was found that the CNN with a 4-11-1 topology has the highest accuracy for the modeling of the considered task. The designed CNN model is able to precisely predict the CO<sub>2</sub>/CH<sub>4</sub> selectivity of seven different MMMs in a broad range of filler concentrations, pressures, and temperatures. The model predicts 118 actual measurements of CO<sub>2</sub>/CH<sub>4</sub> selectivity with an outstanding accuracy (i.e., AARD = 2.92%, MSE = 1.55, R = 0.9964). |
| first_indexed | 2024-03-11T03:30:53Z |
| format | Article |
| id | doaj.art-fabbab4696e9443a9e5bcbd25c77c021 |
| institution | Directory Open Access Journal |
| issn | 2077-0375 |
| language | English |
| last_indexed | 2024-03-11T03:30:53Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Membranes |
| spelling | doaj.art-fabbab4696e9443a9e5bcbd25c77c0212023-11-18T02:24:42ZengMDPI AGMembranes2077-03752023-05-0113552610.3390/membranes13050526Simulating and Comparing CO<sub>2</sub>/CH<sub>4</sub> Separation Performance of Membrane–Zeolite Contactors by Cascade Neural NetworksSeyyed Amirreza Abdollahi0AmirReza Andarkhor1Afham Pourahmad2Ali Hosin Alibak3Falah Alobaid4Babak Aghel5Faculty of Mechanical Engineering, University of Tabriz, Tabriz 5166616471, IranDepartment of Chemistry, Payam Noor University (Bushehr Branch), Bushehr 1688, IranDepartment of Polymer Engineering, Amirkabir University of Technology, Tehran 1591634311, IranChemical Engineering Department, Faculty of Engineering, Soran University, Soran 44008, IraqInstitut Energiesysteme und Energietechnik, Technische Universität Darmstadt, Otto-Berndt-Straße 2, 64287 Darmstadt, GermanyInstitut Energiesysteme und Energietechnik, Technische Universität Darmstadt, Otto-Berndt-Straße 2, 64287 Darmstadt, GermanySeparating carbon dioxide (CO<sub>2</sub>) from gaseous streams released into the atmosphere is becoming critical due to its greenhouse effect. Membrane technology is one of the promising technologies for CO<sub>2</sub> capture. SAPO-34 filler was incorporated in polymeric media to synthesize mixed matrix membrane (MMM) and enhance the CO<sub>2</sub> separation performance of this process. Despite relatively extensive experimental studies, there are limited studies that cover the modeling aspects of CO<sub>2</sub> capture by MMMs. This research applies a special type of machine learning modeling scenario, namely, cascade neural networks (CNN), to simulate as well as compare the CO<sub>2</sub>/CH<sub>4</sub> selectivity of a wide range of MMMs containing SAPO-34 zeolite. A combination of trial-and-error analysis and statistical accuracy monitoring has been applied to fine-tune the CNN topology. It was found that the CNN with a 4-11-1 topology has the highest accuracy for the modeling of the considered task. The designed CNN model is able to precisely predict the CO<sub>2</sub>/CH<sub>4</sub> selectivity of seven different MMMs in a broad range of filler concentrations, pressures, and temperatures. The model predicts 118 actual measurements of CO<sub>2</sub>/CH<sub>4</sub> selectivity with an outstanding accuracy (i.e., AARD = 2.92%, MSE = 1.55, R = 0.9964).https://www.mdpi.com/2077-0375/13/5/526CO<sub>2</sub>/CH<sub>4</sub> gas mixturemembrane separationselectivityintelligent modeling |
| spellingShingle | Seyyed Amirreza Abdollahi AmirReza Andarkhor Afham Pourahmad Ali Hosin Alibak Falah Alobaid Babak Aghel Simulating and Comparing CO<sub>2</sub>/CH<sub>4</sub> Separation Performance of Membrane–Zeolite Contactors by Cascade Neural Networks Membranes CO<sub>2</sub>/CH<sub>4</sub> gas mixture membrane separation selectivity intelligent modeling |
| title | Simulating and Comparing CO<sub>2</sub>/CH<sub>4</sub> Separation Performance of Membrane–Zeolite Contactors by Cascade Neural Networks |
| title_full | Simulating and Comparing CO<sub>2</sub>/CH<sub>4</sub> Separation Performance of Membrane–Zeolite Contactors by Cascade Neural Networks |
| title_fullStr | Simulating and Comparing CO<sub>2</sub>/CH<sub>4</sub> Separation Performance of Membrane–Zeolite Contactors by Cascade Neural Networks |
| title_full_unstemmed | Simulating and Comparing CO<sub>2</sub>/CH<sub>4</sub> Separation Performance of Membrane–Zeolite Contactors by Cascade Neural Networks |
| title_short | Simulating and Comparing CO<sub>2</sub>/CH<sub>4</sub> Separation Performance of Membrane–Zeolite Contactors by Cascade Neural Networks |
| title_sort | simulating and comparing co sub 2 sub ch sub 4 sub separation performance of membrane zeolite contactors by cascade neural networks |
| topic | CO<sub>2</sub>/CH<sub>4</sub> gas mixture membrane separation selectivity intelligent modeling |
| url | https://www.mdpi.com/2077-0375/13/5/526 |
| work_keys_str_mv | AT seyyedamirrezaabdollahi simulatingandcomparingcosub2subchsub4subseparationperformanceofmembranezeolitecontactorsbycascadeneuralnetworks AT amirrezaandarkhor simulatingandcomparingcosub2subchsub4subseparationperformanceofmembranezeolitecontactorsbycascadeneuralnetworks AT afhampourahmad simulatingandcomparingcosub2subchsub4subseparationperformanceofmembranezeolitecontactorsbycascadeneuralnetworks AT alihosinalibak simulatingandcomparingcosub2subchsub4subseparationperformanceofmembranezeolitecontactorsbycascadeneuralnetworks AT falahalobaid simulatingandcomparingcosub2subchsub4subseparationperformanceofmembranezeolitecontactorsbycascadeneuralnetworks AT babakaghel simulatingandcomparingcosub2subchsub4subseparationperformanceofmembranezeolitecontactorsbycascadeneuralnetworks |