Neural Network Modeling for Development of High-Pressure Measurement of Carbon Dioxide Solubility in the Aqueous AEEA+Sulfolane
Due to increasing concerns about global warming regarding CO2 release to the atmosphere, various methods are used to capture CO2, among which chemical absorption via amine mixture solutions is very well developed. A set of 179 data related to CO2 absorption in a mixture, including a physical absorbe...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Tehran
2023-06-01
|
| Series: | Journal of Chemical and Petroleum Engineering |
| Subjects: | |
| Online Access: | https://jchpe.ut.ac.ir/article_92759_84036e5d22cb6e5da89b60d3c7868c00.pdf |
| _version_ | 1797362163667435520 |
|---|---|
| author | Arman Hasanzadeh Ahad Ghaemi Shahrokh Shahhosseini |
| author_facet | Arman Hasanzadeh Ahad Ghaemi Shahrokh Shahhosseini |
| author_sort | Arman Hasanzadeh |
| collection | DOAJ |
| description | Due to increasing concerns about global warming regarding CO2 release to the atmosphere, various methods are used to capture CO2, among which chemical absorption via amine mixture solutions is very well developed. A set of 179 data related to CO2 absorption in a mixture, including a physical absorbent (sulfolane) and a chemical absorption (AEEA) in a wide range of temperature, pressure and solvent concentration is used to develop two Artificial Neural Networks (ANN). In Multi-Layer Perceptron (MLP), the Levenberg-Marquardt method is used to train the network. Most important factors such as regression analysis value (R2) of 0.99963, Mean Squared Error (MSE) value of 1.22E-05 and Average Absolute Relative Deviation value (%AARD) of 0.2671 factors reveal that the MLP network has a high capability to predict CO2 loading (αCO2). Also, a Radial Basis Function (RBF) network was developed. RBF network with a spread value of 2.2 and 138 neurons had an outstanding performance and achieved an MSE value of 2.53E-05 along with an R2 value of 0.99993, 11 seconds, and a %AARD value of 0.1460. According to experimental and predicted data, the neural networks are well trained and are able to predict CO2 loading precisely in an economic and optimized way. |
| first_indexed | 2024-03-08T16:03:31Z |
| format | Article |
| id | doaj.art-69e0154f5c0946b290848d254508bda4 |
| institution | Directory Open Access Journal |
| issn | 2423-673X 2423-6721 |
| language | English |
| last_indexed | 2024-03-08T16:03:31Z |
| publishDate | 2023-06-01 |
| publisher | University of Tehran |
| record_format | Article |
| series | Journal of Chemical and Petroleum Engineering |
| spelling | doaj.art-69e0154f5c0946b290848d254508bda42024-01-08T08:42:01ZengUniversity of TehranJournal of Chemical and Petroleum Engineering2423-673X2423-67212023-06-0157217919710.22059/jchpe.2023.345296.139792759Neural Network Modeling for Development of High-Pressure Measurement of Carbon Dioxide Solubility in the Aqueous AEEA+SulfolaneArman Hasanzadeh0Ahad Ghaemi1Shahrokh Shahhosseini2School of Chemical, Petroleum and Gas Engineering, Iran University of Science and Technology, Tehran, Iran.School of Chemical, Petroleum and Gas Engineering, Iran University of Science and Technology, Tehran, Iran.School of Chemical, Petroleum and Gas Engineering, Iran University of Science and Technology, Tehran,Due to increasing concerns about global warming regarding CO2 release to the atmosphere, various methods are used to capture CO2, among which chemical absorption via amine mixture solutions is very well developed. A set of 179 data related to CO2 absorption in a mixture, including a physical absorbent (sulfolane) and a chemical absorption (AEEA) in a wide range of temperature, pressure and solvent concentration is used to develop two Artificial Neural Networks (ANN). In Multi-Layer Perceptron (MLP), the Levenberg-Marquardt method is used to train the network. Most important factors such as regression analysis value (R2) of 0.99963, Mean Squared Error (MSE) value of 1.22E-05 and Average Absolute Relative Deviation value (%AARD) of 0.2671 factors reveal that the MLP network has a high capability to predict CO2 loading (αCO2). Also, a Radial Basis Function (RBF) network was developed. RBF network with a spread value of 2.2 and 138 neurons had an outstanding performance and achieved an MSE value of 2.53E-05 along with an R2 value of 0.99993, 11 seconds, and a %AARD value of 0.1460. According to experimental and predicted data, the neural networks are well trained and are able to predict CO2 loading precisely in an economic and optimized way.https://jchpe.ut.ac.ir/article_92759_84036e5d22cb6e5da89b60d3c7868c00.pdfco2mlprbfmodelingsolubility |
| spellingShingle | Arman Hasanzadeh Ahad Ghaemi Shahrokh Shahhosseini Neural Network Modeling for Development of High-Pressure Measurement of Carbon Dioxide Solubility in the Aqueous AEEA+Sulfolane Journal of Chemical and Petroleum Engineering co2 mlp rbf modeling solubility |
| title | Neural Network Modeling for Development of High-Pressure Measurement of Carbon Dioxide Solubility in the Aqueous AEEA+Sulfolane |
| title_full | Neural Network Modeling for Development of High-Pressure Measurement of Carbon Dioxide Solubility in the Aqueous AEEA+Sulfolane |
| title_fullStr | Neural Network Modeling for Development of High-Pressure Measurement of Carbon Dioxide Solubility in the Aqueous AEEA+Sulfolane |
| title_full_unstemmed | Neural Network Modeling for Development of High-Pressure Measurement of Carbon Dioxide Solubility in the Aqueous AEEA+Sulfolane |
| title_short | Neural Network Modeling for Development of High-Pressure Measurement of Carbon Dioxide Solubility in the Aqueous AEEA+Sulfolane |
| title_sort | neural network modeling for development of high pressure measurement of carbon dioxide solubility in the aqueous aeea sulfolane |
| topic | co2 mlp rbf modeling solubility |
| url | https://jchpe.ut.ac.ir/article_92759_84036e5d22cb6e5da89b60d3c7868c00.pdf |
| work_keys_str_mv | AT armanhasanzadeh neuralnetworkmodelingfordevelopmentofhighpressuremeasurementofcarbondioxidesolubilityintheaqueousaeeasulfolane AT ahadghaemi neuralnetworkmodelingfordevelopmentofhighpressuremeasurementofcarbondioxidesolubilityintheaqueousaeeasulfolane AT shahrokhshahhosseini neuralnetworkmodelingfordevelopmentofhighpressuremeasurementofcarbondioxidesolubilityintheaqueousaeeasulfolane |