Modelling of Adsorption of Methane, Nitrogen, Carbon Dioxide, Their Binary Mixtures, and Their Ternary Mixture on Activated Carbons Using Artificial Neural Network
This work examines the use of neural networks in modelling the adsorption process of gas mixtures (CO2, CH4, and N2) on different activated carbons. Seven feed-forward neural network models, characterized by different structures, were constructed with the aim of predicting the adsorption of gas mixt...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Croatian Society of Chemical Engineers
2019-07-01
|
| Series: | Kemija u Industriji |
| Subjects: | |
| Online Access: | http://silverstripe.fkit.hr/kui/assets/Uploads/III-289-302.pdf |
| _version_ | 1819123556043194368 |
|---|---|
| author | Hadjer Barki Latifa Khaouane Salah Hanini |
| author_facet | Hadjer Barki Latifa Khaouane Salah Hanini |
| author_sort | Hadjer Barki |
| collection | DOAJ |
| description | This work examines the use of neural networks in modelling the adsorption process of gas mixtures (CO2, CH4, and N2) on different activated carbons. Seven feed-forward neural network models, characterized by different structures, were constructed with the aim of predicting the adsorption of gas mixtures. A set of 417, 625, 143, 87, 64, 64, and 40 data points for NN1 to NN7, respectively, were used to test the neural networks. Of the total data, 60 %, 20 %, and 20 % were used, respectively, for training, validation, and testing of the seven models. Results show a good fit between the predicted and experimental values for each model; good correlations were found (R = 0.99656 for NN1, R = 0.99284 for NN2, R = 0.99388 for NN3, R = 0.99639 for Q1 for NN4, R = 0.99472 for Q2 for NN4, R = 0.99716 for Q1 for NN5, R = 0.99752 for Q3 for NN5, R = 0.99746 for Q2 for NN6, R = 0.99783 for Q3 for NN6, R = 0.9946 for Q1 for NN7, R = 0.99089 for Q2 for NN7, and R = 0.9947 for Q3 for NN7). Moreover, the comparison between the predicted results and the classical models (Gibbs model, Generalized dual-site Langmuir model, and Ideal Adsorption Solution Theory) shows that the neural network models gave far better results. |
| first_indexed | 2024-12-22T07:10:13Z |
| format | Article |
| id | doaj.art-f5db50b3e00d421082720f5b2d3ff2fc |
| institution | Directory Open Access Journal |
| issn | 0022-9830 1334-9090 |
| language | English |
| last_indexed | 2024-12-22T07:10:13Z |
| publishDate | 2019-07-01 |
| publisher | Croatian Society of Chemical Engineers |
| record_format | Article |
| series | Kemija u Industriji |
| spelling | doaj.art-f5db50b3e00d421082720f5b2d3ff2fc2022-12-21T18:34:33ZengCroatian Society of Chemical EngineersKemija u Industriji0022-98301334-90902019-07-01687-828930210.15255/KUI.2019.002Modelling of Adsorption of Methane, Nitrogen, Carbon Dioxide, Their Binary Mixtures, and Their Ternary Mixture on Activated Carbons Using Artificial Neural NetworkHadjer Barki0Latifa Khaouane1Salah Hanini2Laboratoire de Biomatériaux et Phénomènes de Transport (LBMPT), Université de Médéa, Pôle urbain, 26 000, MEDEA, AlgeriaLaboratoire de Biomatériaux et Phénomènes de Transport (LBMPT), Université de Médéa, Pôle urbain, 26 000, MEDEA, AlgeriaLaboratoire de Biomatériaux et Phénomènes de Transport (LBMPT), Université de Médéa, Pôle urbain, 26 000, MEDEA, AlgeriaThis work examines the use of neural networks in modelling the adsorption process of gas mixtures (CO2, CH4, and N2) on different activated carbons. Seven feed-forward neural network models, characterized by different structures, were constructed with the aim of predicting the adsorption of gas mixtures. A set of 417, 625, 143, 87, 64, 64, and 40 data points for NN1 to NN7, respectively, were used to test the neural networks. Of the total data, 60 %, 20 %, and 20 % were used, respectively, for training, validation, and testing of the seven models. Results show a good fit between the predicted and experimental values for each model; good correlations were found (R = 0.99656 for NN1, R = 0.99284 for NN2, R = 0.99388 for NN3, R = 0.99639 for Q1 for NN4, R = 0.99472 for Q2 for NN4, R = 0.99716 for Q1 for NN5, R = 0.99752 for Q3 for NN5, R = 0.99746 for Q2 for NN6, R = 0.99783 for Q3 for NN6, R = 0.9946 for Q1 for NN7, R = 0.99089 for Q2 for NN7, and R = 0.9947 for Q3 for NN7). Moreover, the comparison between the predicted results and the classical models (Gibbs model, Generalized dual-site Langmuir model, and Ideal Adsorption Solution Theory) shows that the neural network models gave far better results.http://silverstripe.fkit.hr/kui/assets/Uploads/III-289-302.pdfactivated carbonsadsorptiongas mixturemodellingneural network |
| spellingShingle | Hadjer Barki Latifa Khaouane Salah Hanini Modelling of Adsorption of Methane, Nitrogen, Carbon Dioxide, Their Binary Mixtures, and Their Ternary Mixture on Activated Carbons Using Artificial Neural Network Kemija u Industriji activated carbons adsorption gas mixture modelling neural network |
| title | Modelling of Adsorption of Methane, Nitrogen, Carbon Dioxide, Their Binary Mixtures, and Their Ternary Mixture on Activated Carbons Using Artificial Neural Network |
| title_full | Modelling of Adsorption of Methane, Nitrogen, Carbon Dioxide, Their Binary Mixtures, and Their Ternary Mixture on Activated Carbons Using Artificial Neural Network |
| title_fullStr | Modelling of Adsorption of Methane, Nitrogen, Carbon Dioxide, Their Binary Mixtures, and Their Ternary Mixture on Activated Carbons Using Artificial Neural Network |
| title_full_unstemmed | Modelling of Adsorption of Methane, Nitrogen, Carbon Dioxide, Their Binary Mixtures, and Their Ternary Mixture on Activated Carbons Using Artificial Neural Network |
| title_short | Modelling of Adsorption of Methane, Nitrogen, Carbon Dioxide, Their Binary Mixtures, and Their Ternary Mixture on Activated Carbons Using Artificial Neural Network |
| title_sort | modelling of adsorption of methane nitrogen carbon dioxide their binary mixtures and their ternary mixture on activated carbons using artificial neural network |
| topic | activated carbons adsorption gas mixture modelling neural network |
| url | http://silverstripe.fkit.hr/kui/assets/Uploads/III-289-302.pdf |
| work_keys_str_mv | AT hadjerbarki modellingofadsorptionofmethanenitrogencarbondioxidetheirbinarymixturesandtheirternarymixtureonactivatedcarbonsusingartificialneuralnetwork AT latifakhaouane modellingofadsorptionofmethanenitrogencarbondioxidetheirbinarymixturesandtheirternarymixtureonactivatedcarbonsusingartificialneuralnetwork AT salahhanini modellingofadsorptionofmethanenitrogencarbondioxidetheirbinarymixturesandtheirternarymixtureonactivatedcarbonsusingartificialneuralnetwork |