Prediction of phase equilibrium between soybean biodiesel, alcohols and supercritical CO2 using artificial neural networks
In this paper, a non-conventional approach of modeling phase equilibrium was applied. An alternative tool, the artificial neural network (ANN) technique has been used for estimating transition pressures for two ternary systems at high pressures (CO2 + Biodiesel + Methanol) and (CO2 + Biodiesel + Eth...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-06-01
|
| Series: | Chemical Thermodynamics and Thermal Analysis |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667312622000153 |
| _version_ | 1828344706021457920 |
|---|---|
| author | Gustavo Petroli Irede Dalmolin Claiton Zanini Brusamarello |
| author_facet | Gustavo Petroli Irede Dalmolin Claiton Zanini Brusamarello |
| author_sort | Gustavo Petroli |
| collection | DOAJ |
| description | In this paper, a non-conventional approach of modeling phase equilibrium was applied. An alternative tool, the artificial neural network (ANN) technique has been used for estimating transition pressures for two ternary systems at high pressures (CO2 + Biodiesel + Methanol) and (CO2 + Biodiesel + Ethanol). Temperatures, molar ratios, and compositions were utilized as input variables at ranges of 303.15 to 343.15 K, 4.30 to 15.62 MPa and 0.4 to 0.99, respectively. The databases taken from the literature were split into training, validating, and testing data. Multiple ANN structures were applied and the model with the lowest mean square error (MSE) was selected. The selected ANN model for the methanol system was a two-layered Feed-Forward Network and achieved a determination coefficient (R2) of 0.99878 and MSE of 0.01612. While the ethanol system was best described by an Elman Network presenting an R2 and MSE of 0.99359 and 0.06078, respectively. Results were then compared with Peng-Robinson models using van der Waals quadratic and Wong-Sandler mixing rules. The results showed a better agreement with experimental data than the thermodynamic models. |
| first_indexed | 2024-04-14T00:01:19Z |
| format | Article |
| id | doaj.art-7b4783db457043b5bbc2f186b838185c |
| institution | Directory Open Access Journal |
| issn | 2667-3126 |
| language | English |
| last_indexed | 2024-04-14T00:01:19Z |
| publishDate | 2022-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Chemical Thermodynamics and Thermal Analysis |
| spelling | doaj.art-7b4783db457043b5bbc2f186b838185c2022-12-22T02:23:42ZengElsevierChemical Thermodynamics and Thermal Analysis2667-31262022-06-016100048Prediction of phase equilibrium between soybean biodiesel, alcohols and supercritical CO2 using artificial neural networksGustavo Petroli0Irede Dalmolin1Claiton Zanini Brusamarello2Universidade Tecnológica Federal do Paraná (UTFPR), Engineering Department, Francisco Beltrão, BrazilUniversidade Tecnológica Federal do Paraná (UTFPR), Engineering Department, Francisco Beltrão, BrazilCorresponding author at: Universidade Tecnológica Federal do Paraná (UTFPR), Engineering Department, Francisco Beltrão, Brazil.; Universidade Tecnológica Federal do Paraná (UTFPR), Engineering Department, Francisco Beltrão, BrazilIn this paper, a non-conventional approach of modeling phase equilibrium was applied. An alternative tool, the artificial neural network (ANN) technique has been used for estimating transition pressures for two ternary systems at high pressures (CO2 + Biodiesel + Methanol) and (CO2 + Biodiesel + Ethanol). Temperatures, molar ratios, and compositions were utilized as input variables at ranges of 303.15 to 343.15 K, 4.30 to 15.62 MPa and 0.4 to 0.99, respectively. The databases taken from the literature were split into training, validating, and testing data. Multiple ANN structures were applied and the model with the lowest mean square error (MSE) was selected. The selected ANN model for the methanol system was a two-layered Feed-Forward Network and achieved a determination coefficient (R2) of 0.99878 and MSE of 0.01612. While the ethanol system was best described by an Elman Network presenting an R2 and MSE of 0.99359 and 0.06078, respectively. Results were then compared with Peng-Robinson models using van der Waals quadratic and Wong-Sandler mixing rules. The results showed a better agreement with experimental data than the thermodynamic models.http://www.sciencedirect.com/science/article/pii/S2667312622000153TransesterificationArtificial neural networksPhase equilibrium |
| spellingShingle | Gustavo Petroli Irede Dalmolin Claiton Zanini Brusamarello Prediction of phase equilibrium between soybean biodiesel, alcohols and supercritical CO2 using artificial neural networks Chemical Thermodynamics and Thermal Analysis Transesterification Artificial neural networks Phase equilibrium |
| title | Prediction of phase equilibrium between soybean biodiesel, alcohols and supercritical CO2 using artificial neural networks |
| title_full | Prediction of phase equilibrium between soybean biodiesel, alcohols and supercritical CO2 using artificial neural networks |
| title_fullStr | Prediction of phase equilibrium between soybean biodiesel, alcohols and supercritical CO2 using artificial neural networks |
| title_full_unstemmed | Prediction of phase equilibrium between soybean biodiesel, alcohols and supercritical CO2 using artificial neural networks |
| title_short | Prediction of phase equilibrium between soybean biodiesel, alcohols and supercritical CO2 using artificial neural networks |
| title_sort | prediction of phase equilibrium between soybean biodiesel alcohols and supercritical co2 using artificial neural networks |
| topic | Transesterification Artificial neural networks Phase equilibrium |
| url | http://www.sciencedirect.com/science/article/pii/S2667312622000153 |
| work_keys_str_mv | AT gustavopetroli predictionofphaseequilibriumbetweensoybeanbiodieselalcoholsandsupercriticalco2usingartificialneuralnetworks AT irededalmolin predictionofphaseequilibriumbetweensoybeanbiodieselalcoholsandsupercriticalco2usingartificialneuralnetworks AT claitonzaninibrusamarello predictionofphaseequilibriumbetweensoybeanbiodieselalcoholsandsupercriticalco2usingartificialneuralnetworks |