Vapor-Liquid equilibria modeling using gray-box neural networks as binary interaction parameters predictor
Fuente:
Redalyc
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Artículo científico |
| Lingua: | en |
| Pubblicazione: |
Universidad Nacional de Colombia
2017
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1876457108944191488 |
|---|---|
| author | Eduardo Vyhmeister |
| author_facet | Eduardo Vyhmeister |
| contents | Vapor-Liquid equilibria modeling using gray-box neural networks as binary interaction parameters predictor Eduardo Vyhmeister Jonathan Rodríguez-Pino Lorenzo Reyes-Bozo Rosa Galleguillos-Pozo Héctor Valdés-González Roman Rodríguez-Maecker Ingeniería Non Peng Acetone Robinson Alcohol System Simulations of vapor-liquid equilibrium (VLE) are widely used given their impact on the scale, design, and extrapolation of different operational units. However, due to a number of factors, it is almost impossible to experimentally study each of the VLE systems. VLE simulations can be developed using representations that are strongly dependent on the nature and interactions of the compounds forming mixtures. A model that helps in predicting these interactions would facilitate simulation processes. A Gray Box Neural Network Model (GNM) was created as Binary Interaction Parameters predictors (BIP), which are estimated using state variables and information from pure components. This information was used to predict VLE behavior in mixtures and ranges not used in the mathematical formulation. The GNM prediction capabilities (including temperature dependency) showed an error level lower than 5% and 20% for mixtures considered and not considered in the training data, respectively. 2017 artículo científico 0012-7353 https://www.redalyc.org/articulo.oa?id=49655603029 https://www.redalyc.org/journal/496/49655603029/ https://www.redalyc.org/journal/496/49655603029/html/ https://www.redalyc.org/journal/496/49655603029/49655603029.epub https://www.redalyc.org/journal/496/49655603029/movil 10.15446/dyna.v84n203.56364 en http://www.redalyc.org/revista.oa?id=496 Dyna application/pdf Universidad Nacional de Colombia Dyna (Colombia) Num.203 Vol.84 |
| format | Artículo científico |
| id | redalyc_49655603029 |
| institution | Redalyc |
| language | en |
| publishDate | 2017 |
| publisher | Universidad Nacional de Colombia |
| spellingShingle | Vapor-Liquid equilibria modeling using gray-box neural networks as binary interaction parameters predictor Eduardo Vyhmeister Ingeniería Non Peng Acetone Robinson Alcohol System Vapor-Liquid equilibria modeling using gray-box neural networks as binary interaction parameters predictor Eduardo Vyhmeister Jonathan Rodríguez-Pino Lorenzo Reyes-Bozo Rosa Galleguillos-Pozo Héctor Valdés-González Roman Rodríguez-Maecker Ingeniería Non Peng Acetone Robinson Alcohol System Simulations of vapor-liquid equilibrium (VLE) are widely used given their impact on the scale, design, and extrapolation of different operational units. However, due to a number of factors, it is almost impossible to experimentally study each of the VLE systems. VLE simulations can be developed using representations that are strongly dependent on the nature and interactions of the compounds forming mixtures. A model that helps in predicting these interactions would facilitate simulation processes. A Gray Box Neural Network Model (GNM) was created as Binary Interaction Parameters predictors (BIP), which are estimated using state variables and information from pure components. This information was used to predict VLE behavior in mixtures and ranges not used in the mathematical formulation. The GNM prediction capabilities (including temperature dependency) showed an error level lower than 5% and 20% for mixtures considered and not considered in the training data, respectively. 2017 artículo científico 0012-7353 https://www.redalyc.org/articulo.oa?id=49655603029 https://www.redalyc.org/journal/496/49655603029/ https://www.redalyc.org/journal/496/49655603029/html/ https://www.redalyc.org/journal/496/49655603029/49655603029.epub https://www.redalyc.org/journal/496/49655603029/movil 10.15446/dyna.v84n203.56364 en http://www.redalyc.org/revista.oa?id=496 Dyna application/pdf Universidad Nacional de Colombia Dyna (Colombia) Num.203 Vol.84 |
| title | Vapor-Liquid equilibria modeling using gray-box neural networks as binary interaction parameters predictor |
| topic | Ingeniería Non Peng Acetone Robinson Alcohol System |
| url | https://www.redalyc.org/articulo.oa?id=49655603029 https://www.redalyc.org/journal/496/49655603029/ https://www.redalyc.org/journal/496/49655603029/html/ https://www.redalyc.org/journal/496/49655603029/49655603029.epub https://www.redalyc.org/journal/496/49655603029/movil |