Predicting phase inversion in agitated dispersions with machine learning algorithms

"In agitated systems, the phase inversion (PI) phenomenon – the mechanism by which a dispersed phase becomes the continuous one – has been studied extensively in an empirical manner and few models have been put forward through the years. The underlying physics are still to be fully understoo...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Maffi, Juan M., Estenoz, Diana
Formato: Artículos de Publicaciones Periódicas acceptedVersion
Lenguaje:Inglés
Publicado: info
Materias:
REDES NEURONALES
APRENDIZAJE AUTOMATICO
SEPARACION
EMULSIONES
Acceso en línea:http://ri.itba.edu.ar/handle/123456789/3202
Aporte de:
Repositorio Institucional Instituto Tecnológico de Buenos Aires (ITBA) de Instituto Tecnológico de Buenos Aires (ITBA)
id I32-R138-123456789-3202
record_format dspace
spelling I32-R138-123456789-32022022-12-07T13:05:39Z Predicting phase inversion in agitated dispersions with machine learning algorithms Maffi, Juan M. Estenoz, Diana REDES NEURONALES APRENDIZAJE AUTOMATICO SEPARACION EMULSIONES "In agitated systems, the phase inversion (PI) phenomenon – the mechanism by which a dispersed phase becomes the continuous one – has been studied extensively in an empirical manner and few models have been put forward through the years. The underlying physics are still to be fully understood. In this work, the experimental evidence published in literature is used to train machine learning models that may infer the inherent rules that lead to a given dispersion type (O/W or W/O), as well as predict the value of the dispersed phase volume fraction at the edge of the inversion point. Decision trees, bagged decision trees, support-vector machines and multiple perceptrons are implemented and compared. Results show that it is possible to infer an ensemble of physical rules that explain why a given dispersion is O/W or W/O, where a strong “turbulence constraint” is identified. The intuitive rule that PI occurs at 50% dispersed phase almost never holds. Moreover, neural networks have shown a better performance at predicting the PI point than the other algorithms tested. Finally, a theoretical study is performed in an effort to produce a phase inversion map with the relevant operating variables. This study showed a strong non-linear effect of the impeller-to-vessel size ratio, and an asymmetrical behavior of the interfacial tension on the phase inversion points." info:eu-repo/date/embargoEnd/2021-09-16 2020-10-26T18:00:25Z 2020-10-26T18:00:25Z 2020-09 Artículos de Publicaciones Periódicas info:eu-repo/semantics/acceptedVersion 0098-6445 http://ri.itba.edu.ar/handle/123456789/3202 en info:eu-repo/semantics/altIdentifier/doi/10.1080 / 00986445.2020.1815715 info:eu-repo/semantics/embargoedAccess application/pdf
institution Instituto Tecnológico de Buenos Aires (ITBA)
institution_str I-32
repository_str R-138
collection Repositorio Institucional Instituto Tecnológico de Buenos Aires (ITBA)
language Inglés
topic REDES NEURONALES
APRENDIZAJE AUTOMATICO
SEPARACION
EMULSIONES
spellingShingle REDES NEURONALES
APRENDIZAJE AUTOMATICO
SEPARACION
EMULSIONES
Maffi, Juan M.
Estenoz, Diana
Predicting phase inversion in agitated dispersions with machine learning algorithms
topic_facet REDES NEURONALES
APRENDIZAJE AUTOMATICO
SEPARACION
EMULSIONES
description "In agitated systems, the phase inversion (PI) phenomenon – the mechanism by which a dispersed phase becomes the continuous one – has been studied extensively in an empirical manner and few models have been put forward through the years. The underlying physics are still to be fully understood. In this work, the experimental evidence published in literature is used to train machine learning models that may infer the inherent rules that lead to a given dispersion type (O/W or W/O), as well as predict the value of the dispersed phase volume fraction at the edge of the inversion point. Decision trees, bagged decision trees, support-vector machines and multiple perceptrons are implemented and compared. Results show that it is possible to infer an ensemble of physical rules that explain why a given dispersion is O/W or W/O, where a strong “turbulence constraint” is identified. The intuitive rule that PI occurs at 50% dispersed phase almost never holds. Moreover, neural networks have shown a better performance at predicting the PI point than the other algorithms tested. Finally, a theoretical study is performed in an effort to produce a phase inversion map with the relevant operating variables. This study showed a strong non-linear effect of the impeller-to-vessel size ratio, and an asymmetrical behavior of the interfacial tension on the phase inversion points."
format Artículos de Publicaciones Periódicas
acceptedVersion
author Maffi, Juan M.
Estenoz, Diana
author_facet Maffi, Juan M.
Estenoz, Diana
author_sort Maffi, Juan M.
title Predicting phase inversion in agitated dispersions with machine learning algorithms
title_short Predicting phase inversion in agitated dispersions with machine learning algorithms
title_full Predicting phase inversion in agitated dispersions with machine learning algorithms
title_fullStr Predicting phase inversion in agitated dispersions with machine learning algorithms
title_full_unstemmed Predicting phase inversion in agitated dispersions with machine learning algorithms
title_sort predicting phase inversion in agitated dispersions with machine learning algorithms
publishDate info
url http://ri.itba.edu.ar/handle/123456789/3202
work_keys_str_mv AT maffijuanm predictingphaseinversioninagitateddispersionswithmachinelearningalgorithms
AT estenozdiana predictingphaseinversioninagitateddispersionswithmachinelearningalgorithms
_version_ 1765660874591174656

Ejemplares similares