Predicting bubble size and bubble rate data in water and in froth flotation-like slurry from computational fluid dynamics (CFD) by applying deep neural networks (DNN)
Author
dc.contributor.author
Montes Atenas, Gonzalo
Author
dc.contributor.author
Seguel, Fabián
Author
dc.contributor.author
Valencia Musalem, Álvaro
Author
dc.contributor.author
Masood Bhatti, Sohail
Author
dc.contributor.author
Salman Khan, Muhammad
Author
dc.contributor.author
Soto Gómez, Ismael
Author
dc.contributor.author
Becerra Yoma, Néstor
Admission date
dc.date.accessioned
2016-12-29T19:04:20Z
Available date
dc.date.available
2016-12-29T19:04:20Z
Publication date
dc.date.issued
2016
Cita de ítem
dc.identifier.citation
International Communications in Heat and Mass Transfer 76 (2016) 197–201
es_ES
Identifier
dc.identifier.other
10.1016/j.icheatmasstransfer.2016.05.031
Identifier
dc.identifier.uri
https://repositorio.uchile.cl/handle/2250/142205
Abstract
dc.description.abstract
Accurate characterization of two phase bubbly flows is crucial in many industrial processes such as fluidized reactors, ore froth flotation, etc. The bubble size determines the rate at which components present in the gas phase are transferred to the surroundings and vice versa while bubble rate defines the appropriate bubbly flow regime occurring in the heterogeneous system. This research work employs deep neural networks (DNNs) to predict bubble size and bubble rate using data obtained from validated computational fluid dynamics (CFD) computations. Pure water and slurry (in conditions similar to those employed in mineral froth flotation) case studies are evaluated. It is found that the DNN can predict the CFD results accurately when using four hidden layers, describing discontinuities in the bubbly flow regime. The relative errors computed between the CFD data and the prediction obtained by the DNN is as low as 8.8% and 1.8% for bubble size and bubble rate, respectively. These results confirm that the DNN can be applied to sophisticated fluid dynamics systems and allow developing better control process strategies since once the DNN is trained critical variables can be computed very efficiently. The slurry case study, although restricted to the application of mineral froth flotation, can also be generalized to other industrial operations keeping the exact same procedure. (C) 2016 Elsevier Ltd. All rights reserved
International Communications in Heat and Mass Transfer
es_ES
Keywords
dc.subject
Constant flow conditions
es_ES
Keywords
dc.subject
Numerical-Simulation
es_ES
Keywords
dc.subject
Algorithm
es_ES
Título
dc.title
Predicting bubble size and bubble rate data in water and in froth flotation-like slurry from computational fluid dynamics (CFD) by applying deep neural networks (DNN)