Liquid-Liquid Dispersion Performance Prediction and Uncertainty Quantification Using Recurrent Neural Networks
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Liang, Fuyue | - |
dc.contributor.author | Valdes, Juan P. | - |
dc.contributor.author | Cheng, Sibo | - |
dc.contributor.author | Kahouadji, Lyes | - |
dc.contributor.author | Shin, Seungwon | - |
dc.contributor.author | Chergui, Jalel | - |
dc.contributor.author | Juric, Damir | - |
dc.contributor.author | Arcucci, Rossella | - |
dc.contributor.author | Matar, Omar K. | - |
dc.date.accessioned | 2024-06-24T05:00:26Z | - |
dc.date.available | 2024-06-24T05:00:26Z | - |
dc.date.issued | 2024-05-01 | - |
dc.identifier.issn | 0888-5885 | - |
dc.identifier.issn | 1520-5045 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hongik/handle/2020.sw.hongik/33210 | - |
dc.description.abstract | We demonstrate the application of a recurrent neural network (RNN) to perform multistep and multivariate time-series performance predictions for stirred and static mixers as exemplars of complex multiphase systems. We employ two network architectures in this study, fitted with either long short-term memory and gated recurrent unit cells, which are trained on high-fidelity, three-dimensional, computational fluid dynamics simulations of the mixer performance, in the presence and absence of surfactants, in terms of drop size distributions and interfacial areas as a function of system parameters; these include physicochemical properties, mixer geometry, and operating conditions. Our results demonstrate that while it is possible to train RNNs with a single fully connected layer more efficiently than with an encoder-decoder structure, the latter is shown to be more capable of learning long-term dynamics underlying dispersion metrics. Details of the methodology are presented, which include data preprocessing, RNN model exploration, and methods for model performance visualization; an ensemble-based procedure is also introduced to provide a measure of the model uncertainty. The workflow is designed to be generic and can be deployed to make predictions in other industrial applications with similar time-series data. © 2024 The Authors. Published by American Chemical Society. | - |
dc.format.extent | 23 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | American Chemical Society | - |
dc.title | Liquid-Liquid Dispersion Performance Prediction and Uncertainty Quantification Using Recurrent Neural Networks | - |
dc.type | Article | - |
dc.publisher.location | 미국 | - |
dc.identifier.doi | 10.1021/acs.iecr.4c00014 | - |
dc.identifier.scopusid | 2-s2.0-85191365206 | - |
dc.identifier.wosid | 001242278900001 | - |
dc.identifier.bibliographicCitation | Industrial and Engineering Chemistry Research, v.63, no.17, pp 7853 - 7875 | - |
dc.citation.title | Industrial and Engineering Chemistry Research | - |
dc.citation.volume | 63 | - |
dc.citation.number | 17 | - |
dc.citation.startPage | 7853 | - |
dc.citation.endPage | 7875 | - |
dc.type.docType | Article | - |
dc.description.isOpenAccess | Y | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Engineering, Chemical | - |
dc.subject.keywordPlus | DROP SIZE DISTRIBUTIONS | - |
dc.subject.keywordPlus | FLOW | - |
dc.subject.keywordPlus | TRACKING | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
94, Wausan-ro, Mapo-gu, Seoul, 04066, Korea02-320-1314
COPYRIGHT 2020 HONGIK UNIVERSITY. ALL RIGHTS RESERVED.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.