Show simple item record

dc.contributor.authorTatar, Afshin
dc.contributor.authorNaseri, Saeid
dc.contributor.authorBahadori, Mohammad
dc.contributor.authorHezave, Ali Zeinolabedini
dc.contributor.authorKashiwao, Tomoaki
dc.contributor.authorBahadori, Alireza
dc.contributor.authorDarvish, Hoda
dc.date.accessioned2021-08-24T01:13:35Z
dc.date.available2021-08-24T01:13:35Z
dc.date.issued2016
dc.identifier.issn1876-1070
dc.identifier.doi10.1016/j.jtice.2015.11.002
dc.identifier.urihttp://hdl.handle.net/10072/407213
dc.description.abstractElimination of carbon dioxide from gas mixtures is a common commercial step in natural gas refineries. Nowadays, room-temperature ionic liquids, which are a relatively novel type of compounds have gained attention in recent years and have potential to be considered as a substitution for conventional volatile organic solvents in reaction and separation processes. No flammability, high thermal stability, a wide liquid range, and electric conductivity are some properties of ILs, which make them interesting more and more. Information about the solubility and the rate of solubility is a crucial factor for consideration of ILs for potential industrial processes. Because of some difficulties associated with experimental measurements and expenses spent on ILs, developing predictive methods for prognostication of the phase behavior of such types of systems are more favorable. Thermodynamic models are relatively complex and require complicated mathematical operations. Due to such difficulties there is a need to develop general models capable to predict phase behavior of systems such as CO2 with various kinds of ILs. In this study, four different methods based on artificial intelligence are proposed to predict CO2 solubility in different ionic liquids. The results showed that the predicted values are in great agreement with the experimental data and the maximum absolute error deviation for the best predictor is no more than 3.5%. A comparison between developed models and previously published ones reveals the superiority of the proposed models in this study.
dc.description.peerreviewedYes
dc.languageEnglish
dc.publisherELSEVIER SCIENCE BV
dc.relation.ispartofpagefrom151
dc.relation.ispartofpageto164
dc.relation.ispartofjournalJournal of the Taiwan Institute of Chemical Engineers
dc.relation.ispartofvolume60
dc.subject.fieldofresearchChemical engineering
dc.subject.fieldofresearchCivil engineering
dc.subject.fieldofresearchcode4004
dc.subject.fieldofresearchcode4005
dc.subject.keywordsScience & Technology
dc.subject.keywordsTechnology
dc.subject.keywordsEngineering, Chemical
dc.subject.keywordsEngineering
dc.subject.keywordsCO2 solubility
dc.titlePrediction of carbon dioxide solubility in ionic liquids using MLP and radial basis function (RBF) neural networks
dc.typeJournal article
dc.type.descriptionC1 - Articles
dcterms.bibliographicCitationTatar, A; Naseri, S; Bahadori, M; Hezave, AZ; Kashiwao, T; Bahadori, A; Darvish, H, Prediction of carbon dioxide solubility in ionic liquids using MLP and radial basis function (RBF) neural networks, Journal of the Taiwan Institute of Chemical Engineers, 2016, 60, pp. 151-164
dc.date.updated2021-08-24T01:12:04Z
gro.hasfulltextNo Full Text
gro.griffith.authorBahadori, Mohammad


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

  • Journal articles
    Contains articles published by Griffith authors in scholarly journals.

Show simple item record