View in EDS HTML Full Text PDF Full Text

Development of Smart Models to Accurately Predict Dynamic Viscosity of CO2-Saturated Polyethylene Glycol.

Saved in:
Bibliographic Details
Title: Development of Smart Models to Accurately Predict Dynamic Viscosity of CO2-Saturated Polyethylene Glycol.
Authors: Adhab, Ayat Hussein1 (AUTHOR), Mahdi, Morug Salih2 (AUTHOR), Kanabar, Bhavesh3 (AUTHOR) bhavesh.kanabar@marwadieducation.edu.in, Yadav, Anupam4 (AUTHOR), M K, Ranganathaswamy5 (AUTHOR), Thakur, Rishabh6 (AUTHOR), Kumar, Parveen7 (AUTHOR), Krishna, Braj8 (AUTHOR), Mansoor, Aseel Salah9 (AUTHOR), Radi, Usama Kadem10 (AUTHOR), Abd, Nasr Saadoun11 (AUTHOR), Sherzod, Samim12 (AUTHOR) samimsherzod@gmail.com
Source: Journal of Chemical Engineering of Japan. Dec2025, Vol. 58 Issue 1, p1-15. 15p.
Subjects: Dynamic viscosity, Viscosity, K-nearest neighbor classification, Machine learning, Multilayer perceptrons, Polyethylene glycol, Prediction models
Abstract: The role of carbon dioxide as a green alternative solvent has garnered significant interest for its application in various industrial processes, including chemical reactions, separations, and material processing. Polyethylene glycol (PEG) is a valuable compound with extensive applications in industries such as pharmaceuticals, biotechnology, and chemical engineering. Precise estimation of viscosity of CO2-saturated PEG is crucial for several scientific and industrial applications, as viscosity directly impacts the material's performance and feasibility in specific processes. This study, hence, introduces machine learning models utilizing K-nearest neighbors, decision tree, adaptive boosting, multilayer perceptron artificial neural network, convolutional neural network, support vector machine, random forest and ensemble learning algorithms to accurately forecast the dynamic viscosity of CO2-saturated PEG based on PEG molar mass, pressure, and temperature. An experimental dataset is employed to facilitate the development of these intelligent models. Additionally, the leverage method is utilized to assess the authenticity of the data for model development, while a relevancy index is used to elucidate the relative contributions of each input factor to the viscosity. The findings suggest that all the collected experimental data are appropriate for inclusion in the construction of data-driven models. Moreover, it is revealed that pressure, temperature and PEG molar mass have a negative effect on the viscosity of CO2-saturated PEG. Ultimately, multilayer perceptron artificial neural network model is found to be the most accurate method for predicting CO2-saturated PEG viscosity. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Chemical Engineering of Japan is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 190410650
AccessLevel: 6
PubType: Periodical
PubTypeId: serialPeriodical
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Development of Smart Models to Accurately Predict Dynamic Viscosity of CO<subscript>2</subscript>-Saturated Polyethylene Glycol.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Adhab%2C+Ayat+Hussein%22">Adhab, Ayat Hussein</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Mahdi%2C+Morug+Salih%22">Mahdi, Morug Salih</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Kanabar%2C+Bhavesh%22">Kanabar, Bhavesh</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> bhavesh.kanabar@marwadieducation.edu.in</i><br /><searchLink fieldCode="AR" term="%22Yadav%2C+Anupam%22">Yadav, Anupam</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22M+K%2C+Ranganathaswamy%22">M K, Ranganathaswamy</searchLink><relatesTo>5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Thakur%2C+Rishabh%22">Thakur, Rishabh</searchLink><relatesTo>6</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Kumar%2C+Parveen%22">Kumar, Parveen</searchLink><relatesTo>7</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Krishna%2C+Braj%22">Krishna, Braj</searchLink><relatesTo>8</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Mansoor%2C+Aseel+Salah%22">Mansoor, Aseel Salah</searchLink><relatesTo>9</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Radi%2C+Usama+Kadem%22">Radi, Usama Kadem</searchLink><relatesTo>10</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Abd%2C+Nasr+Saadoun%22">Abd, Nasr Saadoun</searchLink><relatesTo>11</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sherzod%2C+Samim%22">Sherzod, Samim</searchLink><relatesTo>12</relatesTo> (AUTHOR)<i> samimsherzod@gmail.com</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+Chemical+Engineering+of+Japan%22">Journal of Chemical Engineering of Japan</searchLink>. Dec2025, Vol. 58 Issue 1, p1-15. 15p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Dynamic+viscosity%22">Dynamic viscosity</searchLink><br /><searchLink fieldCode="DE" term="%22Viscosity%22">Viscosity</searchLink><br /><searchLink fieldCode="DE" term="%22K-nearest+neighbor+classification%22">K-nearest neighbor classification</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Multilayer+perceptrons%22">Multilayer perceptrons</searchLink><br /><searchLink fieldCode="DE" term="%22Polyethylene+glycol%22">Polyethylene glycol</searchLink><br /><searchLink fieldCode="DE" term="%22Prediction+models%22">Prediction models</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The role of carbon dioxide as a green alternative solvent has garnered significant interest for its application in various industrial processes, including chemical reactions, separations, and material processing. Polyethylene glycol (PEG) is a valuable compound with extensive applications in industries such as pharmaceuticals, biotechnology, and chemical engineering. Precise estimation of viscosity of CO2-saturated PEG is crucial for several scientific and industrial applications, as viscosity directly impacts the material's performance and feasibility in specific processes. This study, hence, introduces machine learning models utilizing K-nearest neighbors, decision tree, adaptive boosting, multilayer perceptron artificial neural network, convolutional neural network, support vector machine, random forest and ensemble learning algorithms to accurately forecast the dynamic viscosity of CO2-saturated PEG based on PEG molar mass, pressure, and temperature. An experimental dataset is employed to facilitate the development of these intelligent models. Additionally, the leverage method is utilized to assess the authenticity of the data for model development, while a relevancy index is used to elucidate the relative contributions of each input factor to the viscosity. The findings suggest that all the collected experimental data are appropriate for inclusion in the construction of data-driven models. Moreover, it is revealed that pressure, temperature and PEG molar mass have a negative effect on the viscosity of CO2-saturated PEG. Ultimately, multilayer perceptron artificial neural network model is found to be the most accurate method for predicting CO2-saturated PEG viscosity. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Journal of Chemical Engineering of Japan is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=190410650
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1080/00219592.2025.2465422
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 15
        StartPage: 1
    Subjects:
      – SubjectFull: Dynamic viscosity
        Type: general
      – SubjectFull: Viscosity
        Type: general
      – SubjectFull: K-nearest neighbor classification
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Multilayer perceptrons
        Type: general
      – SubjectFull: Polyethylene glycol
        Type: general
      – SubjectFull: Prediction models
        Type: general
    Titles:
      – TitleFull: Development of Smart Models to Accurately Predict Dynamic Viscosity of CO2-Saturated Polyethylene Glycol.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Adhab, Ayat Hussein
      – PersonEntity:
          Name:
            NameFull: Mahdi, Morug Salih
      – PersonEntity:
          Name:
            NameFull: Kanabar, Bhavesh
      – PersonEntity:
          Name:
            NameFull: Yadav, Anupam
      – PersonEntity:
          Name:
            NameFull: M K, Ranganathaswamy
      – PersonEntity:
          Name:
            NameFull: Thakur, Rishabh
      – PersonEntity:
          Name:
            NameFull: Kumar, Parveen
      – PersonEntity:
          Name:
            NameFull: Krishna, Braj
      – PersonEntity:
          Name:
            NameFull: Mansoor, Aseel Salah
      – PersonEntity:
          Name:
            NameFull: Radi, Usama Kadem
      – PersonEntity:
          Name:
            NameFull: Abd, Nasr Saadoun
      – PersonEntity:
          Name:
            NameFull: Sherzod, Samim
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 12
              Text: Dec2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 00219592
          Numbering:
            – Type: volume
              Value: 58
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Journal of Chemical Engineering of Japan
              Type: main
ResultId 1