View in EDS

Modeling Dynamic Viscosity of Pure Fatty Acid Methyl Esters via Robust Machine Learning Approaches.

Saved in:
Bibliographic Details
Title: Modeling Dynamic Viscosity of Pure Fatty Acid Methyl Esters via Robust Machine Learning Approaches.
Authors: Abu‐Shareha, Ahmad Adel1 (AUTHOR), Zaki, Magdi E. A.2 (AUTHOR), Alfilh, Raed3 (AUTHOR), Sudhamsu, Gadug4 (AUTHOR), Sahu, Prabhat Kumar5 (AUTHOR), Kamalesh, Murari Devakannan6 (AUTHOR), Sharma, Sumit7 (AUTHOR), Gomha, Sobhi M.8 (AUTHOR) smgomha@iu.edu.sa, Hussaini, Soraya9 (AUTHOR) soraya.hussaini1995@outlook.com
Source: Chemical Engineering & Technology. Apr2026, Vol. 49 Issue 4, p1-20. 20p.
Subjects: Dynamic viscosity, Machine learning, Biomass energy, Fatty acid methyl esters, Pressure measurement, Thermodynamics
Abstract: Fatty acid methyl esters (FAMEs) are renewable, biodegradable biofuels. This study built machine learning models (DT, AdaBoost, EL, K‐nearest neighboring (KNN), random forest (RF), EN, CNN, SVR, and MLP‐ANN) to predict their dynamic viscosity using 488 literature data points. Inputs: temperature, pressure, molar mass, and C/H/O fractions. Models used five‐fold cross‐validation (90% training/validation, 10% testing). Metrics: R2, mean squared error (MSE), AARE%. MLP‐ANN performed best (R2 = 0.9987, MSE = 0.0038, and AARE = 1.68%). DT and AdaBoost showed higher errors; elastic net was weakest (R2 = 0.8486, AARE ≈ 25.78%). Pressure was the most impactful parameter, followed by temperature. SHapley Additive exPlanations (SHAP) analysis confirmed pressure as dominant. The framework is robust, accurate, and cost‐effective across broad thermodynamic conditions. [ABSTRACT FROM AUTHOR]
Copyright of Chemical Engineering & Technology is the property of Wiley-Blackwell 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
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 193324062
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Modeling Dynamic Viscosity of Pure Fatty Acid Methyl Esters via Robust Machine Learning Approaches.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Abu‐Shareha%2C+Ahmad+Adel%22">Abu‐Shareha, Ahmad Adel</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zaki%2C+Magdi+E%2E+A%2E%22">Zaki, Magdi E. A.</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Alfilh%2C+Raed%22">Alfilh, Raed</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sudhamsu%2C+Gadug%22">Sudhamsu, Gadug</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sahu%2C+Prabhat+Kumar%22">Sahu, Prabhat Kumar</searchLink><relatesTo>5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Kamalesh%2C+Murari+Devakannan%22">Kamalesh, Murari Devakannan</searchLink><relatesTo>6</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sharma%2C+Sumit%22">Sharma, Sumit</searchLink><relatesTo>7</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Gomha%2C+Sobhi+M%2E%22">Gomha, Sobhi M.</searchLink><relatesTo>8</relatesTo> (AUTHOR)<i> smgomha@iu.edu.sa</i><br /><searchLink fieldCode="AR" term="%22Hussaini%2C+Soraya%22">Hussaini, Soraya</searchLink><relatesTo>9</relatesTo> (AUTHOR)<i> soraya.hussaini1995@outlook.com</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Chemical+Engineering+%26+Technology%22">Chemical Engineering & Technology</searchLink>. Apr2026, Vol. 49 Issue 4, p1-20. 20p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Dynamic+viscosity%22">Dynamic viscosity</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Biomass+energy%22">Biomass energy</searchLink><br /><searchLink fieldCode="DE" term="%22Fatty+acid+methyl+esters%22">Fatty acid methyl esters</searchLink><br /><searchLink fieldCode="DE" term="%22Pressure+measurement%22">Pressure measurement</searchLink><br /><searchLink fieldCode="DE" term="%22Thermodynamics%22">Thermodynamics</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Fatty acid methyl esters (FAMEs) are renewable, biodegradable biofuels. This study built machine learning models (DT, AdaBoost, EL, K‐nearest neighboring (KNN), random forest (RF), EN, CNN, SVR, and MLP‐ANN) to predict their dynamic viscosity using 488 literature data points. Inputs: temperature, pressure, molar mass, and C/H/O fractions. Models used five‐fold cross‐validation (90% training/validation, 10% testing). Metrics: R2, mean squared error (MSE), AARE%. MLP‐ANN performed best (R2 = 0.9987, MSE = 0.0038, and AARE = 1.68%). DT and AdaBoost showed higher errors; elastic net was weakest (R2 = 0.8486, AARE ≈ 25.78%). Pressure was the most impactful parameter, followed by temperature. SHapley Additive exPlanations (SHAP) analysis confirmed pressure as dominant. The framework is robust, accurate, and cost‐effective across broad thermodynamic conditions. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Chemical Engineering & Technology is the property of Wiley-Blackwell 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=193324062
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1002/ceat.70220
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 20
        StartPage: 1
    Subjects:
      – SubjectFull: Dynamic viscosity
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Biomass energy
        Type: general
      – SubjectFull: Fatty acid methyl esters
        Type: general
      – SubjectFull: Pressure measurement
        Type: general
      – SubjectFull: Thermodynamics
        Type: general
    Titles:
      – TitleFull: Modeling Dynamic Viscosity of Pure Fatty Acid Methyl Esters via Robust Machine Learning Approaches.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Abu‐Shareha, Ahmad Adel
      – PersonEntity:
          Name:
            NameFull: Zaki, Magdi E. A.
      – PersonEntity:
          Name:
            NameFull: Alfilh, Raed
      – PersonEntity:
          Name:
            NameFull: Sudhamsu, Gadug
      – PersonEntity:
          Name:
            NameFull: Sahu, Prabhat Kumar
      – PersonEntity:
          Name:
            NameFull: Kamalesh, Murari Devakannan
      – PersonEntity:
          Name:
            NameFull: Sharma, Sumit
      – PersonEntity:
          Name:
            NameFull: Gomha, Sobhi M.
      – PersonEntity:
          Name:
            NameFull: Hussaini, Soraya
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 04
              Text: Apr2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 09307516
          Numbering:
            – Type: volume
              Value: 49
            – Type: issue
              Value: 4
          Titles:
            – TitleFull: Chemical Engineering & Technology
              Type: main
ResultId 1