Predicting biodiesel properties and its optimal fatty acid profile via explainable machine learning

Basit Öğe Kaydı
dc.authoridIslam, Md Jahirul/0000-0002-0209-5336|Gunay, M. Erdem/0000-0003-1282-718X|Rasul, Mohammad/0000-0001-8159-1321|YILDIRIM, RAMAZAN/0000-0001-5077-5689|U, Anushri/0000-0002-8891-7766|Yeap, Aaron/0000-0001-7012-025X|Janaun, Jidon/0000-0002-9225-0845
dc.authorwosidIslam, Md Jahirul/AAU-6029-2020
dc.authorwosidJanaun, Jidon/H-1673-2016
dc.contributor.authorSuvarna, Manu
dc.contributor.authorJahirul, Mohammad Islam
dc.contributor.authorAaron-Yeap, Wai Hung
dc.contributor.authorAugustine, Cheryl Valencia
dc.contributor.authorUmesh, Anushri
dc.contributor.authorRasul, Mohammad Golam
dc.contributor.authorGunay, Mehmet Erdem
dc.date.accessioned2024-07-18T20:56:04Z
dc.date.available2024-07-18T20:56:04Z
dc.date.issued2022
dc.departmentİstanbul Bilgi Üniversitesien_US
dc.description.abstractThe accurate prediction of biodiesel fuel properties and determination of its optimal fatty acid (FA) profiles is a non-trivial process. To this aim, machine learning (ML) based predictive models were developed for cetane number (CN) and cold filter plugging point (CFPP), where the extreme gradient boost (XGB) and random forest (RF) algorithms had the best performance with R-2 of 0.89 and 0.91 on the test data, respectively. A classifier model for oxidative stability (OS) was devised to predict if it would pass or fail the ASTM and EU limits, where the support vector classifier (SVC) had the highest accuracy of 0.93 and 0.77 for ASTM and EU limits. Causal analysis via Shapley and Accumulated Local Effects revealed the significance and correlation of FAs with the fuel properties. This eventually aided the determination of the optimal FA composition via evolutionary optimization, such that the properties would meet the ASTM and EU standards. This study presents an end-to-end ML framework including descriptive, predictive, causal and prescriptive analytics to predict biodiesel fuel properties as a function of its FA composition; and eventually prescribes the optimal FA composition necessary to ensure that the fuel properties meet the regulatory standards.(c) 2022 Elsevier Ltd. All rights reserved.en_US
dc.description.sponsorshipUniversiti Malaysia Sabah Special Fund Scheme [SDK0321-2021]en_US
dc.description.sponsorshipFunding & acknowledgments This study is partly supported by Universiti Malaysia Sabah Special Fund Scheme (SDK0321-2021) . The authors would like to thank Dr. Sudip Talukdar, British Columbia Institute of Technology, Dr. Ranjeeth Kumar, Rianta Solution Inc., and Mr. Manas Bhatnagar, University of Southern California for their technical support. The authors would also like to thank DeepDyve, the online rental repository of academic publication for providing membership at discounted rates.en_US
dc.identifier.doi10.1016/j.renene.2022.02.124
dc.identifier.endpage258en_US
dc.identifier.issn0960-1481
dc.identifier.issn1879-0682
dc.identifier.scopus2-s2.0-85125951132en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.startpage245en_US
dc.identifier.urihttps://doi.org/10.1016/j.renene.2022.02.124
dc.identifier.urihttps://hdl.handle.net/11411/8849
dc.identifier.volume189en_US
dc.identifier.wosWOS:000780033100005en_US
dc.identifier.wosqualityQ1en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherPergamon-Elsevier Science Ltden_US
dc.relation.ispartofRenewable Energyen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectCetane Numberen_US
dc.subjectCold Filter Plugging Pointen_US
dc.subjectOxidative Stabilityen_US
dc.subjectSupport Vector Machinesen_US
dc.subjectExtreme Gradient Boosten_US
dc.subjectParticle-Swarm Optimizationen_US
dc.subjectCetane Numberen_US
dc.subjectKinematic Viscosityen_US
dc.subjectOxidative Stabilityen_US
dc.subjectChemical-Propertiesen_US
dc.subjectEngine Performanceen_US
dc.subjectVegetable-Oilsen_US
dc.subjectIntelligenten_US
dc.subjectDensityen_US
dc.titlePredicting biodiesel properties and its optimal fatty acid profile via explainable machine learningen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

Web of Science Indexed Publications
Scopus Indexed Publications