Data Driven Performance Prediction in Steel Making

Simple item page
dc.contributor.authorBoto, Fernando
dc.contributor.authorMurua, Maialen
dc.contributor.authorGutierrez, Teresa
dc.contributor.authorCasado, Sara
dc.contributor.authorCarrillo, Ana
dc.contributor.authorArteaga, Asier
dc.contributor.institutionTecnalia Research & Innovation
dc.contributor.institutionFACTORY
dc.contributor.institutionCIRMETAL
dc.contributor.institutionPROMETAL
dc.date.issued2022-01-18
dc.descriptionPublisher Copyright: © 2022 by the authors. Licensee MDPI, Basel, Switzerland.
dc.description.abstractThis work presents three data-driven models based on process data, to estimate different indicators related to process performance in a steel production process. The generated models allow the optimization of the process parameters to achieve optimal performance and quality levels. A new approach based on ensembles has been developed with feature selection methods and four state-of-the-art regression approximations (random forest, gradient boosting, xgboost and neural networks). The results show that the proposed approach makes the prediction more stable reducing the variance for all cases, even in one case, slightly reducing the bias. Furthermore, from the four machine learning paradigms presented, random forest is the one with the best results in a quantitative way, obtaining a coefficient of determination of 0.98 as a maximum, depending on the target sub-process.en
dc.description.statusPeer reviewed
dc.format.extent1
dc.format.extent5004886
dc.identifier.citationBoto , F , Murua , M , Gutierrez , T , Casado , S , Carrillo , A & Arteaga , A 2022 , ' Data Driven Performance Prediction in Steel Making ' , Metals , vol. 12 , no. 2 , 172 , pp. 172 . https://doi.org/10.3390/met12020172
dc.identifier.doi10.3390/met12020172
dc.identifier.issn2075-4701
dc.identifier.otherresearchoutputwizard: 11556/1295
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85122889197&partnerID=8YFLogxK
dc.language.isoeng
dc.relation.ispartofMetals
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subject.keywordsSteel making
dc.subject.keywordsEnsemble learning
dc.subject.keywordsFeature selection
dc.subject.keywordsRandom forest
dc.subject.keywordsOptimization
dc.subject.keywordsSteel making
dc.subject.keywordsEnsemble learning
dc.subject.keywordsFeature selection
dc.subject.keywordsRandom forest
dc.subject.keywordsOptimization
dc.subject.keywordsGeneral Materials Science
dc.subject.keywordsMetals and Alloys
dc.subject.keywordsProject ID
dc.subject.keywordsinfo:eu-repo/grantAgreement/EC/H2020/723661/EU/Coordinating Optimisation of Complex Industrial Processes/COCOP
dc.subject.keywordsinfo:eu-repo/grantAgreement/EC/H2020/723661/EU/Coordinating Optimisation of Complex Industrial Processes/COCOP
dc.subject.keywordsFunding Info
dc.subject.keywordsThis research is supported by the European Union’s Horizon 2020 Research and Innovation Framework Programme [grant agreement No 723661; COCOP; http://www.cocop-spire.eu (accessed on 6 January 2022)]. The authors want to acknowledge the work of the whole COCOP consortium.
dc.subject.keywordsThis research is supported by the European Union’s Horizon 2020 Research and Innovation Framework Programme [grant agreement No 723661; COCOP; http://www.cocop-spire.eu (accessed on 6 January 2022)]. The authors want to acknowledge the work of the whole COCOP consortium.
dc.titleData Driven Performance Prediction in Steel Makingen
dc.typejournal article
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
metals-12-00172-v2.pdf
Size:
4.77 MB
Format:
Adobe Portable Document Format
Download