Logo do repositório
 
Publicação

Performance analysis of steel W18CR4V grinding using RSM, DNN-GA, KNN, LM, DT, SVM models, and optimization via desirability function and MOGWO

2025-02-28Artigo de investigação Acesso aberto
Ver registo simples
datacite.subject.fosEngenharia e Tecnologia::Engenharia Mecânica
datacite.subject.sdg09:Indústria, Inovação e Infraestruturas
dc.contributor.authorFernandes, Filipe
dc.contributor.authorTouati, Sofiane
dc.contributor.authorBoumediri, Haithem
dc.contributor.authorKarmi, Yacine
dc.contributor.authorChitour, Mourad
dc.contributor.authorBoumediri, Khaled
dc.contributor.authorZemmouri, Amina
dc.contributor.authorMoussa, Athmani
dc.date.accessioned2026-02-11T14:06:42Z
dc.date.available2026-02-11T14:06:42Z
dc.date.issued2025-02-28
dc.description.abstractThis study presents an innovative approach to optimizing the grinding process of W18CR4V steel, a high-performance material used in reamer manufacturing, using advanced machine learning models and multi-objective optimization techniques. The novel combination of Deep Neural Networks with Genetic Algorithm (DNN-GA), K-Nearest Neighbors (KNN), Levenberg-Marquardt (LM), Decision Trees (DT), and Support Vector Machines (SVM) was employed to predict key process outcomes, such as surface roughness (Ra), maximum roughness height (Rz), and production time. The results reveal significant improvements, with Ra values ranging from 0.231 μm to 1.250 μm (up to 81.5 % reduction) and Rz from 1.519 μm to 6.833 μm (up to 77.7 % reduction). The hybrid DNN-GA model achieved R2 > 0.99, reducing prediction errors by 23–45 % compared to traditional models. Optimization via the Desirability Function achieved Ra values around 0.341 μm and Rz around 2.3 μm, with production times ranging from 1181 to 1426 s. The innovative Multi-Objective Grey Wolf Optimization (MOGWO) provided Pareto-optimal solutions, minimizing Ra to 0.3 μm, Rz to 1.5 μm, and production times between 2000 and 3000 s, offering better balance between surface quality and machining efficiency. This work highlights the unique integration of machine learning models with optimization techniques to significantly enhance grinding performance and manufacturing efficiency in high-precision industries.eng
dc.description.sponsorshipFilipe Fernandes acknowledges the UIDB/00285/2020 and LA/P/0112/2020 projects, sponsored by FEDER Funds through Portugal 2020 (PT2020), the Competitiveness and Internationalization Operational Program (COMPETE 2020), and national funds through the Portuguese Foundation for Science and Technology (FCT).
dc.identifier.citationSofiane Touati, Haithem Boumediri, Yacine Karmi, Mourad Chitour, Khaled Boumediri, Amina Zemmouri, Athmani Moussa, Filipe Fernandes, Performance analysis of steel W18CR4V grinding using RSM, DNN-GA, KNN, LM, DT, SVM models, and optimization via desirability function and MOGWO, Heliyon, Volume 11, Issue 4, 2025, e42640, https://doi.org/10.1016/j.heliyon.2025.e42640
dc.identifier.doi10.1016/j.heliyon.2025.e42640
dc.identifier.issn2405-8440
dc.identifier.urihttp://hdl.handle.net/10400.22/31824
dc.language.isoeng
dc.peerreviewedyes
dc.publisherCell Press
dc.relationCentre for Mechanical Enginnering, Materials and Processes
dc.relation.hasversionhttps://www.sciencedirect.com/science/article/pii/S2405844025010205?via%3Dihub
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectGrinding process
dc.subjectW18CR4V steel
dc.subjectSurface roughness
dc.subjectMachine learning models
dc.subjectMulti-objective grey wolf optimization (MOGWO)
dc.subjectDesirability function
dc.titlePerformance analysis of steel W18CR4V grinding using RSM, DNN-GA, KNN, LM, DT, SVM models, and optimization via desirability function and MOGWOeng
dc.typeresearch article
dspace.entity.typePublication
oaire.awardTitleCentre for Mechanical Enginnering, Materials and Processes
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F00285%2F2020/PT
oaire.citation.issue4
oaire.citation.titleHeliyon
oaire.citation.volume11
oaire.fundingStream6817 - DCRRNI ID
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameFernandes
person.givenNameFilipe
person.identifier995468
person.identifier.ciencia-id2113-A18B-EEE8
person.identifier.orcid0000-0003-4035-3241
person.identifier.scopus-author-id55644767300
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
relation.isAuthorOfPublicationf3fb450f-5f22-4f0c-8916-7742d519f6af
relation.isAuthorOfPublication.latestForDiscoveryf3fb450f-5f22-4f0c-8916-7742d519f6af
relation.isProjectOfPublicatione9972dd7-ceaf-49ee-959a-d2a0e393b124
relation.isProjectOfPublication.latestForDiscoverye9972dd7-ceaf-49ee-959a-d2a0e393b124

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
ART_FernandesF_CIDEM_2025_07.pdf
Tamanho:
11.78 MB
Formato:
Adobe Portable Document Format
Ver/Abrir
Licença
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
license.txt
Tamanho:
4.03 KB
Formato:
Item-specific license agreed upon to submission
Descrição:
Ver/Abrir

Coleções

ISEP – CIDEM – Artigos