A comparative study on machine learning regression algorithms aplied to modeling gas centrifuge

dc.contributor.authorANDRADE, DELVONEI A. dept_BR
dc.contributor.authorMESQUITA, ROBERTO N. dept_BR
dc.contributor.authorNASCIMENTO, NATAN P.pt_BR
dc.coverageNacionalpt_BR
dc.date.accessioned2022-12-01T18:04:49Z
dc.date.available2022-12-01T18:04:49Z
dc.date.issued2022pt_BR
dc.description.abstractThe gas Centrifuge is a very hard equipment to model, because it involves a gas dynamic with many complications, such as hypersonic waves and rarefied regions combined with continuous flow areas. Therefore, data analysis regressions remain currently a very important technique to understand and describe the problem in a practical way. This paper intends to apply and compare several regression techniques using machine learning, to obtain a hydraulic and a separative power model of gas centrifuge used in enrichment plants. For this purpose, a set of normalized data composed of 134 experimental lines was used, observing the variables of interest, the separation power (dU), and the waste pressure (Pw), through the following explanatory variables: feed flow (F), cut (q), and product pressure (Pp). The comparisons were presented between the results obtained for the models generated by the following: algorithms, multivariate regression, multivariate adaptive regression splines – MARS, bootstrap aggregating multivariate adaptive regression splines – Bagging MARS, artificial neural network – ANN, extreme gradient boosting – XGBoost, support vector regression– Poly SVR, radial basis Function support vector regression – RBF SVR, K-nearest neighbors – KNN and Stacked Ensemble. That way, to avoid overfitting and provide insights about generalization of the models in unseen data, during the training phase, the k-fold cross validation approach was used. Subsequently, the residuals were analyzed, and the models were compared by the following metrics: Root mean square error – RMSE; Mean squared error – MSE; Mean absolute error – MAE; and Coefficient of determination – R2.pt_BR
dc.format.extent52669-52681pt_BR
dc.identifier.citationANDRADE, DELVONEI A. de; MESQUITA, ROBERTO N. de; NASCIMENTO, NATAN P. A comparative study on machine learning regression algorithms aplied to modeling gas centrifuge. <b>Brazilian Journal of Development</b>, v. 8, n. 7, p. 52669-52681, 2022. DOI: <a href="https://dx.doi.org/10.34117/bjdv8n7-265">10.34117/bjdv8n7-265</a>. Disponível em: http://repositorio.ipen.br/handle/123456789/33380.
dc.identifier.doi10.34117/bjdv8n7-265pt_BR
dc.identifier.fasciculo7pt_BR
dc.identifier.issn2525-8761pt_BR
dc.identifier.orcid0000-0002-5355-0925pt_BR
dc.identifier.orcid0000-0002-6689-3011pt_BR
dc.identifier.orcidhttps://orcid.org/0000-0002-5355-0925
dc.identifier.orcidhttps://orcid.org/0000-0002-6689-3011
dc.identifier.percentilfiSem Percentilpt_BR
dc.identifier.percentilfiCiteScoreSem Percentil CiteScorept_BR
dc.identifier.urihttp://repositorio.ipen.br/handle/123456789/33380
dc.identifier.vol8pt_BR
dc.relation.ispartofBrazilian Journal of Developmentpt_BR
dc.rightsopenAccesspt_BR
dc.subjectisotope separation
dc.subjectgas centrifuges
dc.subjectmachine learning
dc.subjectmultivariate analysis
dc.subjectneural networks
dc.subjectalgorithms
dc.subjectautomation
dc.titleA comparative study on machine learning regression algorithms aplied to modeling gas centrifugept_BR
dc.title.alternativeUm estudo comparativo sobre algoritmos de regressão de aprendizagem de máquinas aplicado à modelagem de centrífugas a gáspt_BR
dc.typeArtigo de periódicopt_BR
dspace.entity.typePublication
ipen.autorROBERTO NAVARRO DE MESQUITA
ipen.autorDELVONEI ALVES DE ANDRADE
ipen.codigoautor1375
ipen.codigoautor1258
ipen.contributor.ipenauthorROBERTO NAVARRO DE MESQUITA
ipen.contributor.ipenauthorDELVONEI ALVES DE ANDRADE
ipen.date.recebimento22-12
ipen.identifier.fiSem F.I.pt_BR
ipen.identifier.fiCiteScoreSem CiteScorept_BR
ipen.identifier.ipendoc29028pt_BR
ipen.type.genreArtigo
relation.isAuthorOfPublication1975aa9b-be26-4f48-8196-96eeb4c2c0c3
relation.isAuthorOfPublication0eeb4436-68e5-4573-a603-35f5fc912178
relation.isAuthorOfPublication.latestForDiscovery0eeb4436-68e5-4573-a603-35f5fc912178
sigepi.autor.atividadeMESQUITA, ROBERTO N. de:1375:420:Npt_BR
sigepi.autor.atividadeANDRADE, DELVONEI A. de:1258:420:Spt_BR
Pacote Original
Agora exibindo 1 - 1 de 1
Carregando...
Imagem de Miniatura
Nome:
29028.pdf
Tamanho:
678.39 KB
Formato:
Adobe Portable Document Format
Descrição:
Licença do Pacote
Agora exibindo 1 - 1 de 1
Nenhuma Miniatura disponível
Nome:
license.txt
Tamanho:
1.71 KB
Formato:
Item-specific license agreed upon to submission
Descrição:
Coleções