Detecção de eventos de obstrução em válvula no processo de lingotamento contínuo com uso de aprendizado de máquinas

Página do item simplificado
dc.contributor.advisor-co1Co-orientador1
dc.contributor.advisor-co1IDhttps://orcid.org/
dc.contributor.advisor-co1Latteshttp://lattes.cnpq.br/
dc.contributor.advisor-co2Co-orientador2
dc.contributor.advisor-co2IDhttps://orcid.org/
dc.contributor.advisor-co2Latteshttp://lattes.cnpq.br/
dc.contributor.advisor-co3Co-orientador3
dc.contributor.advisor-co3IDhttps://orcid.org/
dc.contributor.advisor-co3Latteshttp://lattes.cnpq.br/
dc.contributor.advisor-co4Co-orientador4
dc.contributor.advisor-co4IDID do co-orientador4
dc.contributor.advisor-co4LattesLattes do co-orientador4
dc.contributor.advisor1Orientador1
dc.contributor.advisor1IDhttps://orcid.org/
dc.contributor.advisor1Latteshttp://lattes.cnpq.br/
dc.contributor.advisor2Orientador2
dc.contributor.advisor2IDhttps://orcid.org/
dc.contributor.advisor2Latteshttp://lattes.cnpq.br/
dc.contributor.authorDiniz, Ana Paula Miranda
dc.contributor.authorIDhttps://orcid.org/
dc.contributor.authorLatteshttp://lattes.cnpq.br/
dc.contributor.referee11º membro da banca
dc.contributor.referee1IDhttps://orcid.org/
dc.contributor.referee1Latteshttp://lattes.cnpq.br/
dc.contributor.referee22º membro da banca
dc.contributor.referee2IDhttps://orcid.org/
dc.contributor.referee2Latteshttp://lattes.cnpq.br/
dc.contributor.referee33º membro da banca
dc.contributor.referee3IDhttps://orcid.org/
dc.contributor.referee3Latteshttp://lattes.cnpq.br/
dc.contributor.referee44º membro da banca
dc.contributor.referee4Latteshttp://lattes.cnpq.br/
dc.contributor.referee55º membro da banca
dc.contributor.referee5IDhttps://orcid.org/
dc.contributor.referee5Latteshttp://lattes.cnpq.br/
dc.contributor.referee66º membro da banca
dc.contributor.referee6IDhttps://orcid.org/
dc.contributor.referee6Latteshttp://lattes.cnpq.br/
dc.contributor.referee77º membro da banca
dc.contributor.referee7IDhttps://orcid.org/
dc.contributor.referee7Latteshttp://lattes.cnpq.br/
dc.date.accessioned2024-09-11T19:39:30Z
dc.date.available2024-09-11T19:39:30Z
dc.date.issued2024-05-25
dc.description.abstractThe continuous casting process, used in the manufacture of steel plates, is currently the most economical and efficient way of production within the industry. Although continuous casting is a widely used process, some problems associated with the process have not yet been resolved, one of them being the obstruction of the Submerged Entry Nozzle (SEN), which controls the flow of steel between the tundish and the mold. This obstruction, also called clogging, not only impairs the quality of the product but also results in lower process yield, resulting in losses. Thus, clogging detection is of fundamental importance, because control actions can allow the system to operate for a longer time. In this work, methodologies based on Machine Learning and Deep Learning are presented and compared to detect the occurrences of clogging from historical data of process variables. In general, the performance of the classifiers achieved very promising results in real data with unbalanced classes. In particular, the method employing spatiotemporal analysis, using four process variables, obtained a remarkably superior performance when compared to the others, reaching averages of Precision and Recall, respectively, of 95.53% and 97.33%. To reduce the false positive and negative rates, a post-processing heuristic was implemented and applied to the model output, achieving a Precision and a Recall, respectively, of approximately 98% and 99%. To the best of our knowledge, these results have never been found in the literature. Although a detailed comparison is unfeasible due to the differences between the datasets and their inaccessibility, the modeling proposed here reached higher performance levels when compared to the results found in the literature to solve this industry’s problem. The high and unprecedented results obtained in this work, therefore, will contribute both to the improvement of the quality of the final product and to the reduction of costs associated with steel production, since the more effective classification of clogging occurrences can help operators in the corrective action planning
dc.description.resumoresumo
dc.formatText
dc.identifier.urihttp://repositorio.ufes.br/handle/10/17722
dc.languagepor
dc.language.isopt
dc.publisherUniversidade Federal do Espírito Santo
dc.publisher.countryBR
dc.publisher.courseDoutorado em Engenharia Elétrica
dc.publisher.departmentCentro Tecnológico
dc.publisher.initialsUFES
dc.publisher.programPrograma de Pós-Graduação em Engenharia Elétrica
dc.rightsopen access, restricted access ou embargoed access
dc.subjectPalavra-chave
dc.subject.cnpqEngenharia Elétrica
dc.titleDetecção de eventos de obstrução em válvula no processo de lingotamento contínuo com uso de aprendizado de máquinas
dc.typedoctoralThesis
foaf.mboxemail@ufes.br
Arquivos
Pacote Original
Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
AnaPaulaMirandaDiniz-2024-tese.pdf
Tamanho:
11.99 MB
Formato:
Adobe Portable Document Format
Descrição:
Baixar
Licença do Pacote
Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
license.txt
Tamanho:
1.71 KB
Formato:
Item-specific license agreed upon to submission
Descrição:
Baixar
Coleções
Doutorado em Engenharia Elétrica