A machine learning-based methodology for automated classification of risks in an oil refinery

Detalhes bibliográficos
Ano de defesa: 2019
Autor(a) principal: MACÊDO, July Bias
Orientador(a): MOURA, Márcio José das Chagas
Banca de defesa: Não Informado pela instituição
Tipo de documento: Dissertação
Tipo de acesso: Acesso aberto
Idioma: eng
Instituição de defesa: Universidade Federal de Pernambuco
Programa de Pós-Graduação: Programa de Pos Graduacao em Engenharia de Producao
Departamento: Não Informado pela instituição
País: Brasil
Palavras-chave em Português:
Engenharia de Produção
Avaliação de risco
Aprendizagem de máquina
Máquina de vetores de suporte
Refinarias de petróleo
Link de acesso: https://repositorio.ufpe.br/handle/123456789/33996
Resumo: Oil refineries process hazardous substances at extreme operational conditions to produce valuable products. The necessary and required risk assessment is generally rather time-consuming and involves a multidisciplinary group of experts to identify potential accidental hypotheses, and compute their frequency and severity. With respect to this context, in this work, we present a machine learning method to mine out useful knowledge and information from available data of past risk assessments. The aim is at automatically classifying possible accident scenarios that may occur in oil refinery processing units by using SVM (support vector machines). Data from a previous qualitative risk assessment of an ADU (atmospheric distillation unit) of a real oil refinery is used to demonstrate the applicability of the SVM-based approach. The test classification was made with an F1 score of 89.95%. In this way, the results obtained showed that the proposed method is promising for efficiently performing automated risk assessment of oil refineries.
id UFPE_1cf712d792f7c78c37a3028ec752e523
oai_identifier_str oai:repositorio.ufpe.br:123456789/33996
network_acronym_str UFPE
network_name_str Repositório Institucional da UFPE
repository_id_str
spelling MACÊDO, July Biashttp://lattes.cnpq.br/2540702750653143http://lattes.cnpq.br/7778828466828647MOURA, Márcio José das Chagas2019-10-01T16:24:59Z2019-10-01T16:24:59Z2019-02-19https://repositorio.ufpe.br/handle/123456789/33996Oil refineries process hazardous substances at extreme operational conditions to produce valuable products. The necessary and required risk assessment is generally rather time-consuming and involves a multidisciplinary group of experts to identify potential accidental hypotheses, and compute their frequency and severity. With respect to this context, in this work, we present a machine learning method to mine out useful knowledge and information from available data of past risk assessments. The aim is at automatically classifying possible accident scenarios that may occur in oil refinery processing units by using SVM (support vector machines). Data from a previous qualitative risk assessment of an ADU (atmospheric distillation unit) of a real oil refinery is used to demonstrate the applicability of the SVM-based approach. The test classification was made with an F1 score of 89.95%. In this way, the results obtained showed that the proposed method is promising for efficiently performing automated risk assessment of oil refineries.CAPESRefinarias de petróleo processam substâncias perigosas em condições operacionais extremas para produzir produtos valiosos. A execução da necessária e exigida avaliação de riscos é geralmente bastante demorada e envolve um grupo multidisciplinar de especialistas para identificar possíveis hipóteses acidentais e calcular suas frequências e a severidade de suas consequências. Com relação a este contexto, neste trabalho, apresenta-se um método de aprendizagem de máquina para extrair conhecimento e informações úteis a partir de avaliações anteriores de riscos. O objetivo é classificar automaticamente os possíveis cenários acidentais que possam ocorrer em unidades de processamento de refinaria de petróleo usando máquina de vetores de suporte. Os dados de uma avaliação de risco qualitativa previamente elaborada de uma ADU (unidade de destilação atmosférica) de uma refinaria de petróleo real são usados para demonstrar a aplicabilidade da abordagem baseada em SVM. A classificação dos dados de teste foi feita com um escore F1 de 89,95%. Os resultados obtidos demonstraram que o método proposto é promissor para realizar eficientemente avaliações automáticas de risco de refinarias de petróleo.engUniversidade Federal de PernambucoPrograma de Pos Graduacao em Engenharia de ProducaoUFPEBrasilAttribution-NonCommercial-NoDerivs 3.0 Brazilhttp://creativecommons.org/licenses/by-nc-nd/3.0/br/info:eu-repo/semantics/openAccessEngenharia de ProduçãoAvaliação de riscoAprendizagem de máquinaMáquina de vetores de suporteRefinarias de petróleoA machine learning-based methodology for automated classification of risks in an oil refineryinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesismestradoreponame:Repositório Institucional da UFPEinstname:Universidade Federal de Pernambuco (UFPE)instacron:UFPETHUMBNAILDISSERTAÇÃO July Bias Macêdo.pdf.jpgDISSERTAÇÃO July Bias Macêdo.pdf.jpgGenerated Thumbnailimage/jpeg1187https://repositorio.ufpe.br/bitstream/123456789/33996/5/DISSERTA%c3%87%c3%83O%20July%20Bias%20Mac%c3%aado.pdf.jpg6460e3c0794a5455e451a47d55a320feMD55ORIGINALDISSERTAÇÃO July Bias Macêdo.pdfDISSERTAÇÃO July Bias Macêdo.pdfapplication/pdf1229408https://repositorio.ufpe.br/bitstream/123456789/33996/1/DISSERTA%c3%87%c3%83O%20July%20Bias%20Mac%c3%aado.pdf334b3907d08ad66f34d9ced675d6d247MD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8811https://repositorio.ufpe.br/bitstream/123456789/33996/2/license_rdfe39d27027a6cc9cb039ad269a5db8e34MD52LICENSElicense.txtlicense.txttext/plain; charset=utf-82310https://repositorio.ufpe.br/bitstream/123456789/33996/3/license.txtbd573a5ca8288eb7272482765f819534MD53TEXTDISSERTAÇÃO July Bias Macêdo.pdf.txtDISSERTAÇÃO July Bias Macêdo.pdf.txtExtracted texttext/plain92539https://repositorio.ufpe.br/bitstream/123456789/33996/4/DISSERTA%c3%87%c3%83O%20July%20Bias%20Mac%c3%aado.pdf.txt2410391f7ac670abfcdacd50473f0c50MD54123456789/339962019-10-26 02:53:48.634oai:repositorio.ufpe.br:123456789/33996TGljZW7Dp2EgZGUgRGlzdHJpYnVpw6fDo28gTsOjbyBFeGNsdXNpdmEKClRvZG8gZGVwb3NpdGFudGUgZGUgbWF0ZXJpYWwgbm8gUmVwb3NpdMOzcmlvIEluc3RpdHVjaW9uYWwgKFJJKSBkZXZlIGNvbmNlZGVyLCDDoCBVbml2ZXJzaWRhZGUgRmVkZXJhbCBkZSBQZXJuYW1idWNvIChVRlBFKSwgdW1hIExpY2Vuw6dhIGRlIERpc3RyaWJ1acOnw6NvIE7Do28gRXhjbHVzaXZhIHBhcmEgbWFudGVyIGUgdG9ybmFyIGFjZXNzw612ZWlzIG9zIHNldXMgZG9jdW1lbnRvcywgZW0gZm9ybWF0byBkaWdpdGFsLCBuZXN0ZSByZXBvc2l0w7NyaW8uCgpDb20gYSBjb25jZXNzw6NvIGRlc3RhIGxpY2Vuw6dhIG7Do28gZXhjbHVzaXZhLCBvIGRlcG9zaXRhbnRlIG1hbnTDqW0gdG9kb3Mgb3MgZGlyZWl0b3MgZGUgYXV0b3IuCl9fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fXwoKTGljZW7Dp2EgZGUgRGlzdHJpYnVpw6fDo28gTsOjbyBFeGNsdXNpdmEKCkFvIGNvbmNvcmRhciBjb20gZXN0YSBsaWNlbsOnYSBlIGFjZWl0w6EtbGEsIHZvY8OqIChhdXRvciBvdSBkZXRlbnRvciBkb3MgZGlyZWl0b3MgYXV0b3JhaXMpOgoKYSkgRGVjbGFyYSBxdWUgY29uaGVjZSBhIHBvbMOtdGljYSBkZSBjb3B5cmlnaHQgZGEgZWRpdG9yYSBkbyBzZXUgZG9jdW1lbnRvOwpiKSBEZWNsYXJhIHF1ZSBjb25oZWNlIGUgYWNlaXRhIGFzIERpcmV0cml6ZXMgcGFyYSBvIFJlcG9zaXTDs3JpbyBJbnN0aXR1Y2lvbmFsIGRhIFVGUEU7CmMpIENvbmNlZGUgw6AgVUZQRSBvIGRpcmVpdG8gbsOjbyBleGNsdXNpdm8gZGUgYXJxdWl2YXIsIHJlcHJvZHV6aXIsIGNvbnZlcnRlciAoY29tbyBkZWZpbmlkbyBhIHNlZ3VpciksIGNvbXVuaWNhciBlL291IGRpc3RyaWJ1aXIsIG5vIFJJLCBvIGRvY3VtZW50byBlbnRyZWd1ZSAoaW5jbHVpbmRvIG8gcmVzdW1vL2Fic3RyYWN0KSBlbSBmb3JtYXRvIGRpZ2l0YWwgb3UgcG9yIG91dHJvIG1laW87CmQpIERlY2xhcmEgcXVlIGF1dG9yaXphIGEgVUZQRSBhIGFycXVpdmFyIG1haXMgZGUgdW1hIGPDs3BpYSBkZXN0ZSBkb2N1bWVudG8gZSBjb252ZXJ0w6otbG8sIHNlbSBhbHRlcmFyIG8gc2V1IGNvbnRlw7pkbywgcGFyYSBxdWFscXVlciBmb3JtYXRvIGRlIGZpY2hlaXJvLCBtZWlvIG91IHN1cG9ydGUsIHBhcmEgZWZlaXRvcyBkZSBzZWd1cmFuw6dhLCBwcmVzZXJ2YcOnw6NvIChiYWNrdXApIGUgYWNlc3NvOwplKSBEZWNsYXJhIHF1ZSBvIGRvY3VtZW50byBzdWJtZXRpZG8gw6kgbyBzZXUgdHJhYmFsaG8gb3JpZ2luYWwgZSBxdWUgZGV0w6ltIG8gZGlyZWl0byBkZSBjb25jZWRlciBhIHRlcmNlaXJvcyBvcyBkaXJlaXRvcyBjb250aWRvcyBuZXN0YSBsaWNlbsOnYS4gRGVjbGFyYSB0YW1iw6ltIHF1ZSBhIGVudHJlZ2EgZG8gZG9jdW1lbnRvIG7Do28gaW5mcmluZ2Ugb3MgZGlyZWl0b3MgZGUgb3V0cmEgcGVzc29hIG91IGVudGlkYWRlOwpmKSBEZWNsYXJhIHF1ZSwgbm8gY2FzbyBkbyBkb2N1bWVudG8gc3VibWV0aWRvIGNvbnRlciBtYXRlcmlhbCBkbyBxdWFsIG7Do28gZGV0w6ltIG9zIGRpcmVpdG9zIGRlCmF1dG9yLCBvYnRldmUgYSBhdXRvcml6YcOnw6NvIGlycmVzdHJpdGEgZG8gcmVzcGVjdGl2byBkZXRlbnRvciBkZXNzZXMgZGlyZWl0b3MgcGFyYSBjZWRlciDDoApVRlBFIG9zIGRpcmVpdG9zIHJlcXVlcmlkb3MgcG9yIGVzdGEgTGljZW7Dp2EgZSBhdXRvcml6YXIgYSB1bml2ZXJzaWRhZGUgYSB1dGlsaXrDoS1sb3MgbGVnYWxtZW50ZS4gRGVjbGFyYSB0YW1iw6ltIHF1ZSBlc3NlIG1hdGVyaWFsIGN1am9zIGRpcmVpdG9zIHPDo28gZGUgdGVyY2Vpcm9zIGVzdMOhIGNsYXJhbWVudGUgaWRlbnRpZmljYWRvIGUgcmVjb25oZWNpZG8gbm8gdGV4dG8gb3UgY29udGXDumRvIGRvIGRvY3VtZW50byBlbnRyZWd1ZTsKZykgU2UgbyBkb2N1bWVudG8gZW50cmVndWUgw6kgYmFzZWFkbyBlbSB0cmFiYWxobyBmaW5hbmNpYWRvIG91IGFwb2lhZG8gcG9yIG91dHJhIGluc3RpdHVpw6fDo28gcXVlIG7Do28gYSBVRlBFLCBkZWNsYXJhIHF1ZSBjdW1wcml1IHF1YWlzcXVlciBvYnJpZ2HDp8O1ZXMgZXhpZ2lkYXMgcGVsbyByZXNwZWN0aXZvIGNvbnRyYXRvIG91IGFjb3Jkby4KCkEgVUZQRSBpZGVudGlmaWNhcsOhIGNsYXJhbWVudGUgbyhzKSBub21lKHMpIGRvKHMpIGF1dG9yIChlcykgZG9zIGRpcmVpdG9zIGRvIGRvY3VtZW50byBlbnRyZWd1ZSBlIG7Do28gZmFyw6EgcXVhbHF1ZXIgYWx0ZXJhw6fDo28sIHBhcmEgYWzDqW0gZG8gcHJldmlzdG8gbmEgYWzDrW5lYSBjKS4KRepositório InstitucionalPUBhttps://repositorio.ufpe.br/oai/requestattena@ufpe.bropendoar:22212019-10-26T05:53:48Repositório Institucional da UFPE - Universidade Federal de Pernambuco (UFPE)false
dc.title.pt_BR.fl_str_mv A machine learning-based methodology for automated classification of risks in an oil refinery
title A machine learning-based methodology for automated classification of risks in an oil refinery
spellingShingle A machine learning-based methodology for automated classification of risks in an oil refinery
MACÊDO, July Bias
Engenharia de Produção
Avaliação de risco
Aprendizagem de máquina
Máquina de vetores de suporte
Refinarias de petróleo
title_short A machine learning-based methodology for automated classification of risks in an oil refinery
title_full A machine learning-based methodology for automated classification of risks in an oil refinery
title_fullStr A machine learning-based methodology for automated classification of risks in an oil refinery
title_full_unstemmed A machine learning-based methodology for automated classification of risks in an oil refinery
title_sort A machine learning-based methodology for automated classification of risks in an oil refinery
author MACÊDO, July Bias
author_facet MACÊDO, July Bias
author_role author
dc.contributor.authorLattes.pt_BR.fl_str_mv http://lattes.cnpq.br/2540702750653143
dc.contributor.advisorLattes.pt_BR.fl_str_mv http://lattes.cnpq.br/7778828466828647
dc.contributor.author.fl_str_mv MACÊDO, July Bias
dc.contributor.advisor1.fl_str_mv MOURA, Márcio José das Chagas
contributor_str_mv MOURA, Márcio José das Chagas
dc.subject.por.fl_str_mv Engenharia de Produção
Avaliação de risco
Aprendizagem de máquina
Máquina de vetores de suporte
Refinarias de petróleo
topic Engenharia de Produção
Avaliação de risco
Aprendizagem de máquina
Máquina de vetores de suporte
Refinarias de petróleo
description Oil refineries process hazardous substances at extreme operational conditions to produce valuable products. The necessary and required risk assessment is generally rather time-consuming and involves a multidisciplinary group of experts to identify potential accidental hypotheses, and compute their frequency and severity. With respect to this context, in this work, we present a machine learning method to mine out useful knowledge and information from available data of past risk assessments. The aim is at automatically classifying possible accident scenarios that may occur in oil refinery processing units by using SVM (support vector machines). Data from a previous qualitative risk assessment of an ADU (atmospheric distillation unit) of a real oil refinery is used to demonstrate the applicability of the SVM-based approach. The test classification was made with an F1 score of 89.95%. In this way, the results obtained showed that the proposed method is promising for efficiently performing automated risk assessment of oil refineries.
publishDate 2019
dc.date.accessioned.fl_str_mv 2019-10-01T16:24:59Z
dc.date.available.fl_str_mv 2019-10-01T16:24:59Z
dc.date.issued.fl_str_mv 2019-02-19
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://repositorio.ufpe.br/handle/123456789/33996
url https://repositorio.ufpe.br/handle/123456789/33996
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv Attribution-NonCommercial-NoDerivs 3.0 Brazil
http://creativecommons.org/licenses/by-nc-nd/3.0/br/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Attribution-NonCommercial-NoDerivs 3.0 Brazil
http://creativecommons.org/licenses/by-nc-nd/3.0/br/
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Universidade Federal de Pernambuco
dc.publisher.program.fl_str_mv Programa de Pos Graduacao em Engenharia de Producao
dc.publisher.initials.fl_str_mv UFPE
dc.publisher.country.fl_str_mv Brasil
publisher.none.fl_str_mv Universidade Federal de Pernambuco
dc.source.none.fl_str_mv reponame:Repositório Institucional da UFPE
instname:Universidade Federal de Pernambuco (UFPE)
instacron:UFPE
instname_str Universidade Federal de Pernambuco (UFPE)
instacron_str UFPE
institution UFPE
reponame_str Repositório Institucional da UFPE
collection Repositório Institucional da UFPE
bitstream.url.fl_str_mv https://repositorio.ufpe.br/bitstream/123456789/33996/5/DISSERTA%c3%87%c3%83O%20July%20Bias%20Mac%c3%aado.pdf.jpg
https://repositorio.ufpe.br/bitstream/123456789/33996/1/DISSERTA%c3%87%c3%83O%20July%20Bias%20Mac%c3%aado.pdf
https://repositorio.ufpe.br/bitstream/123456789/33996/2/license_rdf
https://repositorio.ufpe.br/bitstream/123456789/33996/3/license.txt
https://repositorio.ufpe.br/bitstream/123456789/33996/4/DISSERTA%c3%87%c3%83O%20July%20Bias%20Mac%c3%aado.pdf.txt
bitstream.checksum.fl_str_mv 6460e3c0794a5455e451a47d55a320fe
334b3907d08ad66f34d9ced675d6d247
e39d27027a6cc9cb039ad269a5db8e34
bd573a5ca8288eb7272482765f819534
2410391f7ac670abfcdacd50473f0c50
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
MD5
repository.name.fl_str_mv Repositório Institucional da UFPE - Universidade Federal de Pernambuco (UFPE)
repository.mail.fl_str_mv attena@ufpe.br
_version_ 1797782278082920448

Registros relacionados