Desenvolvimento de sensor virtual utilizando redes neurais artificiais na destilação de bebidas fermentadas
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Tipo de documento: | Dissertação |
Idioma: | por |
Título da fonte: | Repositório Institucional da UFS |
Texto Completo: | http://ri.ufs.br/jspui/handle/riufs/17051 |
Resumo: | The need to monitor industrial processes reliably to ensure products quality contrasts with the high cost of available equipments and the difficulty of obtaining information in real time. In relation to Brazilian distilleries producing spirits, this is an even greater challenge, since most are small, often family-owned enterprises. In this context, virtual sensors are a viable alternative for their ability to provide information about quality variables such as composition from easily measurable primary variables such as temperature and pressure using mathematical models programmed into hardware devices. With this objective, this work develops a soft sensor to infer the composition of ethanol in a batch distillation process in the production of distilled beverages of tropical fruits, overcoming the difficulty in the execution of the distillation cuts, made by a craft way. The proposed sensor is based on an artificial neural network of the feedforward multilayer perceptron type, which applies the Levenberg-Marquardt algorithm in the optimization of its parameters. For its construction were used data from binary distillations produced in the laboratory, composed of ethanol and water and with initial concentration close to the initial concentration of fermented fruit must. The built sensor presented excellent results, with mean absolute error (EAM) of 0,0140 to 0,0311 in mass fraction in the experiments performed. In order to prove its efficiency in the situation of interest, the sensor was tested in the fermented must distillations of mango, watermelon and jabuticaba, also produced in the laboratory, obtaining an excellent performance, with EAM of 0.0160 to 0.0324. In this way, the proposed virtual sensor proved capable of inferring the ethanol composition over time in a reliable way, being a viable alternative for the efficient monitoring. |
id |
UFS-2_156eb93ad10032d012fe18ece5b3b0ab |
---|---|
oai_identifier_str |
oai:ufs.br:riufs/17051 |
network_acronym_str |
UFS-2 |
network_name_str |
Repositório Institucional da UFS |
repository_id_str |
|
spelling |
Lima, Tiago Hora Alves deOliveira Junior, Antônio Martins de2023-02-03T22:59:37Z2023-02-03T22:59:37Z2019-04-09LIMA, Tiago Hora Alves de. Desenvolvimento de sensor virtual utilizando redes neurais artificiais na destilação de bebidas fermentadas. 2019. 72 f. Dissertação (Mestrado em Engenharia Química) - Universidade Federal de Sergipe, São Cristóvão, 2019.http://ri.ufs.br/jspui/handle/riufs/17051The need to monitor industrial processes reliably to ensure products quality contrasts with the high cost of available equipments and the difficulty of obtaining information in real time. In relation to Brazilian distilleries producing spirits, this is an even greater challenge, since most are small, often family-owned enterprises. In this context, virtual sensors are a viable alternative for their ability to provide information about quality variables such as composition from easily measurable primary variables such as temperature and pressure using mathematical models programmed into hardware devices. With this objective, this work develops a soft sensor to infer the composition of ethanol in a batch distillation process in the production of distilled beverages of tropical fruits, overcoming the difficulty in the execution of the distillation cuts, made by a craft way. The proposed sensor is based on an artificial neural network of the feedforward multilayer perceptron type, which applies the Levenberg-Marquardt algorithm in the optimization of its parameters. For its construction were used data from binary distillations produced in the laboratory, composed of ethanol and water and with initial concentration close to the initial concentration of fermented fruit must. The built sensor presented excellent results, with mean absolute error (EAM) of 0,0140 to 0,0311 in mass fraction in the experiments performed. In order to prove its efficiency in the situation of interest, the sensor was tested in the fermented must distillations of mango, watermelon and jabuticaba, also produced in the laboratory, obtaining an excellent performance, with EAM of 0.0160 to 0.0324. In this way, the proposed virtual sensor proved capable of inferring the ethanol composition over time in a reliable way, being a viable alternative for the efficient monitoring.A necessidade de monitorar os processos industriais de forma confiável para garantir a qualidade dos produtos contrasta com o alto custo dos equipamentos disponíveis e a dificuldade de obter informações em tempo real. Em relação às destilarias brasileiras produtoras de aguardente se trata de um desafio ainda maior, visto que a maioria são empresas pequenas, muitas vezes familiares. Neste contexto, sensores virtuais mostram-se uma alternativa viável pela sua capacidade de fornecer informações sobre variáveis de qualidade como a composição a partir de variáveis primárias facilmente mensuráveis, como temperatura e pressão, utilizando modelos matemáticos programados em dispositivos de hardware. Com este objetivo, este trabalho desenvolve um sensor virtual para inferir a composição do etanol em um processo de destilação em batelada na produção de bebidas destiladas de frutos tropicais, contornando a dificuldade na execução dos cortes de destilação, realizados manualmente de forma artesanal. O sensor proposto é baseado em uma rede neural artificial do tipo feedforward multilayer perceptron, que aplica o algoritmo Levenberg-Marquardt na otimização dos seus parâmetros. Para a sua construção foram utilizados dados de destilações binárias produzidas em laboratório, compostas por etanol e água e de concentração inicial próxima da concentração inicial dos mostos fermentados de frutas. O sensor construído apresentou ótimos resultados, com erro absoluto médio (EAM) de 0,0140 a 0,0311 em fração mássica nos experimentos realizados. Para comprovar a sua eficiência na situação de interesse, o sensor foi testado nas destilações dos mostos fermentados de manga, melancia e jabuticaba, também produzidos em laboratório, obtendo ótima performance, com EAM de 0,0160 a 0,0324. Desta maneira, o sensor virtual proposto mostrou-se capaz de inferir a composição do etanol ao longo do tempo de forma confiável, sendo uma alternativa viável para a realização de um monitoramento eficiente.Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPESSão CristóvãoporBebidas destiladasSensores virtuaisRedes neurais artificiaisDistilled beveragesSoft sensorsNeural networksENGENHARIAS::ENGENHARIA QUIMICADesenvolvimento de sensor virtual utilizando redes neurais artificiais na destilação de bebidas fermentadasinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisPós-Graduação em Engenharia QuímicaUniversidade Federal de Sergipereponame:Repositório Institucional da UFSinstname:Universidade Federal de Sergipe (UFS)instacron:UFSinfo:eu-repo/semantics/openAccessLICENSElicense.txtlicense.txttext/plain; charset=utf-81475https://ri.ufs.br/jspui/bitstream/riufs/17051/1/license.txt098cbbf65c2c15e1fb2e49c5d306a44cMD51ORIGINALTIAGO_HORA_ALVES_LIMA.pdfTIAGO_HORA_ALVES_LIMA.pdfapplication/pdf1963606https://ri.ufs.br/jspui/bitstream/riufs/17051/2/TIAGO_HORA_ALVES_LIMA.pdf15e5c7202f7dbe094802db1b0cf151faMD52TEXTTIAGO_HORA_ALVES_LIMA.pdf.txtTIAGO_HORA_ALVES_LIMA.pdf.txtExtracted texttext/plain138237https://ri.ufs.br/jspui/bitstream/riufs/17051/3/TIAGO_HORA_ALVES_LIMA.pdf.txt0b2502444a385e8a31c113a797dacb42MD53THUMBNAILTIAGO_HORA_ALVES_LIMA.pdf.jpgTIAGO_HORA_ALVES_LIMA.pdf.jpgGenerated Thumbnailimage/jpeg1184https://ri.ufs.br/jspui/bitstream/riufs/17051/4/TIAGO_HORA_ALVES_LIMA.pdf.jpg469155cc687f19888e211ca3bd54f398MD54riufs/170512023-02-03 19:59:37.486oai:ufs.br:riufs/17051TElDRU7Dh0EgREUgRElTVFJJQlVJw4fDg08gTsODTy1FWENMVVNJVkEKCkNvbSBhIGFwcmVzZW50YcOnw6NvIGRlc3RhIGxpY2Vuw6dhLCB2b2PDqiAobyBhdXRvcihlcykgb3UgbyB0aXR1bGFyIGRvcyBkaXJlaXRvcyBkZSBhdXRvcikgY29uY2VkZSDDoCBVbml2ZXJzaWRhZGUgRmVkZXJhbCBkZSBTZXJnaXBlIG8gZGlyZWl0byBuw6NvLWV4Y2x1c2l2byBkZSByZXByb2R1emlyIHNldSB0cmFiYWxobyBubyBmb3JtYXRvIGVsZXRyw7RuaWNvLCBpbmNsdWluZG8gb3MgZm9ybWF0b3Mgw6F1ZGlvIG91IHbDrWRlby4KClZvY8OqIGNvbmNvcmRhIHF1ZSBhIFVuaXZlcnNpZGFkZSBGZWRlcmFsIGRlIFNlcmdpcGUgcG9kZSwgc2VtIGFsdGVyYXIgbyBjb250ZcO6ZG8sIHRyYW5zcG9yIHNldSB0cmFiYWxobyBwYXJhIHF1YWxxdWVyIG1laW8gb3UgZm9ybWF0byBwYXJhIGZpbnMgZGUgcHJlc2VydmHDp8Ojby4KClZvY8OqIHRhbWLDqW0gY29uY29yZGEgcXVlIGEgVW5pdmVyc2lkYWRlIEZlZGVyYWwgZGUgU2VyZ2lwZSBwb2RlIG1hbnRlciBtYWlzIGRlIHVtYSBjw7NwaWEgZGUgc2V1IHRyYWJhbGhvIHBhcmEgZmlucyBkZSBzZWd1cmFuw6dhLCBiYWNrLXVwIGUgcHJlc2VydmHDp8Ojby4KClZvY8OqIGRlY2xhcmEgcXVlIHNldSB0cmFiYWxobyDDqSBvcmlnaW5hbCBlIHF1ZSB2b2PDqiB0ZW0gbyBwb2RlciBkZSBjb25jZWRlciBvcyBkaXJlaXRvcyBjb250aWRvcyBuZXN0YSBsaWNlbsOnYS4gVm9jw6ogdGFtYsOpbSBkZWNsYXJhIHF1ZSBvIGRlcMOzc2l0bywgcXVlIHNlamEgZGUgc2V1IGNvbmhlY2ltZW50bywgbsOjbyBpbmZyaW5nZSBkaXJlaXRvcyBhdXRvcmFpcyBkZSBuaW5ndcOpbS4KCkNhc28gbyB0cmFiYWxobyBjb250ZW5oYSBtYXRlcmlhbCBxdWUgdm9jw6ogbsOjbyBwb3NzdWkgYSB0aXR1bGFyaWRhZGUgZG9zIGRpcmVpdG9zIGF1dG9yYWlzLCB2b2PDqiBkZWNsYXJhIHF1ZSBvYnRldmUgYSBwZXJtaXNzw6NvIGlycmVzdHJpdGEgZG8gZGV0ZW50b3IgZG9zIGRpcmVpdG9zIGF1dG9yYWlzIHBhcmEgY29uY2VkZXIgw6AgVW5pdmVyc2lkYWRlIEZlZGVyYWwgZGUgU2VyZ2lwZSBvcyBkaXJlaXRvcyBhcHJlc2VudGFkb3MgbmVzdGEgbGljZW7Dp2EsIGUgcXVlIGVzc2UgbWF0ZXJpYWwgZGUgcHJvcHJpZWRhZGUgZGUgdGVyY2Vpcm9zIGVzdMOhIGNsYXJhbWVudGUgaWRlbnRpZmljYWRvIGUgcmVjb25oZWNpZG8gbm8gdGV4dG8gb3Ugbm8gY29udGXDumRvLgoKQSBVbml2ZXJzaWRhZGUgRmVkZXJhbCBkZSBTZXJnaXBlIHNlIGNvbXByb21ldGUgYSBpZGVudGlmaWNhciBjbGFyYW1lbnRlIG8gc2V1IG5vbWUocykgb3UgbyhzKSBub21lKHMpIGRvKHMpIApkZXRlbnRvcihlcykgZG9zIGRpcmVpdG9zIGF1dG9yYWlzIGRvIHRyYWJhbGhvLCBlIG7Do28gZmFyw6EgcXVhbHF1ZXIgYWx0ZXJhw6fDo28sIGFsw6ltIGRhcXVlbGFzIGNvbmNlZGlkYXMgcG9yIGVzdGEgbGljZW7Dp2EuIAo=Repositório InstitucionalPUBhttps://ri.ufs.br/oai/requestrepositorio@academico.ufs.bropendoar:2023-02-03T22:59:37Repositório Institucional da UFS - Universidade Federal de Sergipe (UFS)false |
dc.title.pt_BR.fl_str_mv |
Desenvolvimento de sensor virtual utilizando redes neurais artificiais na destilação de bebidas fermentadas |
title |
Desenvolvimento de sensor virtual utilizando redes neurais artificiais na destilação de bebidas fermentadas |
spellingShingle |
Desenvolvimento de sensor virtual utilizando redes neurais artificiais na destilação de bebidas fermentadas Lima, Tiago Hora Alves de Bebidas destiladas Sensores virtuais Redes neurais artificiais Distilled beverages Soft sensors Neural networks ENGENHARIAS::ENGENHARIA QUIMICA |
title_short |
Desenvolvimento de sensor virtual utilizando redes neurais artificiais na destilação de bebidas fermentadas |
title_full |
Desenvolvimento de sensor virtual utilizando redes neurais artificiais na destilação de bebidas fermentadas |
title_fullStr |
Desenvolvimento de sensor virtual utilizando redes neurais artificiais na destilação de bebidas fermentadas |
title_full_unstemmed |
Desenvolvimento de sensor virtual utilizando redes neurais artificiais na destilação de bebidas fermentadas |
title_sort |
Desenvolvimento de sensor virtual utilizando redes neurais artificiais na destilação de bebidas fermentadas |
author |
Lima, Tiago Hora Alves de |
author_facet |
Lima, Tiago Hora Alves de |
author_role |
author |
dc.contributor.author.fl_str_mv |
Lima, Tiago Hora Alves de |
dc.contributor.advisor1.fl_str_mv |
Oliveira Junior, Antônio Martins de |
contributor_str_mv |
Oliveira Junior, Antônio Martins de |
dc.subject.por.fl_str_mv |
Bebidas destiladas Sensores virtuais Redes neurais artificiais Distilled beverages Soft sensors Neural networks |
topic |
Bebidas destiladas Sensores virtuais Redes neurais artificiais Distilled beverages Soft sensors Neural networks ENGENHARIAS::ENGENHARIA QUIMICA |
dc.subject.cnpq.fl_str_mv |
ENGENHARIAS::ENGENHARIA QUIMICA |
description |
The need to monitor industrial processes reliably to ensure products quality contrasts with the high cost of available equipments and the difficulty of obtaining information in real time. In relation to Brazilian distilleries producing spirits, this is an even greater challenge, since most are small, often family-owned enterprises. In this context, virtual sensors are a viable alternative for their ability to provide information about quality variables such as composition from easily measurable primary variables such as temperature and pressure using mathematical models programmed into hardware devices. With this objective, this work develops a soft sensor to infer the composition of ethanol in a batch distillation process in the production of distilled beverages of tropical fruits, overcoming the difficulty in the execution of the distillation cuts, made by a craft way. The proposed sensor is based on an artificial neural network of the feedforward multilayer perceptron type, which applies the Levenberg-Marquardt algorithm in the optimization of its parameters. For its construction were used data from binary distillations produced in the laboratory, composed of ethanol and water and with initial concentration close to the initial concentration of fermented fruit must. The built sensor presented excellent results, with mean absolute error (EAM) of 0,0140 to 0,0311 in mass fraction in the experiments performed. In order to prove its efficiency in the situation of interest, the sensor was tested in the fermented must distillations of mango, watermelon and jabuticaba, also produced in the laboratory, obtaining an excellent performance, with EAM of 0.0160 to 0.0324. In this way, the proposed virtual sensor proved capable of inferring the ethanol composition over time in a reliable way, being a viable alternative for the efficient monitoring. |
publishDate |
2019 |
dc.date.issued.fl_str_mv |
2019-04-09 |
dc.date.accessioned.fl_str_mv |
2023-02-03T22:59:37Z |
dc.date.available.fl_str_mv |
2023-02-03T22:59:37Z |
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.citation.fl_str_mv |
LIMA, Tiago Hora Alves de. Desenvolvimento de sensor virtual utilizando redes neurais artificiais na destilação de bebidas fermentadas. 2019. 72 f. Dissertação (Mestrado em Engenharia Química) - Universidade Federal de Sergipe, São Cristóvão, 2019. |
dc.identifier.uri.fl_str_mv |
http://ri.ufs.br/jspui/handle/riufs/17051 |
identifier_str_mv |
LIMA, Tiago Hora Alves de. Desenvolvimento de sensor virtual utilizando redes neurais artificiais na destilação de bebidas fermentadas. 2019. 72 f. Dissertação (Mestrado em Engenharia Química) - Universidade Federal de Sergipe, São Cristóvão, 2019. |
url |
http://ri.ufs.br/jspui/handle/riufs/17051 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.program.fl_str_mv |
Pós-Graduação em Engenharia Química |
dc.publisher.initials.fl_str_mv |
Universidade Federal de Sergipe |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFS instname:Universidade Federal de Sergipe (UFS) instacron:UFS |
instname_str |
Universidade Federal de Sergipe (UFS) |
instacron_str |
UFS |
institution |
UFS |
reponame_str |
Repositório Institucional da UFS |
collection |
Repositório Institucional da UFS |
bitstream.url.fl_str_mv |
https://ri.ufs.br/jspui/bitstream/riufs/17051/1/license.txt https://ri.ufs.br/jspui/bitstream/riufs/17051/2/TIAGO_HORA_ALVES_LIMA.pdf https://ri.ufs.br/jspui/bitstream/riufs/17051/3/TIAGO_HORA_ALVES_LIMA.pdf.txt https://ri.ufs.br/jspui/bitstream/riufs/17051/4/TIAGO_HORA_ALVES_LIMA.pdf.jpg |
bitstream.checksum.fl_str_mv |
098cbbf65c2c15e1fb2e49c5d306a44c 15e5c7202f7dbe094802db1b0cf151fa 0b2502444a385e8a31c113a797dacb42 469155cc687f19888e211ca3bd54f398 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFS - Universidade Federal de Sergipe (UFS) |
repository.mail.fl_str_mv |
repositorio@academico.ufs.br |
_version_ |
1802110662515621888 |