Modelagem matemática e simulação computacional aplicadas ao estudo de processos de co-digestão anaeróbia de glicerol e/ou melaço

Detalhes bibliográficos
Autor(a) principal: Ferreira, Carolina Machado
Data de Publicação: 2022
Tipo de documento: Dissertação
Idioma: por
Título da fonte: Repositório Institucional da UFSCAR
Texto Completo: https://repositorio.ufscar.br/handle/ufscar/17201
Resumo: Policies worldwide are increasingly incentivizing and pressuring countries to use renewable sources of energy. Brazil was a pioneer in the production of bioethanol and is one of the main producers of biodiesel. Due to the expanding production of biodiesel in Brazil, large quantities of crude glycerol are generated as a byproduct, while the high cost of its purification means that it is discarded by small and medium sized producers. Given the environmental impacts of such disposal, as well as the energy potential of glycerol (since it is carbon-rich), an attractive application of crude glycerol is in the generation of biomethane by means of anaerobic co-digestion, involving the decomposition of the organic matter in two or more substrates by bacteria and archaea, in the absence of oxygen. Co-digestion enables balancing of the availabilities of nutrients, so that biogas production is optimized. Like glycerol, sugarcane molasses has widespread availability, as a byproduct of sugar crystallization, and contains nitrogen, potassium, calcium, and other elements at concentrations that enable it to be considered as a complementary substrate for use in co-digestion processes. Computational simulations using artificial neural networks and fuzzy logic offer a way to rapidly predict the production of biogas in different scenarios. Therefore, the objective of this work was to evaluate the potential of these artificial intelligence techniques in the production of biomethane from the anaerobic co-digestion of glycerol and sugarcane molasses. Firstly, experimental data reported in the literature were used, where mixtures had a composition of distillery water in the range from 95 to 100%, and a concentration of glycerol and sugarcane molasses from 0 to 5%. A reactor model was implemented using Scilab, with Monod kinetics involving two substrates and an intermediate (M2SI model), in order to generate a database for subsequent fitting and evaluation of neural and fuzzy models. The neural network package of Matlab was used, with evaluation of the effect of the number of neurons in the networks and the distribution of data used for the training, validation, and testing sets. The Matlab package includes the multilayer perceptron artificial neural network framework and the Levenberg-Marquardt backpropagation algorithm (for training). Fuzzy modeling was applied using the Takagi-Sugeno approach available in the ANFIS package of Matlab. A Gaussian membership function and a hybrid algorithm were used for the training. The biomethane production results simulated by M2SI showed very satisfactory predictions for 8 scenarios, which were used in neural network modeling, firstly employing a “generic” network applicable to all 8 scenarios. A very good fit was obtained (R² > 0.99). The minimum quantity of neurons in the hidden layer was 14, with a small error between the intended output value and the output variable simulated by the neural network. Excellent performance was also observed for specific artificial neural networks (one for each condition). The kinetic parameters of the M2SI model for the 8 different conditions were also mapped using an artificial neural network, as a function of the organic material composition. In this case, due to the relatively low volume of data, test data were not allocated, with 90% and 10% being used for training and validation, respectively. A fit with R² > 0.99 was obtained using 25 neurons. In the case of the fuzzy logic, RMSE of 18.88 mL of methane was obtained with 216 rules, which was a value lower than 0.5% of the order of magnitude of the accumulated methane. It could be concluded from the results that fuzzy logic and artificial neural networks offer excellent ability to predict methane production, as well as to parameterize the M2SI kinetic model (using neural networks).
id SCAR_40bfe5d5744bef056be3b8f0661046bb
oai_identifier_str oai:repositorio.ufscar.br:ufscar/17201
network_acronym_str SCAR
network_name_str Repositório Institucional da UFSCAR
repository_id_str 4322
spelling Ferreira, Carolina MachadoSousa Júnior, Ruy dehttp://lattes.cnpq.br/1983482879541203https://lattes.cnpq.br/7005262002323073f59e746b-a78f-42e4-9279-9fb356819fc22023-01-10T17:51:02Z2023-01-10T17:51:02Z2022-11-29FERREIRA, Carolina Machado. Modelagem matemática e simulação computacional aplicadas ao estudo de processos de co-digestão anaeróbia de glicerol e/ou melaço. 2022. Dissertação (Mestrado em Engenharia Química) – Universidade Federal de São Carlos, São Carlos, 2022. Disponível em: https://repositorio.ufscar.br/handle/ufscar/17201.https://repositorio.ufscar.br/handle/ufscar/17201Policies worldwide are increasingly incentivizing and pressuring countries to use renewable sources of energy. Brazil was a pioneer in the production of bioethanol and is one of the main producers of biodiesel. Due to the expanding production of biodiesel in Brazil, large quantities of crude glycerol are generated as a byproduct, while the high cost of its purification means that it is discarded by small and medium sized producers. Given the environmental impacts of such disposal, as well as the energy potential of glycerol (since it is carbon-rich), an attractive application of crude glycerol is in the generation of biomethane by means of anaerobic co-digestion, involving the decomposition of the organic matter in two or more substrates by bacteria and archaea, in the absence of oxygen. Co-digestion enables balancing of the availabilities of nutrients, so that biogas production is optimized. Like glycerol, sugarcane molasses has widespread availability, as a byproduct of sugar crystallization, and contains nitrogen, potassium, calcium, and other elements at concentrations that enable it to be considered as a complementary substrate for use in co-digestion processes. Computational simulations using artificial neural networks and fuzzy logic offer a way to rapidly predict the production of biogas in different scenarios. Therefore, the objective of this work was to evaluate the potential of these artificial intelligence techniques in the production of biomethane from the anaerobic co-digestion of glycerol and sugarcane molasses. Firstly, experimental data reported in the literature were used, where mixtures had a composition of distillery water in the range from 95 to 100%, and a concentration of glycerol and sugarcane molasses from 0 to 5%. A reactor model was implemented using Scilab, with Monod kinetics involving two substrates and an intermediate (M2SI model), in order to generate a database for subsequent fitting and evaluation of neural and fuzzy models. The neural network package of Matlab was used, with evaluation of the effect of the number of neurons in the networks and the distribution of data used for the training, validation, and testing sets. The Matlab package includes the multilayer perceptron artificial neural network framework and the Levenberg-Marquardt backpropagation algorithm (for training). Fuzzy modeling was applied using the Takagi-Sugeno approach available in the ANFIS package of Matlab. A Gaussian membership function and a hybrid algorithm were used for the training. The biomethane production results simulated by M2SI showed very satisfactory predictions for 8 scenarios, which were used in neural network modeling, firstly employing a “generic” network applicable to all 8 scenarios. A very good fit was obtained (R² > 0.99). The minimum quantity of neurons in the hidden layer was 14, with a small error between the intended output value and the output variable simulated by the neural network. Excellent performance was also observed for specific artificial neural networks (one for each condition). The kinetic parameters of the M2SI model for the 8 different conditions were also mapped using an artificial neural network, as a function of the organic material composition. In this case, due to the relatively low volume of data, test data were not allocated, with 90% and 10% being used for training and validation, respectively. A fit with R² > 0.99 was obtained using 25 neurons. In the case of the fuzzy logic, RMSE of 18.88 mL of methane was obtained with 216 rules, which was a value lower than 0.5% of the order of magnitude of the accumulated methane. It could be concluded from the results that fuzzy logic and artificial neural networks offer excellent ability to predict methane production, as well as to parameterize the M2SI kinetic model (using neural networks).Cada vez mais as políticas mundiais incentivam e pressionam os países a utilizarem fontes de energias renováveis. O Brasil foi pioneiro na produção de bioetanol e está entre um dos grandes produtores de biodiesel. Em consequência da crescente produção de biodiesel no Brasil, uma grande quantidade de glicerol bruto é gerada como subproduto. Contudo, seu custo elevado de purificação faz com que pequenos e médios produtores o descartem. Levando em consideração os impactos ambientais do descarte, bem como o seu potencial energético (rico em carbono), torna-se interessante a aplicação do glicerol bruto na geração de biometano a partir da co-digestão anaeróbia. A co-digestão anaeróbia é a decomposição da matéria orgânica de dois ou mais substratos, na ausência de oxigênio, por bactérias e arqueas. A co-digestão é uma forma de balancear a disponibilidade de nutrientes e otimizar a produção de biogás. Assim como o glicerol, o melaço de cana-de-açúcar possui grande disponibilidade. Ele é um subproduto obtido da cristalização do açúcar e apresenta concentrações de nitrogênio, potássio, cálcio, dentre outros elementos, que o qualificam como um substrato complementar para o processo de co-digestão. Neste contexto, as simulações computacionais utilizando redes neurais artificiais e lógica fuzzy surgem como alternativa para prever a produção de biogás em diferentes cenários de maneira rápida. Assim, o objetivo da pesquisa é avaliar o potencial da inteligência computacional na produção de biometano a partir da co-digestão anaeróbia de glicerol e melaço de cana-de-açúcar utilizando redes neurais artificiais e lógica fuzzy. Primeiramente, foram considerados dados experimentais da literatura com uma composição de água de destilaria variando de 100 a 95% e concentração de glicerol e melaço de cana-de-açúcar de 0 a 5%, tendo-se implementado no Scilab o respectivo modelo de reator com cinética de Monod de dois substratos com um intermediário (M2SI) visando à geração de um banco de dados para posterior ajuste e avaliação de modelos neurais e fuzzy. Foi utilizado o pacote Neural Network do Matlab e avaliado o efeito da quantidade de neurônios das redes e da distribuição dos dados para treinamento, validação e teste. O pacote do Matlab conta com a estrutura de rede neural artificial Multilayer Perceptron e do algoritmo Levenberg-Marquardt – backpropagation (para treinamento). Em seguida, foi aplicada a modelagem fuzzy utilizando a abordagem Takagi-Sugeno do pacote ANFIS do Matlab. Selecionou-se a função de pertinência do tipo gaussiana e um algoritmo híbrido para o treinamento. Os resultados de produção de biometano simulados pelo M2SI mostraram predições muito satisfatórias para 8 cenários, os quais foram utilizados na modelagem neural, inicialmente de uma rede “genérica” (abrangendo todos os 8 diferentes cenários de produção de biometano). Foi observado um ajuste muito bom (R²> 0,99). A quantidade mínima de neurônios na camada escondida com um erro pequeno entre o valor de saída pretendido e a variável de saída simulada pela rede neural foi de 14 neurônios. Além disso, foi também constatada a ótima adesão de rede neurais artificiais específicas (uma para cada condição). Também foram mapeados por rede neural artificial os parâmetros cinéticos do M2SI das 8 diferentes condições, em função da composição do material orgânico. Neste caso específico, como o volume de dados era relativamente baixo, não foi alocado dado em teste, tendo sido distribuídos 90% para treinamento e 10% para validação. Dessa forma, foi alcançado um ajuste com R²>0,99. Para a lógica fuzzy encontrou-se um RMSE de 18,88 mL de metano no cumprimento de 216 regras – valor menor que 0,5% da ordem de grandeza de metano acumulado. Conclui-se, com os resultados preliminares, que a lógica fuzzy e as redes neurais artificiais têm grande capacidade de fornecer uma boa projeção de produção de metano e, adicionalmente, a parametrização para o modelo cinético M2SI (por redes neurais).Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)133915/2020-4porUniversidade Federal de São CarlosCâmpus São CarlosPrograma de Pós-Graduação em Engenharia Química - PPGEQUFSCarAttribution-NonCommercial-NoDerivs 3.0 Brazilhttp://creativecommons.org/licenses/by-nc-nd/3.0/br/info:eu-repo/semantics/openAccessGlicerolMelaço de cana-de-açúcarBiometanoCo-digestão anaeróbiaRede neuralLógica fuzzySimulação computacionalGlycerolSugarcane molassesBiomethaneAnaerobic co-digestionNeural networkFuzzy logicComputational simulationENGENHARIAS::ENGENHARIA QUIMICA::PROCESSOS INDUSTRIAIS DE ENGENHARIA QUIMICAModelagem matemática e simulação computacional aplicadas ao estudo de processos de co-digestão anaeróbia de glicerol e/ou melaçoMathematical modeling and computational simulation applied to the study of glycerol and molasses anaerobic co-digestion processesinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesis600600ab69fa78-14aa-4e78-beb8-e23c9aefadecreponame:Repositório Institucional da UFSCARinstname:Universidade Federal de São Carlos (UFSCAR)instacron:UFSCARCC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8811https://repositorio.ufscar.br/bitstream/ufscar/17201/2/license_rdfe39d27027a6cc9cb039ad269a5db8e34MD52ORIGINALDissertação_vfinal-Aprovada.pdfDissertação_vfinal-Aprovada.pdfDissertação de Mestrado_Carolina Ferreiraapplication/pdf19680426https://repositorio.ufscar.br/bitstream/ufscar/17201/1/Disserta%c3%a7%c3%a3o_vfinal-Aprovada.pdf1591a9d28a1979381cbfc6faa7d0d15dMD51TEXTDissertação_vfinal-Aprovada.pdf.txtDissertação_vfinal-Aprovada.pdf.txtExtracted texttext/plain81https://repositorio.ufscar.br/bitstream/ufscar/17201/3/Disserta%c3%a7%c3%a3o_vfinal-Aprovada.pdf.txte675a542ea4029ee89e770bf102c2d74MD53THUMBNAILDissertação_vfinal-Aprovada.pdf.jpgDissertação_vfinal-Aprovada.pdf.jpgIM Thumbnailimage/jpeg6114https://repositorio.ufscar.br/bitstream/ufscar/17201/4/Disserta%c3%a7%c3%a3o_vfinal-Aprovada.pdf.jpgcd0d54c68ec7b93feed7c857139dc5b2MD54ufscar/172012023-09-18 18:32:22.726oai:repositorio.ufscar.br:ufscar/17201Repositório InstitucionalPUBhttps://repositorio.ufscar.br/oai/requestopendoar:43222023-09-18T18:32:22Repositório Institucional da UFSCAR - Universidade Federal de São Carlos (UFSCAR)false
dc.title.por.fl_str_mv Modelagem matemática e simulação computacional aplicadas ao estudo de processos de co-digestão anaeróbia de glicerol e/ou melaço
dc.title.alternative.eng.fl_str_mv Mathematical modeling and computational simulation applied to the study of glycerol and molasses anaerobic co-digestion processes
title Modelagem matemática e simulação computacional aplicadas ao estudo de processos de co-digestão anaeróbia de glicerol e/ou melaço
spellingShingle Modelagem matemática e simulação computacional aplicadas ao estudo de processos de co-digestão anaeróbia de glicerol e/ou melaço
Ferreira, Carolina Machado
Glicerol
Melaço de cana-de-açúcar
Biometano
Co-digestão anaeróbia
Rede neural
Lógica fuzzy
Simulação computacional
Glycerol
Sugarcane molasses
Biomethane
Anaerobic co-digestion
Neural network
Fuzzy logic
Computational simulation
ENGENHARIAS::ENGENHARIA QUIMICA::PROCESSOS INDUSTRIAIS DE ENGENHARIA QUIMICA
title_short Modelagem matemática e simulação computacional aplicadas ao estudo de processos de co-digestão anaeróbia de glicerol e/ou melaço
title_full Modelagem matemática e simulação computacional aplicadas ao estudo de processos de co-digestão anaeróbia de glicerol e/ou melaço
title_fullStr Modelagem matemática e simulação computacional aplicadas ao estudo de processos de co-digestão anaeróbia de glicerol e/ou melaço
title_full_unstemmed Modelagem matemática e simulação computacional aplicadas ao estudo de processos de co-digestão anaeróbia de glicerol e/ou melaço
title_sort Modelagem matemática e simulação computacional aplicadas ao estudo de processos de co-digestão anaeróbia de glicerol e/ou melaço
author Ferreira, Carolina Machado
author_facet Ferreira, Carolina Machado
author_role author
dc.contributor.authorlattes.por.fl_str_mv https://lattes.cnpq.br/7005262002323073
dc.contributor.author.fl_str_mv Ferreira, Carolina Machado
dc.contributor.advisor1.fl_str_mv Sousa Júnior, Ruy de
dc.contributor.advisor1Lattes.fl_str_mv http://lattes.cnpq.br/1983482879541203
dc.contributor.authorID.fl_str_mv f59e746b-a78f-42e4-9279-9fb356819fc2
contributor_str_mv Sousa Júnior, Ruy de
dc.subject.por.fl_str_mv Glicerol
Melaço de cana-de-açúcar
Biometano
Co-digestão anaeróbia
Rede neural
Lógica fuzzy
Simulação computacional
topic Glicerol
Melaço de cana-de-açúcar
Biometano
Co-digestão anaeróbia
Rede neural
Lógica fuzzy
Simulação computacional
Glycerol
Sugarcane molasses
Biomethane
Anaerobic co-digestion
Neural network
Fuzzy logic
Computational simulation
ENGENHARIAS::ENGENHARIA QUIMICA::PROCESSOS INDUSTRIAIS DE ENGENHARIA QUIMICA
dc.subject.eng.fl_str_mv Glycerol
Sugarcane molasses
Biomethane
Anaerobic co-digestion
Neural network
Fuzzy logic
Computational simulation
dc.subject.cnpq.fl_str_mv ENGENHARIAS::ENGENHARIA QUIMICA::PROCESSOS INDUSTRIAIS DE ENGENHARIA QUIMICA
description Policies worldwide are increasingly incentivizing and pressuring countries to use renewable sources of energy. Brazil was a pioneer in the production of bioethanol and is one of the main producers of biodiesel. Due to the expanding production of biodiesel in Brazil, large quantities of crude glycerol are generated as a byproduct, while the high cost of its purification means that it is discarded by small and medium sized producers. Given the environmental impacts of such disposal, as well as the energy potential of glycerol (since it is carbon-rich), an attractive application of crude glycerol is in the generation of biomethane by means of anaerobic co-digestion, involving the decomposition of the organic matter in two or more substrates by bacteria and archaea, in the absence of oxygen. Co-digestion enables balancing of the availabilities of nutrients, so that biogas production is optimized. Like glycerol, sugarcane molasses has widespread availability, as a byproduct of sugar crystallization, and contains nitrogen, potassium, calcium, and other elements at concentrations that enable it to be considered as a complementary substrate for use in co-digestion processes. Computational simulations using artificial neural networks and fuzzy logic offer a way to rapidly predict the production of biogas in different scenarios. Therefore, the objective of this work was to evaluate the potential of these artificial intelligence techniques in the production of biomethane from the anaerobic co-digestion of glycerol and sugarcane molasses. Firstly, experimental data reported in the literature were used, where mixtures had a composition of distillery water in the range from 95 to 100%, and a concentration of glycerol and sugarcane molasses from 0 to 5%. A reactor model was implemented using Scilab, with Monod kinetics involving two substrates and an intermediate (M2SI model), in order to generate a database for subsequent fitting and evaluation of neural and fuzzy models. The neural network package of Matlab was used, with evaluation of the effect of the number of neurons in the networks and the distribution of data used for the training, validation, and testing sets. The Matlab package includes the multilayer perceptron artificial neural network framework and the Levenberg-Marquardt backpropagation algorithm (for training). Fuzzy modeling was applied using the Takagi-Sugeno approach available in the ANFIS package of Matlab. A Gaussian membership function and a hybrid algorithm were used for the training. The biomethane production results simulated by M2SI showed very satisfactory predictions for 8 scenarios, which were used in neural network modeling, firstly employing a “generic” network applicable to all 8 scenarios. A very good fit was obtained (R² > 0.99). The minimum quantity of neurons in the hidden layer was 14, with a small error between the intended output value and the output variable simulated by the neural network. Excellent performance was also observed for specific artificial neural networks (one for each condition). The kinetic parameters of the M2SI model for the 8 different conditions were also mapped using an artificial neural network, as a function of the organic material composition. In this case, due to the relatively low volume of data, test data were not allocated, with 90% and 10% being used for training and validation, respectively. A fit with R² > 0.99 was obtained using 25 neurons. In the case of the fuzzy logic, RMSE of 18.88 mL of methane was obtained with 216 rules, which was a value lower than 0.5% of the order of magnitude of the accumulated methane. It could be concluded from the results that fuzzy logic and artificial neural networks offer excellent ability to predict methane production, as well as to parameterize the M2SI kinetic model (using neural networks).
publishDate 2022
dc.date.issued.fl_str_mv 2022-11-29
dc.date.accessioned.fl_str_mv 2023-01-10T17:51:02Z
dc.date.available.fl_str_mv 2023-01-10T17:51:02Z
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 FERREIRA, Carolina Machado. Modelagem matemática e simulação computacional aplicadas ao estudo de processos de co-digestão anaeróbia de glicerol e/ou melaço. 2022. Dissertação (Mestrado em Engenharia Química) – Universidade Federal de São Carlos, São Carlos, 2022. Disponível em: https://repositorio.ufscar.br/handle/ufscar/17201.
dc.identifier.uri.fl_str_mv https://repositorio.ufscar.br/handle/ufscar/17201
identifier_str_mv FERREIRA, Carolina Machado. Modelagem matemática e simulação computacional aplicadas ao estudo de processos de co-digestão anaeróbia de glicerol e/ou melaço. 2022. Dissertação (Mestrado em Engenharia Química) – Universidade Federal de São Carlos, São Carlos, 2022. Disponível em: https://repositorio.ufscar.br/handle/ufscar/17201.
url https://repositorio.ufscar.br/handle/ufscar/17201
dc.language.iso.fl_str_mv por
language por
dc.relation.confidence.fl_str_mv 600
600
dc.relation.authority.fl_str_mv ab69fa78-14aa-4e78-beb8-e23c9aefadec
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 São Carlos
Câmpus São Carlos
dc.publisher.program.fl_str_mv Programa de Pós-Graduação em Engenharia Química - PPGEQ
dc.publisher.initials.fl_str_mv UFSCar
publisher.none.fl_str_mv Universidade Federal de São Carlos
Câmpus São Carlos
dc.source.none.fl_str_mv reponame:Repositório Institucional da UFSCAR
instname:Universidade Federal de São Carlos (UFSCAR)
instacron:UFSCAR
instname_str Universidade Federal de São Carlos (UFSCAR)
instacron_str UFSCAR
institution UFSCAR
reponame_str Repositório Institucional da UFSCAR
collection Repositório Institucional da UFSCAR
bitstream.url.fl_str_mv https://repositorio.ufscar.br/bitstream/ufscar/17201/2/license_rdf
https://repositorio.ufscar.br/bitstream/ufscar/17201/1/Disserta%c3%a7%c3%a3o_vfinal-Aprovada.pdf
https://repositorio.ufscar.br/bitstream/ufscar/17201/3/Disserta%c3%a7%c3%a3o_vfinal-Aprovada.pdf.txt
https://repositorio.ufscar.br/bitstream/ufscar/17201/4/Disserta%c3%a7%c3%a3o_vfinal-Aprovada.pdf.jpg
bitstream.checksum.fl_str_mv e39d27027a6cc9cb039ad269a5db8e34
1591a9d28a1979381cbfc6faa7d0d15d
e675a542ea4029ee89e770bf102c2d74
cd0d54c68ec7b93feed7c857139dc5b2
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
repository.name.fl_str_mv Repositório Institucional da UFSCAR - Universidade Federal de São Carlos (UFSCAR)
repository.mail.fl_str_mv
_version_ 1813715657806577664