| spelling |
Mariana Ramos Almeidahttp://lattes.cnpq.br/6690913086860156Vânya Márcia Duarte PasaPaulo Roberto FilgueirasBruno Gonçalves Botelhohttps://lattes.cnpq.br/4158983882437581Vinicius Pires Gonçalves2023-03-06T18:49:11Z2023-03-06T18:49:11Z2022-12-20http://hdl.handle.net/1843/50680Combustíveis derivados de petróleo são a principal fonte de energia mundial, entretanto, com a crescente preocupação ambiental global, torna-se necessário o uso de novas fontes de combustíveis, mais baratas e ambientalmente corretas. Dentre estas fontes, destaca-se o biodiesel, um biocombustível que vem sendo misturado ao diesel mineral. Um dos maiores problemas do uso de biodiesel é a formação de sólidos provenientes da sua oxidação, que é cada vez mais comum à medida que o teor de biodiesel aumenta na mistura. Atualmente, existem métodos padronizados de análise de combustíveis, tais métodos são, no entanto, dispendiosos. Assim, urge o desenvolvimento de novas metodologias de análise que sejam mais simples, robustas, portáteis, rápidas e com menor custo, permitindo um monitoramento da cadeia produtiva. Neste contexto, o objetivo do trabalho foi desenvolver modelos de classificação para caracterizar o biodiesel puro em duas categorias: conforme e não conforme, em relação à estabilidade oxidativa, empregando técnicas espectroscópicas (infravermelho e Raman). As amostras foram analisadas por espectroscopia no infravermelho médio com refletância total atenuada (ATR-FTIR), espectroscopia no infravermelho próximo (NIR) com um equipamento portátil e espectroscopia Raman. Dois tipos de modelos foram construídos e avaliados, um modelo linear empregando a análise discriminante linear (LDA) e um modelo não linear, usando o método Floresta aleatória. Para corrigir o desbalanceamento de classes foi utilizada uma estratégia de reamostragem empregando o método Adasyn. O desempenho dos modelos foi avaliado pela matriz de confusão e os parâmetros eficiência e coeficiente de correlação de Matthews foram calculados. Os modelos construídos foram capazes de classificar o biodiesel em conforme e não conforme, sendo o coeficiente de correlação de Matthews superior a 0,8 para todos os modelos. A técnica ATR-FTIR foi a mais promissora para modelos lineares e a espectroscopia Raman para métodos não lineares, ambos com coeficiente de correlação de Matthews de 0,97. Por fim, a utilização de técnicas espectroscópicas associadas à métodos de aprendizados de máquina para a classificação de biodiesel, segundo as normas da ANP, para a estabilidade oxidativa é promissora, permitindo a inspeção de modo direto das amostras de biodiesel B100, sem nenhum preparo, de forma rápida e com detecção in loco com o uso de equipamentos portáteis, disponíveis comercialmente para as três técnicas empregadas neste trabalho.Petroleum-derived fuels are the primary source of energy worldwide, nevertheless, the growing environmental awareness makes it necessary to establish new renewable sources of fuel, cheaper to produce and environmentally friendly. Biodiesel gains emphasis among these sources, as it has been blended with mineral diesel. One of the biggest problems in using of biodiesel is the formation of solids from its oxidation, which is increasingly common as the biodiesel content increases in the blend. Currently, there are standardized methods for fuel analysis, however, such methods are expensive. Thus, it is urgently necessary to develop new analysis methodologies that are simpler, more robust, portable, faster, and less costly, allowing for monitoring of the production chain. In this context, the objective of the work was to develop classification models to characterize pure biodiesel in two categories: compliant and non-compliant, regarding oxidative stability, employing spectroscopic techniques (infrared and Raman). Samples were analyzed by attenuated total reflectance mid-infrared spectroscopy (ATR-FTIR), near-infrared spectroscopy (NIR) with portable equipment, and Raman spectroscopy. Two types of models were built and evaluated, a linear model employing linear discriminant analysis (LDA) and a non-linear model using the Random Forest method. In addition, a resampling strategy employing the Adasyn method was used to correct for class unbalance. The performance of the models was evaluated by the confusion matrix and the parameters efficiency and Matthews correlation coefficient were calculated. The models here constructed were able to classify biodiesel into compliant and non-compliant, and the Matthews correlation coefficient was greater than 0.8 for all models. The ATR-FTIR technique was the most promising for linear models and Raman spectroscopy for non-linear methods, both with Matthews correlation coefficient of 0.97. Finally, the use of spectroscopic techniques associated with machine learning methods for the classification of biodiesel, according to ANP standards, for oxidative stability is promising, allowing the inspection of B100 biodiesel samples directly, without any preparation, quickly and with on-site detection using portable equipment, commercially available for the three techniques employed in this work.Outra AgênciaporUniversidade Federal de Minas GeraisPrograma de Pós-Graduação em QuímicaUFMGBrasilICX - DEPARTAMENTO DE QUÍMICAhttp://creativecommons.org/licenses/by-nc-sa/3.0/pt/info:eu-repo/semantics/openAccessQuímica analíticaBiocombustíveisBiodieselOxidaçãoRaman, Espectroscopia deEspectroscopia de infravermelhoQuimiometriaBiocombustívelQuimiometriaRandom ForestLDAReamostragemMonitoramento da estabilidade oxidativa de biodiesel empregando espectroscopia vibracional associada a ferramentas quimiométricasMonitoring the oxidative stability of biodiesel using vibrational spectroscopy associated with chemometric toolsinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisreponame:Repositório Institucional da UFMGinstname:Universidade Federal de Minas Gerais (UFMG)instacron:UFMGORIGINALDissertação Vinicius_versão final_certo.pdfDissertação Vinicius_versão final_certo.pdfapplication/pdf3233191https://repositorio.ufmg.br/bitstream/1843/50680/1/Disserta%c3%a7%c3%a3o%20Vinicius_vers%c3%a3o%20final_certo.pdfc4e25cf4a72b9df0ffda8338995d7f2aMD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-81037https://repositorio.ufmg.br/bitstream/1843/50680/2/license_rdfd434b2e45b27c6ef831461f4412a9d4eMD52LICENSElicense.txtlicense.txttext/plain; charset=utf-82118https://repositorio.ufmg.br/bitstream/1843/50680/3/license.txtcda590c95a0b51b4d15f60c9642ca272MD531843/506802023-03-06 15:49:12.146oai:repositorio.ufmg.br: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ório InstitucionalPUBhttps://repositorio.ufmg.br/oaiopendoar:2023-03-06T18:49:12Repositório Institucional da UFMG - Universidade Federal de Minas Gerais (UFMG)false
|