Uso de espectroscopia no infravermelho médio, calibração multivariada e seleção de variáveis na quantificação de adulterantes em biodieseis e suas misturas com diesel

• Ano de defesa: 2014
• Autor(a) principal: Souza, Letícia Maria de
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de Uberlândia; BR; Programa de Pós-graduação em Química; Ciências Exatas e da Terra; UFU
• Palavras-chave em Português: Biodiesel; Diesel S-10; MIR; PLS; Seleção de variáveis; Validação multivariada.; Espectroscopia de infravermelho; Calibração; Variables selection; Multivariate validation; CNPQ::CIENCIAS EXATAS E DA TERRA::QUIMICA
• Link de acesso: https://repositorio.ufu.br/handle/123456789/17404; https://doi.org/10.14393/ufu.di.2014.45

In this work, the technique of infrared spectroscopy coupled with Eastern methods of Multivariate Calibration Partial Least Squares (PLS) and Partial Least Squares Interval (iPLS) was applied in order to develop methodology capable of quantifying adulterations oil and alcohols in biodiesels Soy and residual oil and its blends with diesel , and to quantify adulterations residual oil lubricant automotive (RAL) in commercial samples of S-10 diesel at filling stations distributed in Brazil by Petrobras S.A. Most multivariate calibration models with variable selection generated by iPLS presented information gain, decrease in the number of latent variables and lower error values when compared to global PLS models. All models constructed showed values of acceptable errors with Medium Error below 4.5%, while the maximum accepted value, determined by current standards is 10%. Thus, the proposed methodologies can be applied in quality control of these biodiesels and their blends with diesel as it were analytically validated by calculating Figures of Merit.