@MastersThesis{Donato:2018:MaLeSy,
               author = "Donato, Thiago Henrique Rizzi",
                title = "Machine learning systems applied in satellite lithium-ion battery 
                         set impedance estimation",
               school = "Instituto Nacional de Pesquisas Espaciais (INPE)",
                 year = "2018",
              address = "S{\~a}o Jos{\'e} dos Campos",
                month = "2018-04-02",
             keywords = "lithion-ion battery, state of charge, gradient tree boosting, 
                         multi layer perceptron, bateria l{\'{\i}}tio-{\'{\i}}on, 
                         estado de carga,.",
             abstract = "In this work, the internal impedance of the lithium-ion battery 
                         pack, an essential measure of the degradation level of the 
                         batteries, is estimated employing ensembles of machine learning 
                         models. In this study, we take the supervised learning techniques 
                         Multi-Layer Perceptron bagging neural network and gradient tree 
                         boosting into account. Characteristics of the electric power 
                         system, in which the battery pack is inserted, are extracted and 
                         used in the modeling and training phases. During this process, the 
                         architecture of the ensembles and the configuration of their base 
                         learners are tuned through validation iterations. Finally, with 
                         the application of statistical testing and similarity analysis 
                         techniques, the best ensembles of models are examined and compared 
                         to other methods found in the literature. Results indicate that 
                         our approach is a suitable manner to estimate the internal 
                         impedance of batteries. RESUMO: Neste trabalho, a imped{\^a}ncia 
                         interna de um conjunto de baterias l{\'{\i}}tio-{\'{\i}}on 
                         (uma importante medida do n{\'{\i}}vel de 
                         degrada{\c{c}}{\~a}o) {\'e} estimada por meio de conjuntos de 
                         modelos de aprendizado supervisionado tais como: rede neural tipo 
                         MLP (Multi- Layer Perceptron) e Gradient Tree Boosting. Para isto, 
                         caracter{\'{\i}}sticas do sistema de alimenta{\c{c}}{\~a}o 
                         el{\'e}trica, em que o conjunto de baterias est{\'a} inserido, 
                         s{\~a}o extra{\'{\i}}das e utilizadas na constru{\c{c}}{\~a}o 
                         de conjuntos de modelos supervisionados (MLP e xgBoost). Ao longo 
                         deste processo, a arquitetura de tais conjuntos de modelos e suas 
                         respectivas configura{\c{c}}{\~o}es s{\~a}o ajustados por meio 
                         de valida{\c{c}}{\~o}es. Finalmente, com a aplica{\c{c}}{\~a}o 
                         de t{\'e}cnicas de teste e verifica{\c{c}}{\~a}o 
                         estat{\'{\i}}stica, as acur{\'a}cias dos modelos s{\~a}o 
                         calculadas e testes comparativos s{\~a}o conduzidos. Os 
                         resultados obtidos mostram que a abordagem proposta {\'e} 
                         adequada para o problema de estimativa da impend{\^a}ncia de 
                         baterias.",
            committee = "Santos, Rafael Duarte Coelho dos (presidente) and Quiles, Marcos 
                         Gon{\c{c}}alves (orientador) and Rosa, Reinaldo Roberto and 
                         Shiguemori, Elcio Hideiti and Vianna, Wlamir Olivares Loesch and 
                         Basgalupp, Marcio Porto",
         englishtitle = "Estimativa da imped{\^a}ncia de conjuntos de baterias de 
                         l{\'{\i}}tio-{\'{\i}}on por meio de aprendizado de 
                         m{\'a}quina",
             language = "en",
                pages = "85",
                  ibi = "8JMKD3MGP3W34R/3R2BN4B",
                  url = "http://urlib.net/ibi/8JMKD3MGP3W34R/3R2BN4B",
           targetfile = "publicacao.pdf",
        urlaccessdate = "06 maio 2024"
}