SISTEMA INTEGRADO DE MONITORAMENTO E CONTROLE DA QUALIDADE DE COMBUSTÍVEL

• Ano de defesa: 2004
• Autor(a) principal: Marques, Delano Brandes
• Orientador(a): LABIDI, Sofiane
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal do Maranhão
• Programa de Pós-Graduação: PROGRAMA DE PÓS-GRADUAÇÃO EM ENGENHARIA DE ELETRICIDADE/CCET
• Departamento: Engenharia
• País: BR
• Palavras-chave em Português: Análise de Combustíveis; Processo KDD; Mineração de Dados; Data Warehouse; Sistema de Informação Geográfica
• Palavras-chave em Inglês: Fuel Analysis; KDD process; Data Warehouse; Data Mining; Geographic Information Systems
• Área do conhecimento CNPq: CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::METODOLOGIA E TECNICAS DA COMPUTACAO::BANCO DE DADOS
• Link de acesso: http://tedebc.ufma.br:8080/jspui/handle/tede/348

This work aims the implantation of an Integrated System that, besides allowing a better, more efficient and more practical monitoring, makes possible the control and optimization of problems related to the oil industry. In order to guarantee fuel s quality and normalization, the development of efficient tools that allow it s monitoring of any point (anywhere) and for any type of fuel is indispensable. Considering the variety of criteria, a decision making should be based on the evaluation of the most varied types of space data and not space data. In this sense, Knowledge Discovery in Databases process is used, where the Data Warehouse and Data Mining steps allied to a Geographic Information System are emphasized. This system presents as objective including several fuel monitoring regions. From different information obtained in the ANP databases, an analysis was carried out and a Data Warehouse model proposed. In the sequel, Data Mining techniques (Principal Component Analysis, Clustering Analysis and Multiple Regression) were applied to the results in order to obtain knowledge (patterns).