Metodologia Fuzzy aplicada ao triângulo de Duval para o diagnóstico de transformadores de potência por meio de análise de gases dissolvidos

• Ano de defesa: 2017
• Autor(a) principal: Veloso, Diogo Pereira
• Orientador(a): Brito, Leonardo da Cunha
• Banca de defesa: Brito, Leonardo da Cunha , Ribeiro, Cacilda de Jesus, Rocha, Adson Silva
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de Goiás
• Programa de Pós-Graduação: Programa de Pós-graduação em Engenharia Elétrica e da Computação (EMC)
• Departamento: Escola de Engenharia Elétrica, Mecânica e de Computação - EMC (RG)
• País: Brasil
• Palavras-chave em Português: Lógica Fuzzy; Transformadores de potência; Triângulo de Duval; Análise de gases
• Palavras-chave em Inglês: Fuzzy logic; Power transformers; Duval triangle; Gas analysis
• Área do conhecimento CNPq: CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO
• Link de acesso: http://repositorio.bc.ufg.br/tede/handle/tede/7122

Power transformers are essential equipment in eletric systems. Considered as highly expensive equipment it requires greater attention regarding the occurrence of failures. A failure on equipment can cause serious trouble to the concessionaire responsible for the generation, transmission and distribution of energy. In the present scenario, where legislation has increased the severity with which oversees these failures and demanding a higher efficiency of the same, it is necessary to create appropriate policies to investigas possible equipment failure. These failures can be caused by several factors, among them, the gases dissolved in the oil due to its degeneration. One of the most used techniques for the diagnosis of power transformers from these dissolved gases is the Duval Triangle, a method that has a precision and considerably high reliability. However, for proper planning of maintenance, avoiding a possible sudden withdrawal and supply cut, it is necessary to provide further information, including a quantitative analysis of the causes of failure and a history of the evolution of the operating status of the machine. To this end it is proposed to use a fuzzy logic by the method of Duval to provide an analysis of the transitions between the diagnostic originally presented to enable monitor the level of relevance of each possible cause for the diagnosis equipment allowing perform scheduled and preventive maintenance. The proposed methodology was validated using real data equipment in operation in the brazilian electric system.