Uso de redes neurais para a previsibilidade de parâmetros de perfuração de poços de petróleo

• Ano de defesa: 2019
• Autor(a) principal: Pixinine, Thaísa Loureiro
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal do Rio de Janeiro; Brasil; Instituto Alberto Luiz Coimbra de Pós-Graduação e Pesquisa de Engenharia; Programa de Pós-Graduação em Engenharia Mecânica; UFRJ
• Palavras-chave em Português: Redes neurais; Previsibilidade; Parâmetros de perfuração; CNPQ::ENGENHARIAS::ENGENHARIA MECANICA
• Link de acesso: http://hdl.handle.net/11422/13770

This work develops the use of intelligent systems with the objective of achieving the minimum financial cost per meter drilled in the shortest time, through parameter predictions, this selection is currently performed through the analysis of similar wells already made and in the experience of the engineer of responsible drilling, there are few technical devices for this forecast. The use of analytical methods is usually an arduous task due to the complexity of the problem. This dissertation will present a method of transcribing tacit knowledge for computational logic through neural networks in order to predict in a more assertive way one of the main drilling parameters, which in this case is the drilling rate of drills.