Técnicas de inteligência computacional para estimação de sinais de oscilação de eixo em hidrogeradores

• Ano de defesa: 2022
• Autor(a) principal: Oliveira, Bruno Miranda Ribeiro de
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de Lavras; Programa de Pós-graduação em Engenharia de Sistemas e Automação; UFLA; brasil; Departamento de Engenharia
• Palavras-chave em Português: Hidrogeradores; Vibrações; Inteligência computacional; Regressão linear; Regressão não linear; Redes neurais; Hydro generator; Vibrations; Computational intelligence; Linear regression; Nonlinear regression; Neural networks; Ciência da Computação
• Link de acesso: http://repositorio.ufla.br/jspui/handle/1/56067

This work presents computational intelligence techniques for hydro generator axis oscillation regression and comparison with methods through statistical analysis. With the continuous increase in demand for electricity in Brazil and the search for energy producers to increase availability, the reduction of "unplanned outages" resulting from failures was proposed. The failure of mechanical components in relation to the bearing of the hydro generator groups, which can be identified by the increase in "axis oscillation" levels in relation to the bearing, is of interest. The oscillation signals can be acquired (obtained and recorded) by the instrumentation installed in the generator unit and stored by the digital system of the plant. Based on standard values, it is possible to verify if the hydro generator unit will continue to operate reliably without the risk of failure and potential accidents. In this work, actual data from a generator unit located in Brazil were applied to compare computational intelligence techniques through simulations performed in the MATLAB environment and compared with each other.