Automação e modelagem de um ciclone secador de partículas: inteligência computacional

• Ano de defesa: 2017
• Autor(a) principal: Fonseca, Bruno Elyezer
• 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: Modelagem de sistemas; Identificação de sistemas; Inteligência computacional; Ciclone secador; System modeling; Identification of systems; Computational intelligence; Cyclone dryer; Engenharia de Software
• Link de acesso: http://repositorio.ufla.br/jspui/handle/1/28540

Beholding the world demand for new energy sources and better energy improviment, modeling and controlling the variables of a process is necessary as engeneering design. This is due to the fact that in predicting the dynamic behavior of the variables of modeled processes, these system can be better understood and controlled. This work performs the modeling of the temperature inside a cyclone particle dryer by means of white, gray and black-box models. The process input variables are the number of resistors driven and the frequency of the inverter that controls the air flow. Eighteen step experiments were carried out to model the heating and flow of the cyclone and then extracted second - order models to obtain the static behavior of the system and subsequent modeling in a white-box. Four PRBS-type signals were applied to the inputs to obtain the ARX, ARMAX, ARX-Fuzzy Neuro and White Box models. The results demonstrated good fit of the models in all cases averaging R 2 greater than 85% and mean square error of less than 30 ◦ C. The ARX-Neuro Fuzzy model was verified through its surface and the results obtained through the White Box model. The proposed instrumentation also demonstrated its efficiency for obtaining data and temperature control.