Controlador neural aplicado a um sistema posicionador acionado por motores de indução trifásicos

• Ano de defesa: 2011
• Autor(a) principal: Nóbrega Sobrinho, Carlos Alberto
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal da Paraí­ba; BR; Engenharia Mecânica; Programa de Pós-Graduação em Engenharia Mecânica; UFPB
• Palavras-chave em Português: Redes neurais; Controle de posição; Mesa de coordenadas; Neural network; Position control; X-Y table; ENGENHARIAS::ENGENHARIA MECANICA
• Link de acesso: https://repositorio.ufpb.br/jspui/handle/tede/5413

This work presents the design of neural controllers for a X-Y table with two degrees of freedom. Both bases of the table moves horizontally, powered by tree-phases induction motors operated by frequency inverters. For detection position of bases, optical encoders were engaged to the axes of the engines to be obtained the angular displacement. A data acquisition board made the interface between a 2.4 GHz Core2Duo computer and the system. This board catches signals from the encoders and provides control signals to the frequency inverters. Neural controllers implemented in LabVIEW® software, determinate the control variables to power the engines. Step, sine and cosine reference were used to evaluate the system performance, in position control and following trajectory. Experimental results are presented.