A neural network based real time controller tuned by genetic algorithms, with application to a Lab-Scale distillation column under Labview

• Autores: Javier Fernández de Cañete y Rodríguez, Pablo del Saz Orozco, Salvador Gonzalez Perez, Inmaculada García Moral
• Localización: XXX Jornadas de Automática: Palacio de Congresos Conde Ansúrez, 2-4 de septiembre 2009, 2009, ISBN 978-84-692-2387-1, pág. 45
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • Neural networks have become a popular methodology for identification and control of nonlinear systems. Some software tools have become available for development of neural based control schemes. In this paper we provide a MATLABSIMULINK based toolset for process identification and control of nonlinear systems based on artificial neural networks (ANN). Genetic algorithms are used to automatically choice of the optimum control law based on the neural network model of the plant. This tool has been applied to nonlinear lab-scale distillation column DELTALAB DC-SP monitored under LabVIEW, with up to four control loops. The proposed real time control scheme offers high speed of response for changes in set points and null stationary error for dual composition control and show robustness in presence of externally imposed disturbances.