Primeros resultados de la integración de modelos neuronales MIMO en la estrategia iMO-NMPC

  1. Alonso, Aimar 1
  2. Zabaljauregi, Asier 1
  3. Irigoyen, Eloy 1
  4. Larrea, Mikel 1
  1. 1 Universidad del País Vasco/Euskal Herriko Unibertsitatea
    info

    Universidad del País Vasco/Euskal Herriko Unibertsitatea

    Lejona, España

    ROR https://ror.org/000xsnr85

Libro:
XLIII Jornadas de Automática: libro de actas: 7, 8 y 9 de septiembre de 2022, Logroño (La Rioja)
  1. Carlos Balaguer Bernaldo de Quirós (coord.)
  2. José Manuel Andújar Márquez (coord.)
  3. Ramon Costa Castelló (coord.)
  4. Carlos Ocampo Martínez (coord.)
  5. Jesús Fernández Lozano (coord.)
  6. Matilde Santos Peñas (coord.)
  7. José Enrique Simó Ten (coord.)
  8. Montserrat Gil Martínez (coord.)
  9. Jose Luis Calvo Rolle (coord.)
  10. Raúl Marín Prades (coord.)
  11. Eduardo Rocón de Lima (coord.)
  12. Elisabet Estévez Estévez (coord.)
  13. Pedro Jesús Cabrera Santana (coord.)
  14. David Muñoz de la Peña Sequedo (coord.)
  15. José Luis Guzmán Sánchez (coord.)
  16. José Luis Pitarch Pérez (coord.)
  17. Oscar Reinoso García (coord.)
  18. Oscar Déniz Suárez (coord.)
  19. Emilio Jiménez Macías (coord.)
  20. Vanesa Loureiro Vázquez (coord.)

Editorial: Servizo de Publicacións ; Universidade da Coruña

ISBN: 978-84-9749-841-8

Año de publicación: 2022

Páginas: 179-185

Congreso: Jornadas de Automática (43. 2022. Logroño)

Tipo: Aportación congreso

DIALNET GOOGLE SCHOLAR lock_openRUC editor

Resumen

This work presents a preliminary study where the efficiency of artificial neural networks of NARX (Nonlinear Autoregressive eXogenous) topology in reproducing the behavior of systems with complex dynamics and their subsequent use in intelligent control structures will be analyzed and studied. Specifically, the behavior of these NARX networks will be evaluated, not only in the estimation of the outputs of the systems to a sample in the future, but also their behavior will be analyzed up to a certain prediction horizon. In particular, due to the dynamic characteristics of the nonlinear systems studied, this study will be carried out for a horizon of 10 samples in a close-loop configuration. The objective of this study is to analyze whether there are divergences in the outputs estimated by the NARX network as its calculation depends on the previous values estimated by the network itself. These NARX structures will be configured to reproduce both monovariable and multivariable systems. Especially, this study will be extended to the case of nonlinear predictive control based on models, iMO-NMPC, which constitutes a line of work within the intelligent control research group (GICI) of the UPV/EHU.

Fuente de los datos: Dialnet