Técnicas de clasificación supervisadas para la detección de anomalías en el control de procesos industriales

  1. Álvaro Michelena Grandío 1
  2. Francisco Zayas-Gato 1
  3. Esteban Jove Pérez 1
  4. José-Luis Casteleiro-Roca 1
  5. Héctor Quintián Pardo 1
  6. Natalia Prieto Fernández 1
  7. Héctor Alaiz Moretón 2
  8. José Luis Calvo Rolle 1
  1. 1 Universidade da Coruña
    info

    Universidade da Coruña

    La Coruña, España

    ROR https://ror.org/01qckj285

  2. 2 Universidad de León
    info

    Universidad de León

    León, España

    ROR https://ror.org/02tzt0b78

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

Publisher: Servizo de Publicacións ; Universidade da Coruña

Year of publication: 2022

Pages: 224-232

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

Type: Conference paper

DIALNET GOOGLE SCHOLAR lock_openRUC editor

Abstract

Nowadays, detecting anomalies in industrial processes is key to optimizing them and generating greater efficiency in the production process, bringing more significant benefits to companies. Therefore, in this paper, five supervised classification techniques are implemented to detect anomalies in industrial systems. These techniques have been trained and validated using a dataset that included labeled normal and anomalous operation data from a liquid level control plant. Finally, the results obtained were analyzed and compared to obtain the model with the best performance.

Data source: Dialnet