Use this link to cite:
http://hdl.handle.net/2183/31447 Control de caudal con un sensor virtual basado en técnicas de deep learning
Loading...
Identifiers
Publication date
Authors
González Herbón, Raúl
Rodríguez Ossorio, José Ramón
González Mateos, Guzmán
Morán, Antonio
Alonso Castro, Serafín
Fuertes Martínez, Juan José
Advisors
Other responsabilities
Journal Title
Bibliographic citation
González Herbón, R., Rodríguez Ossorio, J. R., González Mateos, G., Morán Álvarez, A., Alonso Castro, S., Fuertes Martínez, J. J. (2022) Control de caudal con un sensor virtual basado en técnicas de deep learning. XLIII Jornadas de Automática: libro de actas, pp.368-375. https://doi.org/10.17979/spudc.9788497498418.0368
Type of academic work
Academic degree
Abstract
[Resumen] En el ámbito del control industrial, resulta sumamente interesante el empleo de sensores virtuales en los casos en los que no se puede tener acceso a la variable física a controlar, bien sea porque el sensor real es costoso, no puede ser instalado o se encuentra averiado. En este artículo se propone la implementación de un lazo de control del caudal de una planta piloto industrial, comparando el desempeño de este lazo cuando se
emplea el caudalímetro real y cuando se emplea un sensor virtual de caudal. El sensor virtual utilizado se ha desarrollado empleando una red neuronal recurrente.
[Abstract] In the field of industrial control, the use of virtual sensors has great interest in cases where it is not possible to have access to the physical variable to be controlled, either because the real sensor is expensive, cannot be installed or is broken-down. This paper proposes the implementation of a flow control loop in an industrial pilot plant, comparing the performance of this loop when the real flow meter is used with the performance when a virtual flow sensor is used. The virtual sensor used has been developed using a recurrent neural network.
[Abstract] In the field of industrial control, the use of virtual sensors has great interest in cases where it is not possible to have access to the physical variable to be controlled, either because the real sensor is expensive, cannot be installed or is broken-down. This paper proposes the implementation of a flow control loop in an industrial pilot plant, comparing the performance of this loop when the real flow meter is used with the performance when a virtual flow sensor is used. The virtual sensor used has been developed using a recurrent neural network.
Description
Editor version
Rights
Atribución-NoComercial-CompartirIgual 4.0 Internacional (CC BY-NC-SA 4.0)
https://creativecommons.org/licenses/by-nc-sa/4.0/deed.es


