Cargando…

Transfer Learning in Wastewater Treatment Plant Control Design: From Conventional to Long Short-Term Memory-Based Controllers

In the last decade, industrial environments have been experiencing a change in their control processes. It is more frequent that control strategies adopt Artificial Neural Networks (ANNs) to support control operations, or even as the main control structure. Thus, control structures can be directly o...

Descripción completa

Detalles Bibliográficos
Autores principales: Pisa, Ivan, Morell, Antoni, Vilanova, Ramón, Vicario, Jose Lopez
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8473304/
https://www.ncbi.nlm.nih.gov/pubmed/34577522
http://dx.doi.org/10.3390/s21186315
_version_ 1784574958620377088
author Pisa, Ivan
Morell, Antoni
Vilanova, Ramón
Vicario, Jose Lopez
author_facet Pisa, Ivan
Morell, Antoni
Vilanova, Ramón
Vicario, Jose Lopez
author_sort Pisa, Ivan
collection PubMed
description In the last decade, industrial environments have been experiencing a change in their control processes. It is more frequent that control strategies adopt Artificial Neural Networks (ANNs) to support control operations, or even as the main control structure. Thus, control structures can be directly obtained from input and output measurements without requiring a huge knowledge of the processes under control. However, ANNs have to be designed, implemented, and trained, which can become complex and time-demanding processes. This can be alleviated by means of Transfer Learning (TL) methodologies, where the knowledge obtained from a unique ANN is transferred to the remaining nets reducing the ANN design time. From the control viewpoint, the first ANN can be easily obtained and then transferred to the remaining control loops. In this manuscript, the application of TL methodologies to design and implement the control loops of a Wastewater Treatment Plant (WWTP) is analysed. Results show that the adoption of this TL-based methodology allows the development of new control loops without requiring a huge knowledge of the processes under control. Besides, a wide improvement in terms of the control performance with respect to conventional control structures is also obtained. For instance, results have shown that less oscillations in the tracking of desired set-points are produced by achieving improvements in the Integrated Absolute Error and Integrated Square Error which go from 40.17% to 94.29% and from 34.27% to 99.71%, respectively.
format Online
Article
Text
id pubmed-8473304
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-84733042021-09-28 Transfer Learning in Wastewater Treatment Plant Control Design: From Conventional to Long Short-Term Memory-Based Controllers Pisa, Ivan Morell, Antoni Vilanova, Ramón Vicario, Jose Lopez Sensors (Basel) Article In the last decade, industrial environments have been experiencing a change in their control processes. It is more frequent that control strategies adopt Artificial Neural Networks (ANNs) to support control operations, or even as the main control structure. Thus, control structures can be directly obtained from input and output measurements without requiring a huge knowledge of the processes under control. However, ANNs have to be designed, implemented, and trained, which can become complex and time-demanding processes. This can be alleviated by means of Transfer Learning (TL) methodologies, where the knowledge obtained from a unique ANN is transferred to the remaining nets reducing the ANN design time. From the control viewpoint, the first ANN can be easily obtained and then transferred to the remaining control loops. In this manuscript, the application of TL methodologies to design and implement the control loops of a Wastewater Treatment Plant (WWTP) is analysed. Results show that the adoption of this TL-based methodology allows the development of new control loops without requiring a huge knowledge of the processes under control. Besides, a wide improvement in terms of the control performance with respect to conventional control structures is also obtained. For instance, results have shown that less oscillations in the tracking of desired set-points are produced by achieving improvements in the Integrated Absolute Error and Integrated Square Error which go from 40.17% to 94.29% and from 34.27% to 99.71%, respectively. MDPI 2021-09-21 /pmc/articles/PMC8473304/ /pubmed/34577522 http://dx.doi.org/10.3390/s21186315 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Pisa, Ivan
Morell, Antoni
Vilanova, Ramón
Vicario, Jose Lopez
Transfer Learning in Wastewater Treatment Plant Control Design: From Conventional to Long Short-Term Memory-Based Controllers
title Transfer Learning in Wastewater Treatment Plant Control Design: From Conventional to Long Short-Term Memory-Based Controllers
title_full Transfer Learning in Wastewater Treatment Plant Control Design: From Conventional to Long Short-Term Memory-Based Controllers
title_fullStr Transfer Learning in Wastewater Treatment Plant Control Design: From Conventional to Long Short-Term Memory-Based Controllers
title_full_unstemmed Transfer Learning in Wastewater Treatment Plant Control Design: From Conventional to Long Short-Term Memory-Based Controllers
title_short Transfer Learning in Wastewater Treatment Plant Control Design: From Conventional to Long Short-Term Memory-Based Controllers
title_sort transfer learning in wastewater treatment plant control design: from conventional to long short-term memory-based controllers
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8473304/
https://www.ncbi.nlm.nih.gov/pubmed/34577522
http://dx.doi.org/10.3390/s21186315
work_keys_str_mv AT pisaivan transferlearninginwastewatertreatmentplantcontroldesignfromconventionaltolongshorttermmemorybasedcontrollers
AT morellantoni transferlearninginwastewatertreatmentplantcontroldesignfromconventionaltolongshorttermmemorybasedcontrollers
AT vilanovaramon transferlearninginwastewatertreatmentplantcontroldesignfromconventionaltolongshorttermmemorybasedcontrollers
AT vicariojoselopez transferlearninginwastewatertreatmentplantcontroldesignfromconventionaltolongshorttermmemorybasedcontrollers