Next Article in Journal
System Implementation Trade-Offs for Low-Speed Rotational Variable Reluctance Energy Harvesters
Next Article in Special Issue
A Wireless Sensor Network Deployment for Soil Moisture Monitoring in Precision Agriculture
Previous Article in Journal
The State Space Subdivision Filter for Estimation on SE(2)
Article

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

1
Wireless Information Networking (WIN) Group, Escola d’Enginyeria, Universitat Autònoma de Barcelona, 08193 Bellaterra, Spain
2
Advanced Systems for Automation and Control (ASAC) Group, Escola d’Enginyeria, Universitat Autònoma de Barcelona, 08193 Bellaterra, Spain
*
Author to whom correspondence should be addressed.
Academic Editors: Miquel À. Cugueró-Escofet and Vicenç Puig
Received: 13 July 2021 / Revised: 9 September 2021 / Accepted: 18 September 2021 / Published: 21 September 2021
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. View Full-Text
Keywords: control design; industrial control; transfer learning; WWTP control design; industrial control; transfer learning; WWTP
Show Figures

Figure 1

MDPI and ACS Style

Pisa, I.; Morell, A.; Vilanova, R.; Vicario, J.L. Transfer Learning in Wastewater Treatment Plant Control Design: From Conventional to Long Short-Term Memory-Based Controllers. Sensors 2021, 21, 6315. https://0-doi-org.brum.beds.ac.uk/10.3390/s21186315

AMA Style

Pisa I, Morell A, Vilanova R, Vicario JL. Transfer Learning in Wastewater Treatment Plant Control Design: From Conventional to Long Short-Term Memory-Based Controllers. Sensors. 2021; 21(18):6315. https://0-doi-org.brum.beds.ac.uk/10.3390/s21186315

Chicago/Turabian Style

Pisa, Ivan, Antoni Morell, Ramón Vilanova, and Jose L. Vicario. 2021. "Transfer Learning in Wastewater Treatment Plant Control Design: From Conventional to Long Short-Term Memory-Based Controllers" Sensors 21, no. 18: 6315. https://0-doi-org.brum.beds.ac.uk/10.3390/s21186315

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop