Edgar Rubión
Research Subjects
Edgar Rubión has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
Carlos Rebate
INDRA
3 shared publications- Gabriel Villarrubia González
Expert Systems and Applications Laboratory, Faculty of Science, University of Salamanca, 37008 Salamanca, Spain
3 shared publications - Javier Bajo
Universidad Politécnica de Madrid
3 shared publications - Juan Manuel Corchado
BISITE Research Group, University of Salamanca, Salamanca, Spain
3 shared publications Alejandro Sánchez
Universidad Pontificia de Salamanca
2 shared publicationsAlicia Fernández
INDRA
2 shared publications
Latest Publications
- Open Access
- 1 October 2026
- Published by IOS Press
- p. 12-15
Data-Driven Model Predictive Control of Seawater Reverse Osmosis Using LSTM
Seawater reverse osmosis desalination (SWRO) is a widely used technology for addressing increasing water scarcity. Despite its advantages, the inherent nonlinear dynamics of the process, combined with varying inlet water characteristics, make reliable and efficient operation difficult to achieve with conventional control strategies. This study presents a data-driven model predictive control (MPC) framework, where system dynamics are identified using a one-step-ahead long short-term memory (LSTM) model. The identified model is embedded within an MPC formulation implemented using do-MPC and CasADi, enabling real-time optimal control with explicit handling of operational constraints. The primary objective of the control system is to achieve precise setpoint tracking of permeate flow and permeate salinity under varying operating conditions. Simulation results confirm that the proposed LSTM-MPC achieves accurate tracking performance for both controlled variables.
- 1 October 2026
- Published by IOS Press
- p. 12-15
Open AccessData-Driven Model Predictive Control of Seawater Reverse Osmosis Using LSTM
Seawater reverse osmosis desalination (SWRO) is a widely used technology for addressing increasing water scarcity. Despite its advantages, the inherent nonlinear dynamics of the process, combined with varying inlet water characteristics, make reliable and efficient operation difficult to achieve with conventional control strategies. This study presents a data-driven model predictive control (MPC) framework, where system dynamics are identified using a one-step-ahead long short-term memory (LSTM) model. The identified model is embedded within an MPC formulation implemented using do-MPC and CasADi, enabling real-time optimal control with explicit handling of operational constraints. The primary objective of the control system is to achieve precise setpoint tracking of permeate flow and permeate salinity under varying operating conditions. Simulation results confirm that the proposed LSTM-MPC achieves accurate tracking performance for both controlled variables.
- Open Access
- 1 April 2024
- Published by IWA Publishing in Journal of Hydroinformatics
- Vol. 26 (4) , 727-743
Sewer sediment deposition prediction using a two-stage machine learning solution
Sediment accumulation in the sewer is a source of cascading problems if left unattended and untreated, causing pipe failures, blockages, flooding, or odour problems. Good maintenance scheduling reduces dangerous incidents, but it also has financial and human costs. In this paper, we propose a predictive model to support the management of maintenance routines and reduce cost expenditure. The solution is based on an architecture composed of an autoencoder and a feedforward neural network that classifies the future sediment deposition. The autoencoder serves as a feature reduction component that receives the physical properties of a sewer section and reduces them into a smaller number of variables, which compress the most important information, reducing data uncertainty. Afterwards, the feedforward neural network receives this compressed information together with rain and maintenance data, using all of them to classify the sediment deposition in four thresholds: more than 5, 10, 15, and 20% sediment deposition. We use the architecture to train four different classification models, with the best score from the 5% threshold, being 82% accuracy, 70% precision, 76% specificity, and 88% sensitivity. By combining the classifications obtained with the four models, the solution delivers a final indicator that categorizes the deposited sediment into clearly defined ranges.
- 1 April 2024
- Published by IWA Publishing in Journal of Hydroinformatics
- Vol. 26 (4) , 727-743
Open AccessSewer sediment deposition prediction using a two-stage machine learning solution
Sediment accumulation in the sewer is a source of cascading problems if left unattended and untreated, causing pipe failures, blockages, flooding, or odour problems. Good maintenance scheduling reduces dangerous incidents, but it also has financial and human costs. In this paper, we propose a predictive model to support the management of maintenance routines and reduce cost expenditure. The solution is based on an architecture composed of an autoencoder and a feedforward neural network that classifies the future sediment deposition. The autoencoder serves as a feature reduction component that receives the physical properties of a sewer section and reduces them into a smaller number of variables, which compress the most important information, reducing data uncertainty. Afterwards, the feedforward neural network receives this compressed information together with rain and maintenance data, using all of them to classify the sediment deposition in four thresholds: more than 5, 10, 15, and 20% sediment deposition. We use the architecture to train four different classification models, with the best score from the 5% threshold, being 82% accuracy, 70% precision, 76% specificity, and 88% sensitivity. By combining the classifications obtained with the four models, the solution delivers a final indicator that categorizes the deposited sediment into clearly defined ranges.
- Open Access
- 28 October 2022
- Published by Taylor & Francis in Urban Water Journal
- Vol. 20 (1) , 1-14
Machine learning solutions in sewer systems: a bibliometric analysis
The use of machine learning solutions has been rising recently, and the water domain is reaping several benefits from its application. However, there is still room in the literature regarding machine learning applied to sewer systems. In this article, we study applied solutions to the predictive problem of four factors in the sewer: pipe defects, sedimentation, and failure and blockage events. Even with the number of publications available to solve each problem, there is still a need for improvement. This article aims to identify existing literature gaps through a bibliometric analysis based on data extracted from Scopus and Web of Science. Results show an increasing trend in published papers studying the domain and identify different knowledge gaps within the literature related to the correct use of data, the need for models capable of generalization, and the identification of novel techniques to be studied in the future.
- 28 October 2022
- Published by Taylor & Francis in Urban Water Journal
- Vol. 20 (1) , 1-14
Open AccessMachine learning solutions in sewer systems: a bibliometric analysis
The use of machine learning solutions has been rising recently, and the water domain is reaping several benefits from its application. However, there is still room in the literature regarding machine learning applied to sewer systems. In this article, we study applied solutions to the predictive problem of four factors in the sewer: pipe defects, sedimentation, and failure and blockage events. Even with the number of publications available to solve each problem, there is still a need for improvement. This article aims to identify existing literature gaps through a bibliometric analysis based on data extracted from Scopus and Web of Science. Results show an increasing trend in published papers studying the domain and identify different knowledge gaps within the literature related to the correct use of data, the need for models capable of generalization, and the identification of novel techniques to be studied in the future.
- Open Access
- 1 January 2014
- Published by Elsevier in Procedia Engineering
- Vol. 89, 1097-1104
Towards an Enhanced Knowledge-based Decision Support System (DSS) for Integrated Water Resource Management (IWRM)
- 1 January 2014
- Published by Elsevier in Procedia Engineering
- Vol. 89, 1097-1104
Open AccessTowards an Enhanced Knowledge-based Decision Support System (DSS) for Integrated Water Resource Management (IWRM)
- Open Access
- 1 January 2012
- Published by Springer Nature
- p. 51-58
Proximity Detection Prototype Adapted to a Work Environment
- 1 January 2012
- Published by Springer Nature
- p. 51-58
Open AccessProximity Detection Prototype Adapted to a Work Environment
- Open Access
- 1 January 2012
- Published by Springer Nature
- p. 133-140
Menu Navigation in Mobile Devices Using the Accelerometer
- 1 January 2012
- Published by Springer Nature
- p. 133-140
Open AccessMenu Navigation in Mobile Devices Using the Accelerometer
- Open Access
- 1 January 2012
- Published by Springer Nature
- p. 229-239
PANGEA – Platform for Automatic coNstruction of orGanizations of intElligent Agents
- 1 January 2012
- Published by Springer Nature
- p. 229-239
Open AccessPANGEA – Platform for Automatic coNstruction of orGanizations of intElligent Agents
- 1 May 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21582246,p. 221-224
Simple and Robust Implementation of a Relative Virtual Mouse Controlled by Head Movements
The following paper introduces the work conducted to create a relative virtual mouse based on the interpretation of the head movements through a low cost camera. This virtual device is designed as a non-contact alternative for people with mobility impairments. First validation results show performance close to a digital joystick.
- 1 May 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21582246,p. 221-224
Simple and Robust Implementation of a Relative Virtual Mouse Controlled by Head Movements
The following paper introduces the work conducted to create a relative virtual mouse based on the interpretation of the head movements through a low cost camera. This virtual device is designed as a non-contact alternative for people with mobility impairments. First validation results show performance close to a digital joystick.