Optimal control strategy based on artificial intelligence applied to a continuous dark fermentation reactor for energy recovery from organic wastes

Dark fermentation process from low-cost renewable substrates for simultaneous wastewater treatment and hydrogen production (H2) is suitable due to economic viability and environmental sustainability. This work explores the application of an innovative control strategy in a scale fermentation bioreac...

Full description

Saved in:
Bibliographic Details
Main Authors: Kelly Joel Gurubel Tun, Elizabeth León-Becerril, Octavio García-Depraect
Format: Article
Language:English
Published: Elsevier 2025-03-01
Series:Green Energy and Resources
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2949720524000663
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850209562761625600
author Kelly Joel Gurubel Tun
Elizabeth León-Becerril
Octavio García-Depraect
author_facet Kelly Joel Gurubel Tun
Elizabeth León-Becerril
Octavio García-Depraect
author_sort Kelly Joel Gurubel Tun
collection DOAJ
description Dark fermentation process from low-cost renewable substrates for simultaneous wastewater treatment and hydrogen production (H2) is suitable due to economic viability and environmental sustainability. This work explores the application of an innovative control strategy in a scale fermentation bioreactor designed for energy recovery from organic wastes. This approach not only promotes low carbon emissions but also offers significant potential for industrial application. Machine learning (ML) and optimization methods are used to model the nonlinear process and then, a neural predictive control (NPC) strategy to drive the system to its optimal operating order under varying influent conditions is developed. Predictive control uses the Newton-Raphson as the optimization algorithm and a multi-layer feedforward neural network for the state prediction. This strategy has demonstrated to be a viable algorithm for real-time control applications. First, experimental data from continuous dark fermentation are modeled using support vector machine (SVM) algorithm for response prediction and then, optimization algorithms are employed to identify the key parameters that enhance H2 production. These optimal operating parameters are then used to create reference trajectory signals within a NPC scheme to achieve the optimal hydrogen production rate. The control strategy led to an HPR mean of 12.35 ± 1.2 NL H2/L-d under pseudo-steady state with hydrogen content in the gaseous phase of 63 % v/v, and a maximum COD recovery of 90% ± 2.8%. The results demonstrate that this innovative control method can significantly improve the performance and efficiency of biogas plants, showing viability for large-scale industrial implementation.
format Article
id doaj-art-1fefeb75db2b40589fce9675aecaca2d
institution OA Journals
issn 2949-7205
language English
publishDate 2025-03-01
publisher Elsevier
record_format Article
series Green Energy and Resources
spelling doaj-art-1fefeb75db2b40589fce9675aecaca2d2025-08-20T02:09:59ZengElsevierGreen Energy and Resources2949-72052025-03-013110011210.1016/j.gerr.2024.100112Optimal control strategy based on artificial intelligence applied to a continuous dark fermentation reactor for energy recovery from organic wastesKelly Joel Gurubel Tun0Elizabeth León-Becerril1Octavio García-Depraect2Water and Energy Department, CUTONALA, Universidad de Guadalajara, Avenida Nuevo Periférico No.555, Ejido San José Tatepozco, 45425, Tonalá, Mexico; Corresponding author.Department of Environmental Technology, Centro de Investigación y Asistencia en Tecnología y Diseño del Estado de Jalisco, A.C., Av. Normalistas 800, Colinas de la Normal, 44270, Guadalajara, Jalisco, MexicoInstitute of Sustainable Processes, University of Valladolid, Dr. Mergelina s/n., 47011, Valladolid, SpainDark fermentation process from low-cost renewable substrates for simultaneous wastewater treatment and hydrogen production (H2) is suitable due to economic viability and environmental sustainability. This work explores the application of an innovative control strategy in a scale fermentation bioreactor designed for energy recovery from organic wastes. This approach not only promotes low carbon emissions but also offers significant potential for industrial application. Machine learning (ML) and optimization methods are used to model the nonlinear process and then, a neural predictive control (NPC) strategy to drive the system to its optimal operating order under varying influent conditions is developed. Predictive control uses the Newton-Raphson as the optimization algorithm and a multi-layer feedforward neural network for the state prediction. This strategy has demonstrated to be a viable algorithm for real-time control applications. First, experimental data from continuous dark fermentation are modeled using support vector machine (SVM) algorithm for response prediction and then, optimization algorithms are employed to identify the key parameters that enhance H2 production. These optimal operating parameters are then used to create reference trajectory signals within a NPC scheme to achieve the optimal hydrogen production rate. The control strategy led to an HPR mean of 12.35 ± 1.2 NL H2/L-d under pseudo-steady state with hydrogen content in the gaseous phase of 63 % v/v, and a maximum COD recovery of 90% ± 2.8%. The results demonstrate that this innovative control method can significantly improve the performance and efficiency of biogas plants, showing viability for large-scale industrial implementation.http://www.sciencedirect.com/science/article/pii/S2949720524000663Dark fermentationNeural predictive controlSupport vector machineOptimizationHydrogen productionWastewater
spellingShingle Kelly Joel Gurubel Tun
Elizabeth León-Becerril
Octavio García-Depraect
Optimal control strategy based on artificial intelligence applied to a continuous dark fermentation reactor for energy recovery from organic wastes
Green Energy and Resources
Dark fermentation
Neural predictive control
Support vector machine
Optimization
Hydrogen production
Wastewater
title Optimal control strategy based on artificial intelligence applied to a continuous dark fermentation reactor for energy recovery from organic wastes
title_full Optimal control strategy based on artificial intelligence applied to a continuous dark fermentation reactor for energy recovery from organic wastes
title_fullStr Optimal control strategy based on artificial intelligence applied to a continuous dark fermentation reactor for energy recovery from organic wastes
title_full_unstemmed Optimal control strategy based on artificial intelligence applied to a continuous dark fermentation reactor for energy recovery from organic wastes
title_short Optimal control strategy based on artificial intelligence applied to a continuous dark fermentation reactor for energy recovery from organic wastes
title_sort optimal control strategy based on artificial intelligence applied to a continuous dark fermentation reactor for energy recovery from organic wastes
topic Dark fermentation
Neural predictive control
Support vector machine
Optimization
Hydrogen production
Wastewater
url http://www.sciencedirect.com/science/article/pii/S2949720524000663
work_keys_str_mv AT kellyjoelgurubeltun optimalcontrolstrategybasedonartificialintelligenceappliedtoacontinuousdarkfermentationreactorforenergyrecoveryfromorganicwastes
AT elizabethleonbecerril optimalcontrolstrategybasedonartificialintelligenceappliedtoacontinuousdarkfermentationreactorforenergyrecoveryfromorganicwastes
AT octaviogarciadepraect optimalcontrolstrategybasedonartificialintelligenceappliedtoacontinuousdarkfermentationreactorforenergyrecoveryfromorganicwastes