Scientists from India's SRM Institute of Science and Technology have developed a technique based on an artificial neural network to assess the potential of solar-powered hydrogen production.
They presented their findings in “Performance assessment of a solar-powered hydrogen production system and its ANFIS model,” which was recently published in Heliyon. The technique is based on the adaptive neuro-fuzzy inference system (ANFIS), which is known for integrating both neural networks and fuzzy logic principles.
Artificial neural networks are a machine-learning technology that help computers to learn from observational data. They are algorithms that can recognize underlying relationships in sets of data through a process that mimics the way the human brain operates.
Fuzzy logic is known to provide clear solutions to complex problems, as it also reflects human thinking and decision-making. While conventional logic works on precise inputs and produces definite outputs such as “true” or “false” and “yes” or “no,” fuzzy logic tends to include the range of possibilities between “yes” or “no” – like “certainly yes” or “possibly not,” for example.
The scientists tested the proposed technique on a hydrogen production system incorporated with a photovoltaic-thermal (PVT) solar collector.
The Indian group took measurements of the hydrogen yield rate and the electrical efficiency of the PVT system by orienting the PV modules toward south at three different angles of 30°, 40°, and 50°. “At each angle, different output parameters such as PV module surface temperature, inlet and outlet fluid temperature, open-circuit voltage and short circuit current are continuously measured by the circulating water, ethylene glycol and water-ethylene glycol mixture in the thermal collector,” they explained.
Their measurements showed that the thermal output of the PVT device increases by raising the tilt angle, while the optimum tilt angle is reached as 40°. “The higher amount of thermal efficiency of 33.8% have been obtained with spiral flow PVT system cooled with water placed at an angle of 40° inclination,” they said.
This system configuration ensured the highest hydrogen yield rate, as more electrical output was provided by the PV unit, they said. “This accelerates the electrolysis process in electrolyzer,” the researchers concluded. “The ANFIS results revealed that the predicted values are in good agreement with the experimental values and it could be a suitable alternate method to predict the values of PVT systems in future.”
This content is protected by copyright and may not be reused. If you want to cooperate with us and would like to reuse some of our content, please contact: firstname.lastname@example.org.