Ayat Ahmed; Khalid Faisal Sultan · 10.18280/ijht.440212 https://doi.org/10.18280/ijht.440212 · 2026 · Experimental · Hybrid system · Machine learning / AI
International Journal of Heat and Technology
Experimental and Theoretical Study Based on Artificial Neural Networks of Photovoltaic Thermal Collector Using Air Cooling Through a Hybrid Solar Chimney Ayat Ahmed; Khalid Faisal Sultan Global warming represents a significant global challenge, emphasizing the urgent need for sustainable and environmentally friendly energy generation systems based on renewable resources.In this study, the performance of a hybrid photovoltaic/thermal (PV/T) system integrated with a solar chimney (SC) was experimentally evaluated to address the reduction in electrical efficiency caused by elevated photovoltaic (PV) module temperatures.Monocrystalline PV collectors were tested under varying operating conditions to assess power output and overall system performance.The results indicated that incorporating the SC notably enhanced airflow and ventilation, leading to a reduction in module temperature by approximately 5-13 °C compared to a conventional PV/T system.This reduction in temperature alleviated thermal stress on the solar cells and resulted in a significant improvement in electrical efficiency, which reached a maximum value of 15.8% at the highest airflow rate of 0.191 kg/s.Additionally, an Artificial Neural Network (ANN) model was developed and trained using experimental data to analyze the system's dynamic behavior.Key operating parameters, such as airflow rate, solar irradiance, ambient temperature, and cell temperature, were considered in the model.The model predictions showed strong agreement with experimental measurements, achieving high accuracy in estimating electrical and thermal efficiencies with minimal deviation.These results confirm that integrating SCs with PV/T systems, supported by Artificial Intelligence (AI) techniques, offers a practical and effective approach to improving system performance and reliability, particularly in hot climates.Furthermore, this approach lays the groundwork for various applications, including solar-assisted cooling, agricultural drying, and the enhancement of electricity generation efficiency.These advantages further support the potential of such systems as a sustainable and reliable component of future energy strategies.
Experimental
Hybrid system
Machine learning / AI
2026
International Journal of Heat and Technology
journal
main
yes
2026-04-30 12:00:00 00001899
experimental and theoretical study based on artificial neural networks of photovoltaic thermal collector using air cooling through a hybrid solar chimney
2026
International Journal of Heat and Technology
Ayat Ahmed; Khalid Faisal Sultan
10.18280/ijht.440212
Abstract
Global warming represents a significant global challenge, emphasizing the urgent need for sustainable and environmentally friendly energy generation systems based on renewable resources.In this study, the performance of a hybrid photovoltaic/thermal (PV/T) system integrated with a solar chimney (SC) was experimentally evaluated to address the reduction in electrical efficiency caused by elevated photovoltaic (PV) module temperatures.Monocrystalline PV collectors were tested under varying operating conditions to assess power output and overall system performance.The results indicated that incorporating the SC notably enhanced airflow and ventilation, leading to a reduction in module temperature by approximately 5-13 ℃ compared to a conventional PV/T system.This reduction in temperature alleviated thermal stress on the solar cells and resulted in a significant improvement in electrical efficiency, which reached a maximum value of 15.8% at the highest airflow rate of 0.191 kg/s.Additionally, an Artificial Neural Network (ANN) model was developed and trained using experimental data to analyze the system's dynamic behavior.Key operating parameters, such as airflow rate, solar irradiance, ambient temperature, and cell temperature, were considered in the model.The model predictions showed strong agreement with experimental measurements, achieving high accuracy in estimating electrical and thermal efficiencies with minimal deviation.These results confirm that integrating SCs with PV/T systems, supported by Artificial Intelligence (AI) techniques, offers a practical and effective approach to improving system performance and reliability, particularly in hot climates.Furthermore, this approach lays the groundwork for various applications, including solar-assisted cooling, agricultural drying, and the enhancement of electricity generation efficiency.These advantages further support the potential of such systems as a sustainable and reliable component of future energy strategies.
Abstract by the authors, reproduced under the CC BY 4.0 licence. Original publication via the link below.
Open source
PDF (open access)