TY - GEN
T1 - Numerical analysis and AI prediction of heat removal using PCM attached to PV panel
AU - Raza, Saleem
AU - Im, Ik Tae
AU - Abdelmotalib, Hamada M.
N1 - Publisher Copyright:
© 2025 Begell House, Inc.
PY - 2025
Y1 - 2025
N2 - This study numerically investigates the cooling performance of a photovoltaic (PV) panel integrated with phase change material (PCM), specifically, paraffin wax RT42, attached to its back surface. The research aims to evaluate the PV-PCM system performance under a steady heat flux of 800 W/m², with the panel tilted at angles of 15°, 20°, 25°, and 30°. The melting process and heat transfer within the PCM are modeled using the enthalpy-porosity technique. The results indicate that the upper part of the PV panel experiences the highest temperatures, while the lower section remains relatively cooler. Furthermore, artificial intelligence (AI) models are employed to predict the PV panel temperature under various conditions, for predicting the PV panel temperature. We trained the data obtained from the simulations. The AI predictions deliver accurate forecasts that complement the simulation results. Overall, the study highlights the advantages of PCM-based cooling and AI-driven temperature prediction in enhancing PV efficiency while reducing computational costs.
AB - This study numerically investigates the cooling performance of a photovoltaic (PV) panel integrated with phase change material (PCM), specifically, paraffin wax RT42, attached to its back surface. The research aims to evaluate the PV-PCM system performance under a steady heat flux of 800 W/m², with the panel tilted at angles of 15°, 20°, 25°, and 30°. The melting process and heat transfer within the PCM are modeled using the enthalpy-porosity technique. The results indicate that the upper part of the PV panel experiences the highest temperatures, while the lower section remains relatively cooler. Furthermore, artificial intelligence (AI) models are employed to predict the PV panel temperature under various conditions, for predicting the PV panel temperature. We trained the data obtained from the simulations. The AI predictions deliver accurate forecasts that complement the simulation results. Overall, the study highlights the advantages of PCM-based cooling and AI-driven temperature prediction in enhancing PV efficiency while reducing computational costs.
UR - https://www.scopus.com/pages/publications/105023977547
U2 - 10.1615/THMT-25.1180
DO - 10.1615/THMT-25.1180
M3 - Conference paper
AN - SCOPUS:105023977547
SN - 9781567005530
T3 - Proceedings of the International Symposium on Turbulence, Heat and Mass Transfer
BT - THMT-25 Turbulence, Heat and Mass Transfer
PB - Begell House Inc.
T2 - 11th International Symposium on Turbulence, Heat and Mass Transfer, THMT 2025
Y2 - 21 July 2025 through 25 July 2025
ER -