Machine Learning-Based Approach for Modeling the Nanofluid Flow in a Solar Thermal Panel in the Presence of Phase Change Materials

Considering the importance of environmental protection and renewable energy resources, particularly solar energy, present study investigates temperature control a panel using nanofluid (NFD) flow with eco-friendly nanoparticles (NPs) phase change material (PCM). The PCM was used under panel, NFD flowed through pipes within PCM. A number straight fins (three fins) were exploited on pipes, output temperature, heat transfer (HTR) coefficient, melted volume fraction measured for different pipe diameters (D_Pipe) from 4 mm to 8 at various time points (from 0 100 min). Additionally, use artificial intelligence machine learning, best conditions obtaining lowest highest pressure drop have been determined. While porosity approach model melt front, two-phase mixture simulate flow. It discovered that both increased considerably between t = 10 min before beginning rise varying rates, depending D_Pipe. HTR coefficient over time, showing similar behavior temperature. entire short D_Pipes 6 mm, while large remained un-melted long D_Pipe mm. An increase in D_Pipe, reduced maximum average temperatures, leading lower Furthermore, remaining longer panel.