Irreversibility Analysis through Neural Networking of the Hybrid Nanofluid for the Solar Collector Optimization

Abstract

Abstract Advanced techniques are used to increase the efficiency of the energy assets and maximize the appliance efficiency of the main resources. In the recent study, the focus is paid to the solar collector to cover thermal radiation through optimization and enhance the performance of the solar panel. Hybrid nanofluids (HNs) consist of a base liquid (C3H8O2) glycol whereas copper (Cu), and aluminum oxide (Al2O3) are used as nanomaterials for formation (HNs). The flow of the stagnation point is considered in the presence of the Riga plate. The state of the solar thermal system is termed viva stagnation to control the additional heating through the flow variation in the collector loop. The inclusion of entropy generation and Bejan number formation is primarily conceived under the influence of physical parameters for energy optimization. The computational analysis was carried out utilizing the control volume finite element method (CVFEM), and Runge–Kutta 4 (RK-4) methods. The results are further validated through a machine learning neural networking procedure. The conclusions showed that the heat transfer rate is greatly upgraded with a variation of the nanoparticle's volume fraction. We expect this improvement to progress the stability of heat transfer in the solar power system.