Graphene-based thin wire K-shaped machine learning optimized solar thermal absorber design using Cr-SiO2-Ag materials

Engineers are motivated to pursue green energy to mitigate the effects of climate change and generate sustainable electricity. Three materials are employed in an effective solar design: chromium (Cr) as a resonator, silicon dioxide (SiO2) as an intermediate layer, and silver (Ag) applied as a base part. This design harvests radiation in various light regions, including ultraviolet, visible, and near-infrared. The bandwidth exploration for 2800 nm (0.2-3 mu m), 1300 nm (0.2-1.5 mu m), and 800 nm (0.2-1 mu m) wavelengths is 90.24 %, 95.4 %, and 97.6 %, respectively. The proposed essay explores many approaches to presenting the current design. Design and parameters are investigated to express layer parameters and design building processes using variation analysis in all parameter sections. We examined the ML model's ability to accurately predict outcomes by varying its parameters. The highest achieved R2 value was 0.996353, obtained with a 0.25 test number. Additionally, the mean squared error was 3.22497 x 10-5. Compared to similar published studies, the current K-shaped design can optimize machine learning and graphene inclusion for high absorption output in household and industrial applications. The current K-shaped absorbed heat concentrates on solar heat for cooling, baking, heating, drying, cooking, and smoking at home. However, large industries can utilize it for sterilizing, viscosity control, washing, boiler preheating, and more.