Box-Behnken design for the machine learning prediction of heat flow rate on the flow of Aluminium alloy aqueous hybrid nanomaterial over wedged Riga surface: Sensitivity analysis

Abstract

The present analysis pursuit of optimizing heat transfer rate by employing a Box-Behnken machine learning design of aluminium alloy aqueous hybrid nanomaterial over a Riga Wedge surface. The interaction of alloy nanoparticles AA7072 and AA7075 are taking part in pursuing the heat flow rate of the hybrid nanomaterial in association with the radiating heat and substantial heat supplier/absorption. The heightened thermal conductivity and stability of the hybrid nanomaterial offered by the inclusion of both alloy nanoparticles address the limitations of conventional fluid. The proposed mathematical framework is converted into dimensionless form by the adequate similarity function and a computational technique is adopted for the solution of the problem. Further, a robust statistical approach such as Box-Behnken design is utilized to evaluate systematically the influence of various factors such as particle concentrations, and radiating heat. By the use of machine learning techniques, it predicts the optimal conditions for heat transfer rate. Sensitivity evaluation is conducted to assess the influence of each of the terms on the thermal performance. This ongoing investigation is utilized in several applications spanning industries for efficient thermal management including aerospace, electronics, etc. However, the important outcomes of the study are; the thinner in momentum bounding surface is observed for the enhanced Hartmann number which enhances the profile in magnitude. Further, the inclusion of heat source overshoots the heat transport properties.