Deep learning approach for predicting heat transfer in water-based hybrid nanofluid thin film flow and optimization via response surface methodology

Abstract

Significance: There have been rapid developments in ternary hybrid nanofluids in the past few years due to their potential and importance. The potential of ternary hybrid nanofluids to maximise heat transport has enthralled researchers, prompting them to conduct a more thorough investigation of the performance of common base fluids. Researchers utilise nanofluids in applications like sophisticated cool systems, atriums, biomedical artifices, and active-chemical reactors to maximise mass and heat transmission. Objective: Dynamic simulations of an unsteady Ternary-hybrid nano flow via Thin film is investigated by considering Thermal radiation, Inclined MHD, and viscous dissipation. Method: ology: The present study develops a novel mathematical model using PDEs as governing equations. These PDEs can be transformed through similarity transformations into ODEs after the BVP4C is utilised to solve them numerically. Findings: The current study showed that SWCNT-Al2O3-MWCNT with H2O has a higher heat transfer rate than SWCNT-Al2O3 with H2O, making it appropriate for improving thermal performance in cutting-edge cooling systems such as heat exchangers and electrical devices.

Keywords

• Response surface optimization
• Deep learning
• Hybrid nanofluid
• Thin film flow