Prediction of heat exchanger efficiency using laminar heat transfer in swirling flow of radiated graphene oxide with nano fluid additives using machine learning technique

Abstract

Nanotechnology has recently led to new possibilities for enhancing heat transfer in heat exchangers. The remarkable thermal characteristics of graphene oxide (GO)-based nanofluids with nanoscale additions have garnered significant attention in particular. When nanofluids and intricate flow patterns are involved, traditional analytical models frequently fail to appropriately forecast the efficiency of heat exchangers. Analyzed the phenomenon of laminar heat transfer in a heat exchanger that has a swirling flow of fluid dynamics, and pressure drop, and predicted the condensation heat transfer coefficient (HTC) of LHT. The functionalized radiated GO was chosen as nanomaterials in the present for the Pre-processing of Data Methods for managing outliers by machine learning (ML) models, like the CLAHE algorithm. The logarithmic mean temperature difference (LMTD) can be used to determine the temperature driving power for heat transfer within a heat exchanger. The Dynamic Smagorinsky Model (DSLM) and Wall-Adapting Local Eddy-viscosity (WALE) Model are turbulence models primarily designed for capturing turbulent behavior in fluid flows. The Kern technique and Hagen–Poiseuille equation are used for the pressure drop and pumping power needed in a shell and tube in laminar flow through a microtube based on Levenberg–Marquardt and Momentum Algorithm to predict Nusselt number and pressure drop in heat exchangers. The prediction sensitivity of the HTC by an LHT-trained ML model is used to evaluate the performance. The ML methods may be effectively used to forecast and maximize heat exchanger performance in the setting of laminar heat transfer in radiated GO nanofluid swirling flows. The accuracy score of 99%, demonstrating its exceptional predictive capabilities and results has great potential to improve energy efficiency, save operating costs, and advance sustainable practices in various industrial applications.

Keywords:

• Fluid dynamics
• heat exchanger
• laminar heat transfer
• machine learning
• nanofluid

Disclosure statement

The authors declare that they have no conflict of interest.

Data availability statement

Data sharing not applicable to this article as no datasets were generated or analyzed during this study.