Computing of temperature-dependent thermal conductivity and viscosity correlation for solar energy and turbulence appliances via artificial neuro network algorithm

The growing popularity of artificial intelligence approaches has led to their application in a wide range of engineering fields. The most widely used artificial intelligence tool, artificial neural networks, can be used to predict data with high accuracy. An artificial neural network approach is being used to predict effective and accurate thermal conductivity and viscosity models for hybrid nanofluid systems. Here, new types of correlations relating to the thermophysical properties of Fly Ash-Cu nanoparticles with diameter sized 15.2nm and which are temperature-dependent are developed. The highest thermal conductivity and viscosity values were obtained for hybrid nanofluids with a mixture ratio of 20:80, with maximum amplification exceeding 83.2% and 65%, respectively, over the base fluid. The Fly Ash-Cu/water hybrid nanofluid's viscosity and thermal conductivity are evaluated for a concentration range of 0-4%. The evaluation of the Fly Ash-Cu/water hybrid nanofluids system at concentrations ranging from 0 to 4% most likely entails a scientific or engineering study aimed at understanding the behavior and properties of this nanofluid mixture. Nanoparticles can agglomerate or settle in the base fluid over time, compromising the stability of the nanofluids. Researchers may be interested in determining how varied quantities of Fly Ash and Cu nanoparticles affect the nanofluid's stability and sedimentation behavior. The heat transfer potential is examined within the optimistic range of temperatures of 30-80 circle C. Many fruitful results for turbulence and solar energy have been drawn. The Mouromtseff number achieved an optimal value for all concentration levels. The heat transfers of turbulent flow and thermal conductivity of hybrid nanofluids increase with the augmented values of concentrations and temperature. Researchers found an increase in thermal conductivity of hybrid nanofluids at 0-4% concentrations, potentially impacting heat transfer applications. The conclusion explores the potential integration of the developed correlations and neural network model into practical engineering or industrial applications involving solar energy and turbulence appliances. In this work, we extend the work of Kanti et al. [Sol. Energy Mater. Sol. Cells 234 (2022) 111423] which is on the properties of water-based fly ash-copper hybrid nanofluid for solar energy applications.