Thermal Performance of Magnetized Darcy-Forchheimer Flow of Boger Hybrid Nanofluid With Cattaneo-Christov Flux Model Using Artificial Neural Networks

Abstract

This concept has numerous uses, including sophisticated thermal management, porous media conveyance, and industrial cooling systems. Boger hybrid nanofluids' (HNFs') magnetized Darcy-Forchheimer flow improves heat transmission in geothermal systems, packed-bed reactors, filtration devices, and energy storage technologies. The Cattaneo-Christov flux model defines heat transport more accurately by accounting for thermal relaxation effects, whereas thermophoretic particle deposition is crucial in coating processes, aerosol technology, and nanoparticle (NP)-based manufacturing. Furthermore, the use of artificial neural networks (ANNs) for precise enhancement of complex flow and thermal behaviors makes the model useful for smart engineering designs, electronic cooling, biomedical devices, and renewable energy applications. This study uses the Cattaneo-Christov heat and mass flux model and integrated numerical computing to evaluate the Marangoni convection (MC) flow of MHD Boger HNF across a sheet with thermophoretic particle deposition using the intelligent Levenberg-Marquardt (ILM) optimization algorithm and an ANN algorithm. Moreover, the algorithm's consistency and stability are guaranteed. Mapping thermal, velocity, and solutal profiles from input to output is another use for neural networking. These outcomes show how accurate ANN forecasts and optimizations may be. The data used by the ANN-based LM optimization technique is divided into three categories: validation (15%), testing (15%), and training (70%). As the values of the thermal and concentration relaxation parameters rise, the thermal and concentration profiles decrease.