Application of Artificial Neural Networks Modelling for Analyzing Non-Newtonian Fluid Flow Over Porous Media with an Induced Magnetic Field

Abstract

The goal of this work is to better comprehend how enhanced thermal transfer, which really increased the induced magnetic field of hybrid nanofluid, may alleviate the growing heat density of tiny and other technological processes. Non-Newtonian fluid, like Oldroyd-B fluid is encrypted for a given physical model. Furthermore, copper and alumina hybridize in sodium alginate to produce a homogeneous, very diluted combination. The non-linear PDE system of equations is transformed into an ordinary differential system by applying the appropriate self-similarity variables. For this stage of the work, we built a mid-rich integrated ANN-LMBP that is envisioned with non-linear thermal radiation and heat production. Graphical depictions are used to demonstrate the interplay between various skewing. The entropy production of the Oldroyd-B fluid slopes with temperature ratio for all comparing scenarios, while Bejan number exhibits a declination with increase in Brinkman number. For uses including thickening, gelling, emulsifying, stabilizing, and texturizing, the predictions come true. Since sodium alginate is a standard component that is utilized in many cuisines today, including ice cream, jelly, acidic milk drinks, sauces, fast noodles and beer.