CONSTRUCTION OF NEURAL NETWORK BASED INTELLIGENT COMPUTING FOR TREATMENT OF DARCY-FORCHHEIMER SISKO NANOFLUID FLOW WITH ROSSELAND'S RADIATIVE PROCESS

Abstract

A generalization of Newtonian and power-law fluids is the Sisko model. It foretells dilatants and fluid pseudoplasticity. It was first suggested to use the Sisko fluid model to gauge high shear rates in lubricating greases. Three constants in this model are easily selectable for certain fluids, and it is demonstrated that the model is a good predictor of shear thickening and thinning. The study of nanofluids is gaining popularity quickly because of unique thermal, mechanical, and chemical characteristics of nanomaterials. Sisko nanofluids are also required for the production of nanoscale materials because of the superb wetting and dispersing capabilities they possess. In the present investigation, the Levenberg-Marquardt method with backpropagated neural networks is used to evaluate the nanomaterial flow of Darcy-Forchheimer Sisko fluid model. Thermophoresis and Brownian motion effects are considered when developing the nanofluid model. By applying the necessary transformations, the original nonlinear coupled partial differential system representing fluidic model are converted to an analogous nonlinear ordinary differential system. For different fluid model scenarios, a dataset for the proposed multilayer perceptron artificial neural network is produced by altering the necessary variables via the Galerkin weighted residual approach. An artificial neural network called a multilayer perceptron has been created in order to forecast the multilayer perceptron values.