Artificial neural network based computational evaluation of bioconvective gyrotactic microorganisms wedge flow of MHD Carreau fluid with thermal radiations

This project studies the boundary‑layer flow of a magnetohydrodynamic (MHD) Carreau fluid over a wedge, including bioconvection caused by gyrotactic microorganisms and the effects of thermal radiation. The mathematical model leads to highly nonlinear, coupled differential equations that describe momentum, heat transfer, nanoparticle concentration, and microorganism density. To solve these equations we use a hybrid computational approach. First, a reference solution is generated with MATLAB’s bvp4c boundary‑value solver. Next, an artificial neural network (ANN) that uses back‑propagation is built, trained, and validated against the reference data. The network adjusts its weights and biases over many training epochs to predict the velocity, temperature, and concentration profiles across the boundary layer. This

method lets us examine how key physical parameters—such as the Hartmann number, the thermal‑radiation parameter, and the bioconvection Lewis number—affect the flow. By combining machine learning with traditional numerical solvers, we obtain a fast and reliable way to model complex non‑Newtonian fluid flows in bioconvective systems.

Message: Hi FE, I need help with “Artificial neural network based computational evaluation of bioconvective gyrotactic microorganisms wedge flow of MHD Carreau fluid with thermal radiations” in “Mechanical Engineering”