A recent study has employed a hybrid physics-informed neural network (PINN) to analyze and model the flow of ternary hybrid nanofluids in a rotating annulus. This approach combines the ability of neural networks to learn complex patterns with the robustness of known physical laws, allowing for a detailed sensitivity analysis of the parameters governing the behavior of these fluids. The work focuses on understanding how factors such as rotation, nanoparticle concentration, and thermal properties affect heat transfer and flow.

Hybrid nanofluids, composed of the dispersion of two or more types of nanoparticles in a base fluid, offer enhanced thermal properties that make them attractive for heat transfer applications. The use of a rotating annulus introduces additional complexities due to Coriolis and centrifugal forces, which significantly influence fluid dynamics. The PINN methodology used in this study overcomes the limitations of traditional numerical methods by integrating the Navier-Stokes equations and energy conservation directly into the neural network's cost function, resulting in more accurate and physically consistent solutions.

The results of the sensitivity analysis reveal the critical influence of various parameters, such as the Reynolds number, Hartmann number, and nanoparticle volume fraction, on the velocity and temperature profiles of the nanofluid. This advanced modeling not only provides a deeper understanding of the underlying physics but also opens new avenues for the design and optimization of heat transfer systems in engineering. The ability to accurately predict the behavior of these fluids under various operating conditions is fundamental for the development of more efficient and sustainable technologies.