Dynamic prediction of nano-milk transport in a parabolically elevated electromagnetic channel with parabolic thermal ramping: A Python-based machine learning approach

This study analyzes the fluctuating dynamics of milk flow containing silver and magnesium oxide nanoparticles in a parabolically elevated electromagnetic channel exposed to a parabolic thermal ramp-up, employing artificial intelligence (AI)-based machine learning algorithms in Python. This study unifies key physical phenomena comprising thermal heat flux, heat sinks, and porous medium's impendence. Employing rigorous mathematical and computational methods such as the Laplace transform for streamlined solutions to dynamic flow equations, we analyze milk flow dynamics, concentrating on variables like shear stress (SS) and rate of heat transfer (RHT), and presenting results through detailed graphical representations. The findings indicate that nanoparticles significantly enhance thermal conductivity and viscosity, thereby improving heat transport efficiency and modifying flow dynamics. Notably, an elevation in milk momentum is observed with a higher modified Hartmann number, while wider electrode widths help mitigate this effect. In milk flow, escalated pressure oscillation frequencies intensify SS, and elevated heat source parameters enhance RHT. The AI-based machine learning algorithms in Python, reinforced by artificial neural networks, achieves 100% precision in SS prediction on both training and validation datasets and maintains 99.974% accuracy on testing datasets and 99.93% during cross-validation for RHT predictions. The model findings highlight the potential of nanoparticle-enhanced milk for efficient heating, crucial to improving pasteurization and sterilization. Python AI algorithms enable real-time control, boosting efficiency, quality, and sustainability in dairy processing.