Dynamic Behavior of Ferro‐Nanofluid Flow Over a Vertical Stretching Sheet for Enhanced Cooling Applications: A Machine Learning Approach

ABSTRACT Due to their stimuli‐responsive behavior and superior thermal conductivity, as well as low inherent toxicity and chemical stability, the ferrite oxide nanoparticles are useful in the cooling systems, microfluidics, and energy systems. The colloidal suspensions of single‐domain magnetic nanoparticles, with water known as ferro‐nanofluids, find more applications in biology, emerging technologies, and other engineering disciplines. This study examines the time‐dependent two‐dimensional flow of electrically conducting, magnetic‐type ferro‐nanofluid over a vertically expanding sheet, influenced by a heat source, and Lorentz force effect. The governing equations of the present problem are reduced to ordinary differential equations through similarity transformations and solved using the Runge Kutta Fehlberg 5 th order method with shooting approach. Additionally, an artificial neural network (ANN) model is utilized to optimize the thermal transfer rate within the system. The developed ANN model proves to be reliable, as it exhibits excellent accuracy during the training, validation, and testing phases. Moreover, the results indicate that suction and nanoparticle concentration reduce the velocity distribution, whereas the unsteady parameter and heat source parameter enhance the thermal distribution. Finally, the agreement between the present results and existing findings reinforces their credibility.