Thermal Analysis of Casson-Based Hybrid Nanofluid Flow on a Permeable Stretching Surface with Heat Source and Sink: A New Stochastic Approach

Abstract

Hybrid Casson nanoparticles are quite interesting to researchers due to their enhanced thermal and rheological properties. The use of artificial neural networks to describe and forecast thermal behaviors can dramatically improve the understanding of heat transfer across nanofluid models. With this motivation, this research aims to examine the heat transfer across a hybrid Casson nanofluid on a permeable stretching porous surface utilizing Runge Kutta Fehlberg’s 45th method and artificial neural networks (ANN). The governing partial differential equations are also reduced to ordinary differential equations using similarity transformations and solved numerically via Runge Kutta Fehlberg’s 45th method. The impact of various parameters over respective velocity and temperature profiles is analyzed and displayed graphically. The increase in the Casson parameter and porosity parameter slows down the fluid velocity, whereas elevated heat transfer is observed for augmented values of heat source/sink parameter. The ANN model was validated as a most convincing model owing to its admirable exactitude throughout testing, validation, and training and was compared to numerical outcomes. The ANN’s predictions are closely matched with the observed numerical data, implying that the model has effectively learned the underlying connections in the dataset. The findings from the current study can be utilized to develop more effective biomedical devices like drug delivery systems and blood flow simulations in artificial organs.