The growing use of artificial intelligence in fluid mechanics research has resulted in scientists accepting soft-computing methods to correctly measure nonlinear transport phenomena. This research studies the movement of a Casson fluid that has two distinct layers above a plate, which extends in one direction and allows fluid movement through its surface, with the Cattaneo–Christov heat flux model that uses changing thermal conductivity and quadratic thermal stratification to perform real-world non-Fourier heat transfer research. The researchers applied similarity transformations to convert governing partial differential equations into nonlinear ordinary differential equations for numerical solution. An artificial neural network (ANN) was developed based on numerical solutions to provide quick predictions of flow and thermal characteristics. The ANN model demonstrates outstanding performance because its mean square error ranges from 10⁻⁶ to 10⁻⁸ and its regression coefficients approach 1. The research shows how Casson fluid parameters and stratification affect velocity and temperature distribution patterns, which researchers can apply to polymer manufacturing, biomedical applications, and industrial cooling systems. The ANN framework provides a trustworthy and effective method for simulating stratified non-Newtonian fluid movement with non-Fourier heat conduction.
Farooq et al. (Tue,) studied this question.