Application of machine learning for thermal exchange of dissipative ternary nanofluid over a stretchable wavy cylinder with thermal slip

This article explores the enhancement of thermal exchange in a dissipative Triple-nanoparticle (Al₂O₃+CuO+Cu) hybrid fluid over a stretchable wavy cylindrical surface with slip effect, incorporating Python bvp algorithm with artificial intelligence AI analysis of numerical results. The stochastic AI analysis gives the enhanced and optimized results with predictive modeling, incorporating randomness of influencing parameters and nonlinear turbulent behavior of model. The model has significant importance and application in noise reducing and drag reduction devices or structures. Moreover, the presented geometrical structure is useful in enhancing thermal conduction characteristic. The intricate interplay of constituent nanoparticles and their effect on complex heat transfer in drag optimization devices is the main focus of this study. Mathematical Model of PDEs of this flow problem is converted into system of ODEs by similarity transformations with introducing dimensionless parameters. Numerical solutions of the emerged system are obtained by Python bvp solver algorithm and graphical solutions by Python are presented. To expedite the solution process and enhance the accuracy of prediction, advanced AI algorithm, such as neural network and machine learning technique is adopted. Numerical dataset obtained from Python is embedded for further AI analysis by using Levenberg Marquardt Feed-forward Algorithm (LMFA) with 10 computing neurons and 4 output layers representing results for 4 parametric variations. A rise in the fluid flow speed is observed with higher of value yield stress or Newtonian-behavior i.e. of Casson parameter a₁ and stretching parameter λ for the sheet, but shows a decline with enhancing turbulence s₂. Temperature profile show a descending behavior with inclination of Eckert ratio Ec, and Prandtl ratio of momentum-thermal diffusivity.