Thermal and flow dynamics of hybrid nanomaterial with thermophoresis and surface tension gradient using machine learning technique
Annotatsiya
The suggested model has significant implications for industrial renewable energy systems, sustainable thermal management, cooling technologies, and environmentally friendly lubricating operations. The vegetable oil-based hybrid nanofluid improves heat transfer efficiency, and thermophoresis study aids in understanding nanoparticle movement and surface coating phenomena. The machine learning technique allows for precise prediction and optimization of thermal behaviors and complex flow, making the model useful for manufacturing processes, and sophisticated energy-efficient engineering systems. This study inspects the result of MC (Marangoni convection) on thermophoretic particle deposition in chemical reactive flow of vegetable oil hybrid nanofluid flow over a sheet with a heat radiation. The nonlinear behaviour of the vegetable oil hybrid nanofluid model is approximated using the Levenberg–Marquardt backpropagation (LMBP) method within an artificial neural network (ANN) architecture. The conventional Bvp4c solver is used to create highfidelity reference data, and regression analysis, mean squared error, absolute error, and correlation coefficients are used to assess the ANN-LMBP model. The outcomes show that the suggested ANN-LMBP method is accurate and dependable. The concentration filed decrease as rise the values of thermophoretic parameter.
Hali tarjima qilinmagan