Machine learning investigation through Python for thermophoretic deposition with radiation on thermal mass transfer of trihybrid nanofluid across sharp dynamics

This research work employs a machine learning approach with Python to analyze the complex relation of thermophoretic deposition and radiation effect on the mass and heat transfer of ternary hybrid nanofluid flow over the wedge. The colloidal comprising [Formula: see text], [Formula: see text] and ZnO with Engine Oil and Water in equal proportion as a base fluid, is considered here, due to the potential enhancer of thermal performance in numerous applications. The governing PDEs for flow rate, heat and mass transfer are transformed into a system of ODEs and numerical dataset generated by Python for stochastic evaluation through Matlab Neural Network assisted by Levenberg Marquardt Machine Learning Algorithm to extract intricate patterns and comparison between numerical and stochastic simulations. The impact of influencing parameters such as volume fraction, wedge angles, Eckert ratio and Radiation coefficients are analyzed. The outcomes of this research shed light on the synergetic effects of thermophoretic deposition and radiation on the thermal mass exchange of tri-nanohybrid fluid across the sharp edge of the device. This machine learning artificial intelligence (AI) tool is cost-effective and far better than deterministic numerical outputs as compared with analytical evaluations. A detailed graphical representation is embedded in this paper for comparisons and error analysis. Influencing parameters are analyzed for temperature, velocity and concentration profiles. Moreover, engineering parameters are also evaluated and plotted against the infecting agents. Graphical analysis of Nusselt, Sherwood and Skin friction coefficients added for broad spectrum comparison and comprehensive analysis for the significant implementation of the present discussion at the industrial level, for the benefit of production units, heavy industry and energy management systems in numerous fields.

Перевод пока недоступен