Machine learning analysis for the thermophoretic particle deposition in casson nanofluid with porous medium and heat generation

Abstract

The aim of this work is to evaluate the impacts of heat generation on the radiative flow of Casson nanofluid over a sheet under LTNE circumstances while microbes are present, utilizing machine learning techniques based on the Levenberg-Marquardt algorithm. A simple method for moving tiny particles across a temperature gradient is thermophoretic particle deposition, which is essential for electrical and aerosol solution engineering. The energy equations are derived from the local thermal non-equilibrium to determine the unique thermal profiles of the solid and liquid phases. The current model, which combines the Levenberg-Marquardt method with AI-NN (artificial intelligence neural networks), offers a more complex computational solution than standard numerical methods. The proposed model has broad uses in environmental research, and industrial fluid dynamics. By optimizing microorganisms in MHD Casson nanofluid flow with thermophoretic particle deposition, the model improves pollutant removal by bio-convection, leading to better wastewater treatment. It helps in the growth of more efficient bioreactors for microbial fuel cells and pharmaceutical medication delivery systems. Furthermore, nanofluid-based heat transfers and advanced biotechnology applications gain from the capacity to precisely predict and control microbe behaviour in complex fluid environments through the use of ANNs (artificial neural networks). The concentration profile decreases as the thermophoretic parameter values rise.