Intelligent neuro computing paradigm for thermophoresis in carboxymethyl cellulose–water trihybrid nanoliquid with heat generation effects
Abstract
This research uses thermophoretic particle deposition and a heat source to examine the effects of heat production on a trihybrid nanofluid based on carboxymethyl cellulose and water. A fundamental technique in electrical and aero solution engineering for transporting small particles over a heat gradient is thermophoretic particle deposition. This model is beneficial for increasing the efficacy and architecture of modern thermal management systems that rely on thermophoretic particle movement, like as industrial heat exchangers, electronic component cooling, and polymer processing with CMC-based fluid. The framework, which includes Stefan blowing, internal heat generation, and intelligent neuro-computing techniques, enables efficient control of nanoparticle distribution and heat transfer rates, resulting in predictive optimization and better performance in complex thermal processing and energy applications. With the advancement of associated technologies, the importance of artificial intelligence and machine learning has grown significantly. To address the mathematical formulation, this study trains a ML (machine learning) model based on artificial neural networks using the Bayesian-Regularized approach. The concentration profile decreases as the values of the thermophoretic parameters grow.