Mathematical modeling of radiative nanofluid flow over nonlinear stretching sheet using artificial neural networks and Levenberg-Marquardt scheme: Applications in solar thermal energy

This work can be applied to improve solar thermal energy systems by accurately modeling the flow and heat transfer characteristics of nanofluids over nonlinear stretching sheet. The use of artificial neural networks with the Levenberg-Marquardt scheme enhances the precision and speed of simulations, enabling better design and optimization of solar collectors and heat exchangers. Additionally, it can be used to predict and control thermal performance in advanced renewable energy technologies. The aim of current work is to evaluate dissipative and radiative nanofluid flow over a nonlinear stretching sheet (DRNF-NFNSS) through utilizing an Intelligent Back-propagated Neural Network with Levenberg Marquardt (LMTNNs) to improve the prediction accuracy of radiation affected nanofluid flow dynamics. The research methodology involves transforming a nonlinear system of partial differential equations (PDEs) representing DRNF-NFNSS into an ordinary system by applying suitable transformations. To generate datasets of attractors related to fluid flow systems, several important parameters were varied using the Lobatto-IIIA technique (bvp4c solver). Applying datasets to construct the intelligent computing-based neural network of LMTNNs, which were then trained, tested and verified to generate approximation results for DRNF-NFNSS parameters, this paper discusses about it. Moreover, correlation analysis using the data of flow rate; heat transfer coefficient; mass transfer coefficient; Nusselt number at the surface and pressure drop will be done to propose a simple model that can be used in thermal design of nanofluid flows. These findings indicate that as heat mass transfer rates increase so do Weissenberg number, magnetic number and porous parameter while suction parameter increases these rates but has an opposite effect. This ability enables to design more efficient thermal management solutions for complex interactions in radiative nanofluid flows, thus reducing energy consumption and improving system reliability.