Impact of thermal radiation on fractional viscoelastic nanofluid flow with joint heat mass transfer using a neural network based approach
Abstract
This study aims to enhance the predictive modeling of free convection flow in viscoelastic nanofluids influenced by thermal radiation, concentrating especially on improving the understanding of heat and mass transfer behavior. To achieve this, a novel computational framework is developed by incorporating the Prabhakar fractional operator, it successfully records memory effects and non-local behavior of-ten neglected in classical models. The governing fractional partial differential equations are solved using Levenberg-Marquardt backpropagation algorithm-trained artificial neural networks. Training data are generated analytically through the Laplace transform, with a 70 %30 % training-validation split. The proposed model demonstrates high predictive accuracy, achieving a mean squared error below 10−4. Sensitivity analysis reveals that the fractional parameter reduces velocity fluid, while concentration and temperature respond strongly to chemical reactions and thermal conditions. The main contribution of this work lies in combining fractional calculus with ANN-based optimization to provide a reliable, efficient tool for modeling and enhancing heat transfer in nanofluid-based engineering systems.
Author
Nashwan Adnan OTHMAN
Publisher
ISSN
Publish Date: