Optimization of heat and mass transfer in exothermic reactive fluids using advanced numerical methods and ANN models DOI
Shahzad Khattak, Mumtaz Khan, Mudassar Imran

et al.

ZAMM ‐ Journal of Applied Mathematics and Mechanics / Zeitschrift für Angewandte Mathematik und Mechanik, Journal Year: 2025, Volume and Issue: 105(5)

Published: April 19, 2025

Abstract Artificial intelligence (AI) has emerged as a transformative tool in fluid flow modeling, offering enhanced simulation accuracy, optimization, and system performance. This study investigates the mixed convective of Jeffery over slendering sheet, incorporating effects thermal radiation, heat generation, Joule heating, chemical reactions. The governing partial differential equations (PDEs) are transformed into nonlinear ordinary (ODEs) solved using bvp4c solver MATLAB. To optimize artificial neural networks (ANNs) backpropagation (BPNNs) employed, leveraging Levenberg–Marquardt algorithm (LMA) for training validation. dataset is partitioned training, testing, validation, with performance evaluated mean squared error (MSE), curve‐fitting graphs, histograms. results demonstrate high MSE values consistently range validating robustness ANN‐LM LMA‐BPNN frameworks. Furthermore, physical parameters on momentum, thermal, concentration boundary layers examined detail. Heat generation found to enhance temperature profile, thickening layer, while variable thickness parameter improves skin friction, heat, mass transfer. Conversely, higher Schmidt numbers reduce profile due limited diffusivity. quantitative qualitative outcomes thoroughly analyzed, benchmarked against existing literature, showing close alignment. provides valuable insights influence key behavior establishes robust AI‐driven framework future research dynamics.

Language: Английский

Optimization of heat and mass transfer in exothermic reactive fluids using advanced numerical methods and ANN models DOI
Shahzad Khattak, Mumtaz Khan, Mudassar Imran

et al.

ZAMM ‐ Journal of Applied Mathematics and Mechanics / Zeitschrift für Angewandte Mathematik und Mechanik, Journal Year: 2025, Volume and Issue: 105(5)

Published: April 19, 2025

Abstract Artificial intelligence (AI) has emerged as a transformative tool in fluid flow modeling, offering enhanced simulation accuracy, optimization, and system performance. This study investigates the mixed convective of Jeffery over slendering sheet, incorporating effects thermal radiation, heat generation, Joule heating, chemical reactions. The governing partial differential equations (PDEs) are transformed into nonlinear ordinary (ODEs) solved using bvp4c solver MATLAB. To optimize artificial neural networks (ANNs) backpropagation (BPNNs) employed, leveraging Levenberg–Marquardt algorithm (LMA) for training validation. dataset is partitioned training, testing, validation, with performance evaluated mean squared error (MSE), curve‐fitting graphs, histograms. results demonstrate high MSE values consistently range validating robustness ANN‐LM LMA‐BPNN frameworks. Furthermore, physical parameters on momentum, thermal, concentration boundary layers examined detail. Heat generation found to enhance temperature profile, thickening layer, while variable thickness parameter improves skin friction, heat, mass transfer. Conversely, higher Schmidt numbers reduce profile due limited diffusivity. quantitative qualitative outcomes thoroughly analyzed, benchmarked against existing literature, showing close alignment. provides valuable insights influence key behavior establishes robust AI‐driven framework future research dynamics.

Language: Английский

Citations

0