Prediction of magnetohydrodynamics fluid flow with viscous dissipation through artificial neural network
Abstract The prediction of fluid flow in non-Newtonian Magneto-hydrodynamics (MHD) with Biot number is examined in this article. The Levenberg–Marquardt algorithm to predict the Nusselt Number (NN) and Skin Friction Coefficients (SFCs). Along with the Biot number, Eckert number and thermal Grashof n...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer Nature
2025-07-01
|
| Series: | Discover Molecules |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s44345-025-00026-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract The prediction of fluid flow in non-Newtonian Magneto-hydrodynamics (MHD) with Biot number is examined in this article. The Levenberg–Marquardt algorithm to predict the Nusselt Number (NN) and Skin Friction Coefficients (SFCs). Along with the Biot number, Eckert number and thermal Grashof number, the flow characteristics are analysed in relation to the convective boundary condition. Using the proper similarity transformations, the system of non-linear partial differential equations was transformed into a system of non-linear ordinary differential equations. By altering the values of each parameter found in the transformed flow ODEs and boundary condition using the spectral quasi-linearization method (SQLM), the input and output data sets for the proposed models are produced. This trained network analyzed Mean Square Error (MSE), Root Mean Square Error (RMSE), Correlation Coefficient (R), Mean of errors, Standard deviation of errors to check the prediction accuracy of our designed ANN model. The results indicate that with increasing Biot number, the temperature profile increases, while the flow profiles are also increased. |
|---|---|
| ISSN: | 3004-9350 |