Artificial Neural Network and Response Surface Methodology-Driven Optimization of Cu-Al2O3/Water Hybrid Nanofluid Flow in a Wavy Enclosure with Inclined Periodic Magnetohydrodynamic Effects

• Type: Article in International Scientific Journal
• Date: 2025

Authors

Islam, T (Author) Other; Sílvio Gama (Author) FCUP; Afonso, MM (Author) FCUP

Journal

Title: Mathematics

Vol. 13

Final page: 78

Publisher: MDPI

Indexing

ISI Web of Knowledge - 0 Citations

Scopus - 0 Citations

Other information

Authenticus ID: P-017-SFA

DOI: 10.3390/math13010078

Abstract (EN): This study explores the optimization of a Cu-Al2O3/water hybrid nanofluid within an irregular wavy enclosure under inclined periodic MHD effects. Hybrid nanofluids, with different mixture ratios of copper (Cu) and alumina (Al2O3) nanoparticles in water, are used in this study. Numerical simulations using the Galerkin residual-based finite-element method (FEM) are conducted to solve the governing PDEs. At the same time, artificial neural networks (ANNs) and response surface methodology (RSM) are employed to optimize thermal performance by maximizing the average Nusselt number (Nuav), the key indicator of thermal transport efficiency. Thermophysical properties such as viscosity and thermal conductivity are evaluated for validation against experimental data. The results include visual representations of heatlines, streamlines, and isotherms for various physical parameters. Additionally, Nuav, friction factors, and thermal efficiency index are analyzed using different nanoparticle ratios. The findings show that buoyancy and MHD parameters significantly influence heat transfer, friction, and thermal efficiency. The addition of Cu nanoparticles improves heat transport compared to Al2O3 nanofluid, demonstrating the superior thermal conductivity of the Cu-Al2O3/water hybrid nanofluid. The results also indicate that adding Al2O3 nanoparticles to the Cu/water nanofluid diminishes the heat transport rate. The waviness of the geometry shows a significant impact on thermal management as well. Moreover, the statistical RSM analysis indicates a high R2 value of 98.88% for the response function, which suggests that the model is well suited for predicting Nuav. Furthermore, the ANN model demonstrates high accuracy with a mean squared error (MSE) of 0.00018, making it a strong alternative to RSM analysis. Finally, this study focuses on the interaction between the hybrid nanofluid, a wavy geometry, and MHD effects, which can optimize heat transfer and contribute to energy-efficient cooling or heating technologies.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 44