Artificial intelligent approach for flow stability in Eyring Powell hybrid nanofluids via porous shrinking sheets

作     者：Fatima, Nahid Kouki, Marouan Khan, Muhammad Imran Amjad, Arslan Bin Asghar, Zaheer Zeeshan, Ahmad Ijaz, Nouman 

作者机构：Department of Mathematics and Sciences Prince Sultan University Riyadh11586 Saudi Arabia Department of Information System Faculty of Computing and Information Technology Northern Border University Rafha Saudi Arabia Department of Mathematics and Statistics International Islamic University Islamabad 44000 Pakistan Centre for Mathematical Sciences Pakistan Institute of Engineering and Applied Sciences Nilore Islamabad45650 Pakistan Department of Physics and Applied Mathematics Pakistan Institute of Engineering and Applied Sciences Nilore Islamabad45650 Pakistan Department of Mathematics College of Science Korea University 145 Anam-ro Seongbuk-gu Seoul02841 Korea Republic of Department of Mathematics and Statistics Punjab Group of Colleges G.T. Road Jada Jhelum49600 Pakistan 

出 版 物：《Journal of Molecular Liquids》 (J Mol Liq)

年 卷 期：2025年第422卷

核心收录：

学科分类：07[理学] 081203[工学-计算机应用技术] 080103[工学-流体力学] 080104[工学-工程力学] 0835[工学-软件工程] 070201[理学-理论物理] 0825[工学-航空宇航科学与技术] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 0801[工学-力学（可授工学、理学学位）] 0702[理学-物理学] 

基　　金：Dr Nahid Fatima would like to thank Prince Sultan University Riyadh for support and help through TAS lab. The authors extend their appreciation to the Deanship of Scientific Research at Northern Border University  Arar  KSA for funding this re- search work through the project number \u201CNBU-FFR-2025-2570-02\u201D.The authors extend their appreciation to the Deanship of Scientific Research at Northern Border University   Arar  KSA for funding this re- search work through the project number \u201CNBU-FFR-2024-2570-07\u201D 

主　　题：Eigenvalues and eigenfunctions 

摘      要：This study aims to analyze flow stability using a computational intelligence technique that integrates a Levenberg-Marquardt approach utilizing artificial intelligence implemented through a backpropagation neural network. AI-based LMS-BPNN approach is utilized to examine the flow behavior of Eyring Powell hybrid nanofluid over a porous shrinking sheet. By applying skillful transformations, a set of ordinary differential equations is obtained from the partial differential equations that describe the hybrid nanofluid. Scenarios 1–5 illustrate how the built-in MATLAB function, bvp4c, solves ordinary differential equations systems by carefully modifying input parameters to get the initial or reference solution. The numerical data was split into three groups: 10 % for testing, 10 % for validation, and 80 % for training. The LMS-BPNN was used to find approximate solutions for these scenarios. To verify the effectiveness and reliability of LMS-BPNN, we employed regression analysis, error metrics, and correlation index (R)-based fitness curves. In each scenario, the temperature and velocity profiles gradually approached the boundary conditions as expected. The flow performance outcomes for the dual solution (Cfx and Nux) are also analyzed using the LMS-BPNN method. The perturbation scheme is applied to the boundary layer problem to obtain the eigenvalues problem. The unsteady solution f(η,τ) converges to steady solution fo(η) for τ→∞ when γ≥0. However, an unsteady solution f(η,τ) diverges to a steady solution fo(η) for τ→∞ when γ © 2025 Elsevier B.V.