Parametric study of plasma swirling flow based on magnetohydrodynamics informed deep learning
Authors:
- Wudi LuoWLWudi Luo
- Jun-Xue RenJRJun-Xue Ren
- Zhiyuan ChenZCZhiyuan Chen
- Renfan MaoRMRenfan Mao
- Guangchuan ZhangGZGuangchuan Zhang
- Yibai WangYWYibai Wang
- Haibin TangHTHaibin Tang
- 1 July 2025
- journal article
- Published by AIP Publishing in Physics of Fluids
- Vol. 37 (7)
Abstract
A magnetohydrodynamics (MHD) informed deep learning framework is developed to address the challenges of achieving higher accuracy and faster optimization speeds in physics-informed neural networks (PINNs) for solving multi-parameter MHD problems without labeled data. By integrating hybrid boundary conditions, optimized activation functions, and residual-based adaptive sampling strategy, the proposed framework achieves a global relative error of approximately 2% across a wide parameter range. To address the challenge of training coupled equations in broad parameter regimes, we introduce coefficient normalization for coupled terms that balances loss contributions and prevents equation decoupling. Through this MHD-informed deep learning approach, comprehensive parametric studies and parameter optimizations are conducted to systematically investigate the effects of magnetic field strength, mass flow rate, and geometric configuration on plasma swirling flow dynamics. The proposed methodology leverages the automatic differentiability of PINNs for rapid parameter optimization, achieving up to an order-of-magnitude acceleration in parameter optimization compared to conventional methods like Genetic Algorithm while maintaining comparable accuracy. This advancement demonstrates significant potential for the parametric analysis and optimization design of MHD flow-based devices in the areas of advanced space thruster and manufacturing technologies.Keywords
Funding Information
- National Natural Science Foundation of China (12372291)
- National Natural Science Foundation of China (U24B2008)
- National Natural Science Foundation of China (52272383)
- National Natural Science Foundation of China (52407157)
This publication has 36 references indexed in Scilit:
- Thermal performance of radiative hydromagnetic peristaltic pumping of hybrid nanofluid through curved duct with industrial applicationsCase Studies in Thermal Engineering, 2024
- Physics‐informed deep learning study for MHD particle‐fluid suspension flow with heat transfer in porous annular‐sector ductHeat Transfer, 2024
- Peristaltic pumping of convective nanofluid with magnetic field and thermal radiation in a porous channelCase Studies in Thermal Engineering, 2023
- Physics-informed deep learning for simultaneous surrogate modeling and PDE-constrained optimization of an airfoil geometryComputer Methods in Applied Mechanics and Engineering, 2023
- A comprehensive study of non-adaptive and residual-based adaptive sampling for physics-informed neural networksComputer Methods in Applied Mechanics and Engineering, 2022
- Scientific Machine Learning Through Physics–Informed Neural Networks: Where we are and What’s NextJournal of Scientific Computing, 2022
- Optimally weighted loss functions for solving PDEs with Neural NetworksJournal of Computational and Applied Mathematics, 2022
- Physics-informed neural networks (PINNs) for fluid mechanics: a reviewActa Mechanica Sinica, 2021
- Two-dimensional analytical investigation into energy conversion and efficiency maximization of magnetohydrodynamic swirling flow actuatorsEnergy, 2020
- Numerical simulation of the entrained flow hydropyrolysis of coal in magnetically rotating plasma reactorEnergy Conversion and Management, 2017