Structure-preserving Randomized Neural Networks for Incompressible Magnetohydrodynamics Equations

2026-03-01

AI Summary

This work addresses the challenge of efficiently solving the incompressible magnetohydrodynamics (MHD) equations, which are hindered by strong nonlinearities and dual divergence-free constraints that traditional numerical methods struggle to handle. The authors propose a structure-preserving randomized neural network (SP-RaNN), which uniquely integrates structure-preserving principles with randomized neural networks to automatically and exactly satisfy the divergence-free constraints within a unified space-time framework. By linearizing the governing equations via Picard or Newton iteration and discretizing them at collocation points using finite differences, the original problem is reformulated as a linear least-squares optimization, thereby avoiding non-convex training. Benchmark tests on Navier–Stokes, Maxwell, and MHD problems demonstrate that SP-RaNN significantly outperforms both conventional and deep learning-based methods in accuracy and convergence speed while rigorously preserving the underlying physical constraints.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Structured Learning
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The incompressible magnetohydrodynamic (MHD) equations are fundamental in many scientific and engineering applications. However, their strong nonlinearity and dual divergence-free constraints make them highly challenging for conventional numerical solvers. To overcome these difficulties, we propose a Structure-Preserving Randomized Neural Network (SP-RaNN) that automatically and exactly satisfies the divergence-free conditions. Unlike deep neural network (DNN) approaches that rely on expensive nonlinear and nonconvex optimization, SP-RaNN reformulates the training process into a linear least-squares system, thereby eliminating nonconvex optimization. The method linearizes the governing equations through Picard or Newton iterations, discretizes them at collocation points within the domain and on the boundaries using finite-difference schemes, and solves the resulting linear system via a linear least-squares procedure. By design, SP-RaNN preserves the intrinsic mathematical structure of the equations within a unified space-time framework, ensuring both stability and accuracy. Numerical experiments on the Navier-Stokes, Maxwell, and MHD equations demonstrate that SP-RaNN achieves higher accuracy, faster convergence, and exact enforcement of divergence-free constraints compared with both traditional numerical methods and DNN-based approaches. This structure-preserving framework provides an efficient and reliable tool for solving complex PDE systems while rigorously maintaining their underlying physical laws.

Problem

• incompressible magnetohydrodynamics
• divergence-free constraints
• nonlinear PDEs
• numerical solvers
• structure preservation

Innovation

• Structure-preserving
• Randomized Neural Networks
• Divergence-free constraints
• Linear least-squares
• Incompressible MHD