Fuse-PINN:结合有限元方法与物理信息神经网络实现大规模并行仿真
Fuse-PINN: Combining Finite Element Methods and Physics-Informed Neural Networks to enable massively parallel simulations of non-linear PDEs
做科学计算或数值仿真的同学可以看看:PINN 一直被吐槽没法在 HPC 上并行扩展,这个框架用有限元公式解决了这个问题,还在磁约束聚变的非线性模型上跑出了接近线性的多 GPU 扩展。如果你在搞聚变、流体或任何非线性 PDE 仿真,值得对照传统 FEM 代码试试。
Fraunhofer 等机构的研究团队发布 Fuse-PINN 框架,将有限元方法(FEM)与物理信息神经网络(PINN)结合,提出 FEM-NN 的数学化公式,使 PINN 能够在 GPU 高性能计算集群上大规模并行运行。
框架内置 Energy Natural Gradient Descent 优化器以实现高精度收敛,并在磁约束聚变相关物理模型上验证,包括具有细尺度动力学的非线性对流模型。多 GPU 测试中,随着问题规模扩大,系统达到接近完美的线性扩展,回应了社区中“PINN 无法扩展”的普遍质疑。
此前多数 PINN 研究仅停留在简单物理方程、少变量和短时间尺度的玩具模型上,难以处理大空间域中的湍流动力学。Fuse-PINN 的模块化设计为工业级非线性 PDE 仿真提供了新路径,对聚变研究等依赖大规模数值模拟的领域具有直接参考价值。
Fuse-PINN: Combining Finite Element Methods and Physics-Informed Neural Networks to enable massively parallel simulations of non-linear PDEs
Research in the domain of Physics-Informed Neural Networks applied to PDE modelling has advanced significantly in recent years, providing a wide ecosystem of novel methods. However, one frequent limitation is the inability of PINNs to scale out on High-Performance Computing architectures to address more ambitious challenges, particularly non-linear physics models with turbulent dynamics in large spatial domains. Typical studies restrain demonstrations to toy models with simple physics equations, few variables, and rarely any complex non-linear dynamics evolved over long timescales. Part of the AI community has even adopted the idea that "PINNs don't scale". This work proves otherwise. We present a mathematically robust formulation of Finite-Element-Method for Neural Networks (FEM-NN) implemented into a comprehensive, modular framework: Fuse-PINN. This formulation provides the basis for a sclable parallelisation of Physics-Informed Neural Networks on GPU-based HPC systems. Furthermore, an Energy Natural Gradient Descent optimiser is implemented to allow high-precision convergence. Fuse-PINN is demonstrated on physics models relevant to Magnetic Confinement Fusion, including non-linear convective models with fine-scale dynamics. Near-perfect scaling is achieved on multi-GPU runs with increasing problem size.
本条情报归属 AITOP「论文」核心栏目,重点聚焦欧洲人工智能治理与技术生态。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:Fuse-PINN、PINN、有限元方法、HPC并行计算,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始线索采编自「arXiv cs.LG」(@Stanislas Pamela, Nicolas Pailliez, Emmanuel Franck, Victor Michel-Dansac, Laurent Navoret, Vignesh Gopakumar),经 AITOP 多维评分管线结构化提炼。