arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2606.08796cs.CE
收藏

不规则区域固体力学的一种非重叠Schwarz混合有限元-神经算子框架

A Non-Overlapping Schwarz Hybrid Finite Element-Neural Operator Framework for Solid Mechanics on Irregular Domains

The Hong Kong Polytechnic University(香港理工大学);Johns Hopkins University(约翰斯·霍普金斯大学);Vanderbilt University(范德堡大学);PolyU-Daya Bay Technology and Innovation Research Institute(港大-大亚湾技术与创新研究院)

Wei Wang, Abhinav Gupta, Haihui Ruan, Somdatta Goswami

AI总结:

提出非重叠Schwarz交替法结合Neumann-Dirichlet界面交换,消除重叠层并减少内迭代;Point-DeepONet处理不规则几何,从位移算子解析导出应变应力算子,降低参数量并保证力学一致性。

摘要:

有限元方法是固体力学仿真的基准,但对于局部非线性、细尺度特征或长时间动态演化问题,其计算成本变得过高。在我们早期的有限元-神经算子混合框架[1]中,通过具有Dirichlet-Dirichlet界面交换的重叠区域分解,将物理信息深度算子网络与有限元求解器耦合,加速了密集子域同时保持其他区域的有限元保真度。仍存在两个限制:重叠公式需要冗余的界面计算,增加了内Schwarz迭代次数;卷积特征提取器将神经算子子域限制在结构化网格上,排除了不规则几何。本文采用具有Neumann-Dirichlet界面交换的非重叠Schwarz交替方法替代,将牵引力从神经算子传递到有限元而非位移。这消除了重叠层并减少了内Schwarz迭代,同时在所有测试时间范围内保持有界误差累积。对于任意形状的子域,Point-DeepONet在非结构化有限元点云上运行而无需插值,将其扩展到非凸和不规则几何。应变和应力算子通过运动学方程从位移算子解析导出,而非作为独立网络,从而减少可训练参数集并通过构造强制执行力学一致性。该框架在三个基准上得到验证:静态线弹性、准静态超弹性和具有规则及不规则几何的弹性动力学。这些结果建立了一种几何灵活、参数高效且收敛稳定的非重叠有限元-神经算子耦合范式,为大规模动态固体力学中基于物理和算子学习的混合求解器提供了途径。

英文摘要:

Finite element (FE) methods are the benchmark for solid mechanics simulations, yet their computational cost becomes prohibitive for problems with localised nonlinearities, fine-scale features, or long-time dynamic evolution. In our earlier FE-neural operator (FE-NO) hybrid framework [1], physics-informed deep operator networks were coupled with FE solvers through overlapping domain decomposition with Dirichlet-Dirichlet interface exchange, accelerating intensive subdomains while preserving FE fidelity elsewhere. Two limitations remained: the overlapping formulation required redundant interface computations that increased inner Schwarz iteration counts, and the convolutional feature extractor restricted the NO subdomain to structured grids, precluding irregular geometries. A non-overlapping Schwarz alternating method with Neumann-Dirichlet interface exchange replaces it, transmitting traction from the NO to FE rather than displacement. This eliminates the overlap layer and reduces inner Schwarz iterations while maintaining bounded error accumulation across all tested time horizons. For arbitrarily shaped subdomains, a Point-DeepONet operates on unstructured FE point clouds without interpolation, extending it to non-convex and irregular geometries. Strain and stress operators are derived analytically from the displacement operators via kinematic equations, rather than as independent networks, reducing trainable parameter sets while enforcing mechanical consistency by construction. The framework is validated on three benchmarks: static linear elasticity, quasi-static hyperelasticity, and elastodynamics with regular and irregular geometries. These results establish a non-overlapping FE-NO coupling paradigm that is geometry-flexible, parameter-efficient, and convergence-stable, providing a pathway for hybrid physics-based and operator-learning solvers in large-scale dynamic solid mechanics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑