GFocal:一种用于求解任意几何形状上偏微分方程的全局-焦点神经算子
GFocal: A Global-Focal Neural Operator for Solving PDEs on Arbitrary Geometries
AI总结:
针对现有偏微分方程神经算子忽略局部细节与全局特征协同学习的问题,提出GFocal方法,通过全局、焦点模块结合卷积门控融合多尺度信息,在多数基准上取得SOTA,适配任意几何与工业仿真。
摘要:
基于Transformer的神经算子凭借Transformer在捕捉长程依赖和全局关联方面的有效性——这一点已在语言建模中得到充分验证——已成为颇具前景的偏微分方程代理求解器。然而,现有方法忽略了局部物理细节与全局特征之间相互依赖关系的协同学习,而这种协同学习对于解决多尺度问题、在长期推演中保持物理一致性和数值稳定性,以及准确捕捉过渡动力学至关重要。在本研究中,我们提出了GFocal,这是一种基于Transformer的神经算子方法,可强制实现全局与局部特征的同步学习与融合。该方法通过基于Nyström注意力的全局(global)模块和基于切片的焦点(focal)模块分别利用全局关联和局部特征,生成具备物理感知的令牌,随后通过基于卷积的门控模块进行调制与整合,实现多尺度信息的动态融合。GFocal能够在任意几何形状和初始条件下,实现对物理特征的精准建模与预测。实验表明,GFocal在六个基准测试中的五个上取得了当前最优性能,相对增益平均达15.2%,并且在汽车空气动力学模拟、翼型空气动力学模拟等工业级仿真任务中表现出色。
英文摘要:
Transformer-based neural operators have emerged as promising surrogate solvers for partial differential equations, by leveraging the effectiveness of Transformers for capturing long-range dependencies and global correlations, profoundly proven in language modeling. However, existing methodologies overlook the coordinated learning of interdependencies between local physical details and global features, which are essential for tackling multiscale problems, preserving physical consistency and numerical stability in long-term rollouts, and accurately capturing transitional dynamics. In this work, we propose GFocal, a Transformer-based neural operator method that enforces simultaneous global and local feature learning and fusion. Global correlations and local features are harnessed through Nyström attention-based \textbf{g}lobal blocks and slices-based \textbf{focal} blocks to generate physics-aware tokens, subsequently modulated and integrated via convolution-based gating blocks, enabling dynamic fusion of multiscale information. GFocal achieves accurate modeling and prediction of physical features given arbitrary geometries and initial conditions. Experiments show that GFocal achieves state-of-the-art performance with an average 15.2\% relative gain in five out of six benchmarks and also excels in industry-scale simulations such as aerodynamics simulation of automotives and airfoils.
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。