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 2606.25075physics.flu-dyncs.NAmath.NA
收藏

求解器精确性,学习灵活性:斯托克斯流的等变边界校正算子

Solver Exactness, Learned Flexibility: Equivariant Boundary-Correction Operators for Stokes Flow

Direction Scientifique Générale, ONERA, Institut Polytechnique de Paris(巴黎理工学院,ONERA,总科学方向)

Denis Gueyffier

AI总结:

针对粘性斯托克斯流中物体阻力和迁移率问题,提出将精确求解器与学习结合的方法:固定已知的椭圆核心(等变斯托克斯流),仅学习边界校正部分,实现高精度、高数据效率的求解。

摘要:

粘性(斯托克斯)流中物体的阻力和迁移率控制着形状设计、悬浮或微生物游泳等问题。经典求解器能精确但昂贵地计算它们;纯学习替代模型速度快但在训练数据外不可靠。我们将两者结合:求解器对解算子中已知闭形式部分的精确性,以及学习对未知部分的能力。对于不可压缩斯托克斯流,椭圆核心核已知:在自由空间中,Leray投影是一个无自由参数的单一旋转等变斯托克斯流,基于它的边界积分求解器在$O(N)$下精确到机器精度。唯一没有闭形式的是边界校正。我们拆分算子:精确且等变地固定核心,仅学习该校正,作为良态的第二类算子。在精确求解为真值的斯托克斯测试平台上,拆分给出了一个工作求解器(端到端$2 \times 10^{-3}$,数据效率比黑箱DeepONet高$5$-$16$倍),并推翻了三个预期。(i) 条件数不是瓶颈:条件数为$10^{16}$的第一类算子和有界第二类算子给出相同误差。(ii) 跨形状泛化由描述符的等变性而非容量控制:非不变描述符在旋转下退化超过$10^5$倍,而规范化恢复接近机器的迁移。(iii) 覆盖而非表达能力是关键;局部等变核消除了严重的分布外尾部,将最坏情况内部误差从$O(10)$降至$\sim 10^{-7}$。然后我们打开了3D中的中心外部问题:通过扩展求积精确化的完备双层势,是第二类良态且$SO(3)$-等变的,再现了球体和椭球体的解析阻力,并可在多个物体间组合。

英文摘要:

Computing the viscous Stokes flow around a shape requires solving a boundary-integral equation, and for a new shape the solve must begin from scratch. Learned operators promise to spread this cost across shapes, but it is not clear what such an operator retains of the solver it replaces, or what determines whether it transfers to shapes it was not trained on. We make both questions answerable by choosing a problem which is exactly solvable except for a single term: a second-kind boundary-integral problem is solved exactly using a kernel-independent fast summation, while the boundary correction, which has no closed form, is learned. The solver's guarantees carry over unchanged: exactness on the closed-form part, $O(N)$ scaling, $SO(3)$-equivariance to machine precision, and an $O(N)$ differentiable adjoint. We then make precise what the learning contributes. It does not contribute to accuracy, differentiability, or scaling $O(N)$, all of which are provided by the solver. Learning contributes a one-time cost in that the forward map is trained once and then evaluated on a new shape in a single pass rather than resolved. Measured against baselines, the learned map is $5$ to $16\times$ more data-efficient than a black-box DeepONet and maintains a $\sim\!2.5\times$ lower in-distribution error than a geometry-aware operator, although that operator is stronger in the low-data limit and the learned map is less reliable out of distribution. We trace this fragility to the global parameterization and reduce it with a local equivariant kernel. The exactly-solvable setting yields clarity about the mechanism: geometric generalization is governed by invariance and coverage, not by conditioning or by capacity.

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。

↑