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 2606.02475math.NAcs.CEcs.LGcs.NA
收藏

面向有限差分PDE求解器中自适应网格细化的物理信息残差

Physics-Informed Residuals for Adaptive Mesh Refinement in Finite-Difference PDE Solvers

Department of Mathematics, Makerere University(数学系,Makerere大学);Department of Mathematics, Kabale University(数学系,Kabale大学)

Henry Kasumba, Ronald Katende

AI总结:

提出利用物理信息神经网络(PINN)作为离网格残差探针,为有限差分求解器提供自适应网格细化指示,在粘性Burgers方程等基准测试中验证了其有效性。

摘要:

经典有限差分求解器仍是偏微分方程的可靠工具,但其效率取决于网格分辨率的放置位置。当求解困难集中在尖锐梯度、前沿、振荡或约束敏感区域附近时,均匀细化可能浪费自由度。本文研究了一种混合策略,其中物理信息神经网络(PINN)不作为最终求解器,而是作为自适应网格细化的离网格残差探针。PINN残差在域内采样,转换为单元指示器,并在最终近似由有限差分求解器计算之前指导细化。该方法在三个基准测试上进行了评估。主要的全求解器验证使用一维粘性Burgers方程,在自适应网格上进行非均匀有限差分求解。PINN阈值细化在60个自由度下达到最终相对$L^2$误差0.021067,而均匀细化在192个自由度下为0.022617。在匹配网格大小时,PINN阈值将误差降低了约67.5%。PINN-Dörfler细化性能类似,使用58个自由度时误差为0.021264。梯度指示器仍略精确,因此结果支持有用性而非普遍优越性。基于非线性薛定谔方程和不可压缩Navier-Stokes系统的二维和三维代理测试表明,PINN残差可以组织结构化细化并优于随机细化,尽管它们并不始终优于梯度或均匀基线。结果支持PINN引导的AMR作为一种残差指示器策略,将物理信息诊断信息传递到有限差分网格自适应中,同时保留经典求解器作为最终近似引擎。

英文摘要:

Classical finite-difference solvers remain reliable tools for partial differential equations, but their efficiency depends on where mesh resolution is placed. Uniform refinement can waste degrees of freedom when solution difficulty is localised near sharp gradients, fronts, oscillations, or constraint-sensitive regions. This paper studies a hybrid strategy in which a physics-informed neural network (PINN) is used not as the final solver, but as an off-grid residual probe for adaptive mesh refinement. The PINN residual is sampled over the domain, converted into cellwise indicators, and used to guide refinement before the final approximation is computed by a finite-difference solver. The method is evaluated on three benchmarks. The main full-solver validation uses the one-dimensional viscous Burgers equation with a nonuniform finite-difference solve on the adapted meshes. PINN-threshold refinement attains final relative $L^2$ error $0.021067$ with $60$ degrees of freedom, compared with $0.022617$ for uniform refinement with $192$ degrees of freedom. At matched mesh size, PINN-threshold reduces the error by about $67.5\%$. PINN-Dörfler refinement gives similar performance, with error $0.021264$ using $58$ degrees of freedom. A gradient indicator remains slightly more accurate, so the result supports usefulness rather than universal superiority. Manufactured 2D and 3D proxy tests, based on a nonlinear Schrödinger equation and an incompressible Navier--Stokes system, show that PINN residuals can organise structured refinement and improve over random refinement, although they do not consistently outperform gradient or uniform baselines. The results support PINN-guided AMR as a residual-indicator strategy for transferring physics-informed diagnostic information into finite-difference mesh adaptation while preserving the classical solver as the final approximation engine.

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。

↑