[论文解读] Exact imposition of boundary conditions with distance functions in physics-informed deep neural networks
本文提出一种物理信息深度神经网络方法,通过基于R-函数和平均值势场导出的近似距离函数,精确强制执行狄利克雷、诺伊曼和罗宾边界条件。通过将这些具备几何感知能力的函数嵌入网络的试解中,该方法消除了边界条件误差,仅依赖内部残差损失即可简化训练过程,并在复杂2D与4D区域上实现优于标准PINN的精度。
In this paper, we introduce a new approach based on distance fields to exactly impose boundary conditions in physics-informed deep neural networks. The challenges in satisfying Dirichlet boundary conditions in meshfree and particle methods are well-known. This issue is also pertinent in the development of physics informed neural networks (PINN) for the solution of partial differential equations. We introduce geometry-aware trial functions in artifical neural networks to improve the training in deep learning for partial differential equations. To this end, we use concepts from constructive solid geometry (R-functions) and generalized barycentric coordinates (mean value potential fields) to construct $\phi$, an approximate distance function to the boundary of a domain. To exactly impose homogeneous Dirichlet boundary conditions, the trial function is taken as $\phi$ multiplied by the PINN approximation, and its generalization via transfinite interpolation is used to a priori satisfy inhomogeneous Dirichlet (essential), Neumann (natural), and Robin boundary conditions on complex geometries. In doing so, we eliminate modeling error associated with the satisfaction of boundary conditions in a collocation method and ensure that kinematic admissibility is met pointwise in a Ritz method. We present numerical solutions for linear and nonlinear boundary-value problems over domains with affine and curved boundaries. Benchmark problems in 1D for linear elasticity, advection-diffusion, and beam bending; and in 2D for the Poisson equation, biharmonic equation, and the nonlinear Eikonal equation are considered. The approach extends to higher dimensions, and we showcase its use by solving a Poisson problem with homogeneous Dirichlet boundary conditions over the 4D hypercube. This study provides a pathway for meshfree analysis to be conducted on the exact geometry without domain discretization.
研究动机与目标
- 为解决物理信息神经网络(PINNs)在复杂几何上长期存在的边界条件强制不精确问题。
- 开发一种无网格、具备几何感知能力的方法,预先确保本质边界条件与自然边界条件的精确满足。
- 通过预先满足边界条件,消除边界损失项,从而仅依赖损失函数中的内部残差误差来简化PINN训练。
- 实现在精确几何上类似等几何分析的求解,无需域离散化或网格生成。
- 将该方法扩展至高维问题,包括4D超立方体,展示其可扩展性。
提出的方法
- 利用R-函数(通过R-等价复合)和平均值势场构建近似距离函数(ADFs),以表示到域边界的有符号距离。
- 基于倒距离权重的广义仿射插值,将ADFs推广至非齐次狄利克雷、诺伊曼和罗宾条件。
- 通过将PINN近似与ADFs相乘,精确施加边界条件,确保在Ritz方法中满足运动相容性,以及在配点法中逐点满足。
- 采用强形式配点法与Ritz最小化求解PDE,损失函数仅包含内部残差误差。
- 应用自动微分计算神经网络的高阶导数,以评估PDE残差。
- 通过R-等价构造超立方体上的ADFs,将该方法扩展至4D,实现对泊松方程的无网格求解。
实验结果
研究问题
- RQ1基于R-函数和平均值势场的近似距离函数,是否可用于在复杂几何上精确强制PINNs中的多样化边界条件?
- RQ2通过预先满足边界条件来消除边界损失项,是否能提升PINNs的训练效率与解的精度?
- RQ3该方法在非线性与高阶PDE(包括Eikonal方程与双调和方程)上的表现如何?
- RQ4该方法能否在不遭受维度灾难的情况下扩展至高维问题,如4D泊松方程?
- RQ5在精度与计算成本方面,基于R-等价与平均值势场的ADFs构造方式有何差异?
主要发现
- 所提方法在所有基准问题中,包括线性与非线性PDE,均持续优于标准PINN配点法的精度。
- 训练损失与PDE残差损失一致,因为边界条件已预先满足,无需加权边界损失项,从而改善收敛性。
- 在非凸域上的Eikonal方程求解中,R-等价ADFs的精度高于平均值势场ADFs,尽管后者在多边形边界中效率更高。
- 在4D超立方体上,该方法成功使用2–100–100–1网络求解了具有齐次狄利克雷条件的泊松方程,展示了向更高维度扩展的潜力。
- 基于R-函数与平均值势场的ADFs使无网格、类似等几何的仿真成为可能,可在精确几何上实现,无需域离散化。
- 该方法可在曲面及多连通域上实现鲁棒PDE求解,无需生成网格,且精确的边界强制显著提升了解的保真度。
更好的研究,从现在开始
从阅读论文到最终审阅,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。