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 2606.16624cs.AI
收藏

MR-GVNO:一种面向不规则域上Mindlin-Reissner板的几何感知变分物理信息神经算子

GA-VINO: A Geometry-Aware Variational Physics-informed Neural Operator for Mindlin-Reissner Plates

Institute of Computational Mechanics × AI & College of Intelligent Robotics and Advanced Manufacturing, Fudan University(计算力学与人工智能学院及智能机器人与先进制造学院,复旦大学);School of Aerospace Engineering, Xiamen University(航空航天工程学院,厦门大学);Department of Engineering Mechanics, Tsinghua University(工程力学系,清华大学);Institute of Photonics, Department of Mathematics and Physics, Leibniz University(光子研究所,数学与物理系,莱比锡大学);Institute of Structural Mechanics, Bauhaus-Universität Weimar(结构力学研究所,魏玛 Bauhaus-Universität)

Siqi Wang, Daobo Sun, Yizheng Wang, Yilong Zhang, Yabin Jin, Xiaoying Zhuang, Timon Rabczuk

AI总结:

提出MR-GVNO,一种几何感知变分神经算子,通过边界点云表示不规则几何,利用交叉注意力机制融合多物理场输入,基于离散总势能的变分物理信息损失无监督训练,实现对Mindlin-Reissner板问题的快速准确预测。

摘要:

板壳结构在工程中广泛应用,因此在不同几何、材料和载荷下进行快速响应预测非常理想。然而,传统的有限元方法需要重复建模和求解,导致计算成本高昂。本研究提出了一种用于Mindlin-Reissner板问题的几何感知变分神经算子,称为MR-GVNO。该方法使用边界点云表示不规则几何,并采用独立的编码器处理空间变化的材料场、压力载荷和标量物理参数。交叉注意力机制将这些输入与查询点信息集成,以预测任意位置的横向挠度和转角。MR-GVNO无需标记解数据,通过从离散总势能导出的变分物理信息损失进行训练。它直接处理不规则点云,并允许不同的物理场独立离散化,避免了插值到公共网格。在单孔、双孔和L形板上的数值实验表明,在均匀和非均匀材料以及均匀和随机载荷下,该方法能准确预测响应。该模型还实现了毫秒级的全场推理和良好的跨几何泛化能力。

英文摘要:

Plate and shell structures are widely used in engineering fields. Rapid response prediction for such structures under complex geometries, heterogeneous materials, and varying loads is important for engineering design, but conventional numerical methods usually require repeated modeling and solution when the physical configuration changes. To address this issue, this study proposes a geometry-aware variational physics-informed neural operator (GA-VINO) for Mindlin-Reissner plates. GA-VINO represents the plate geometry using boundary point clouds and incorporates a material encoder, a load encoder, and a scalar-parameter branch to handle spatially random material fields, spatially varying pressure loads, and sample-level uniform parameters. Through multi-branch point cloud encoding and cross-attention, GA-VINO fuses geometric, material, loading, and query point information, and predicts the transverse deflection and rotations at arbitrary query locations. Unlike conventional data-driven neural operators, GA-VINO requires no labeled solution data during training. Instead, it minimizes a variational physics-informed loss constructed from the discretized total potential energy of the Mindlin-Reissner plate. Compared with grid-based neural operators, GA-VINO directly processes irregular point clouds and allows different physical fields to be discretized on different point sets, avoiding forced interpolation onto a common grid. The method is validated on multiple examples involving different geometries, material fields, and load distributions. The results show that GA-VINO achieves promising accuracy in deflection, rotation, gradient-sensitive, and energy-based metrics, completes full-field inference for new samples within milliseconds, and exhibits promising cross-geometry generalization capability.

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。

↑