arXiv cs.AI· Siqi Wang, Daobo Sun, Yizheng Wang, Yilong Zhang, Yabin Jin, Xiaoying Zhuang, Timon Rabczuk·· 10 小时前AI 评分18
GA-VINO:面向 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
AI 导读
研究提出几何感知变分物理信息神经算子 GA-VINO,用于 Mindlin-Reissner 板的快速响应预测。该方法以边界点云表示板几何,结合材料编码器、载荷编码器与标量参数分支,通过多分支点云编码和交叉注意力融合几何、材料、载荷与查询点信息,训练时无需标注解数据,仅最小化由离散总势能构造的变分物理信息损失。在新样本上可在毫秒级完成全场推理,并展现出跨几何泛化能力。
正文 · 原文
Abstract: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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.16624 [cs.AI] |
| (or arXiv:2606.16624v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.16624 arXiv-issued DOI via DataCite |
Submission history
From: Siqi Wang [view email]
[v1]
Mon, 15 Jun 2026 12:18:56 UTC (2,602 KB)
[v2]
Fri, 17 Jul 2026 02:33:27 UTC (3,326 KB)
[v3]
Wed, 18 Nov 2026 14:39:44 UTC (6,043 KB)
来源:arXiv cs.AI · arxiv.org