PulseAugur
中
实时 10:52:39
English(EN) MR-GVNO: A Geometry-Aware Variational Physics-Informed Neural Operator for Mindlin-Reissner Plates on Irregular Domains

新型神经网络算子MR-GVNO加速板响应预测

作者 PulseAugur 编辑部 · [2 个来源] ·

研究人员开发了MR-GVNO，这是一种新颖的几何感知变分神经网络算子，旨在加速不规则域上Mindlin-Reissner板的响应预测。该方法利用边界点云表示复杂几何形状，并通过交叉注意力机制整合各种输入场。MR-GVNO使用源自总势能的物理信息损失进行训练，可实现快速的全场推理，并在不同板形状和载荷条件下表现出强大的泛化能力，在计算成本方面显著优于传统的有限元方法。 AI

影响 通过实现复杂板结构毫秒级全场推理，加速工程模拟。

排序理由 该集群包含一篇发表在arXiv上的研究论文，详细介绍了一种新的板分析方法。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Siqi Wang, Daobo Sun, Yizheng Wang, Yilong Zhang, Yabin Jin, Xiaoying Zhuang, Timon Rabczuk ·

    MR-GVNO: A Geometry-Aware Variational Physics-Informed Neural Operator for Mindlin-Reissner Plates on Irregular Domains

    arXiv:2606.16624v1 Announce Type: new Abstract: Plate and shell structures are widely used in engineering, making rapid response prediction under varying geometries, materials, and loads highly desirable. However, conventional finite element methods require repeated modeling and …

  2. arXiv cs.AI TIER_1 English(EN) · Timon Rabczuk ·

    MR-GVNO: A Geometry-Aware Variational Physics-Informed Neural Operator for Mindlin-Reissner Plates on Irregular Domains

    Plate and shell structures are widely used in engineering, making rapid response prediction under varying geometries, materials, and loads highly desirable. However, conventional finite element methods require repeated modeling and solution, resulting in high computational costs.…

相关实体

相关话题