Geom-DeepONet:一种用于三维参数化几何体场预测的基于点云的深度算子网络
Geom-DeepONet: A Point-cloud-based Deep Operator Network for Field Predictions on 3D Parameterized Geometries
AI总结:
本文提出 Geom-DeepONet,通过点云坐标、有符号距离函数和 SIREN 编码参数化三维几何,实现任意节点全场预测,并在精度、泛化和推理速度上优于 PointNet 与原始 DeepONet。
摘要:
现代数字工程设计过程通常涉及在不断变化的三维(3D)几何体上进行昂贵的重复仿真。神经网络(NNs)的高效预测能力使其成为提供设计洞见的合适代理模型。然而,现有神经网络很少能够处理变化三维形状上的解预测。我们提出了一种名为 Geom-DeepONet 的新型深度算子网络(DeepONet)变体,它对参数化三维几何体进行编码,并预测任意数量节点上的全场解。据作者所知,这是文献中的首次尝试,也是我们的主要创新点。除了使用网格坐标表示形状外,还计算每个节点的有符号距离函数,并将其用于增强 Geom-DeepONet 的 trunk 网络输入,从而同时捕捉三维形状的显式和隐式表示。研究还利用正弦表示网络(SIREN)强大的几何编码能力,用 SIREN 替换 trunk 中经典的前馈神经网络。branch 网络与 trunk 网络之间通过逐元素乘积引入额外的数据融合。开展了数值基准测试,将 Geom-DeepONet 与 PointNet 和原始 DeepONet 进行比较;结果表明,我们的架构训练速度快、内存占用小,并在三者中给出最准确的结果,应力误差小于 2 MPa。结果显示,与原始 DeepONet 相比,我们的架构在未见过的非相似设计上具有低得多的泛化误差。模型一经训练即可预测向量解;对于大型网格,其速度可比隐式有限元仿真快 10^5 倍以上。
英文摘要:
Modern digital engineering design process commonly involves expensive repeated simulations on varying three-dimensional (3D) geometries. The efficient prediction capability of neural networks (NNs) makes them a suitable surrogate to provide design insights. Nevertheless, few available NNs can handle solution prediction on varying 3D shapes. We present a novel deep operator network (DeepONet) variant called Geom-DeepONet, which encodes parameterized 3D geometries and predicts full-field solutions on an arbitrary number of nodes. To the best of the authors' knowledge, this is the first attempt in the literature and is our primary novelty. In addition to expressing shapes using mesh coordinates, the signed distance function for each node is evaluated and used to augment the inputs to the trunk network of the Geom-DeepONet, thereby capturing both explicit and implicit representations of the 3D shapes. The powerful geometric encoding capability of a sinusoidal representation network (SIREN) is also exploited by replacing the classical feedforward neural networks in the trunk with SIREN. Additional data fusion between the branch and trunk networks is introduced by an element-wise product. A numerical benchmark was conducted to compare Geom-DeepONet to PointNet and vanilla DeepONet, where results show that our architecture trains fast with a small memory footprint and yields the most accurate results among the three with less than 2 MPa stress error. Results show a much lower generalization error of our architecture on unseen dissimilar designs than vanilla DeepONet. Once trained, the model can predict vector solutions, and speed can be over $10^5$ times faster than implicit finite element simulations for large meshes.
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。