arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.06017cs.CE
收藏

HyperCAN:用于超材料的超网络驱动深度参数化本构模型

HyperCAN: Hypernetwork-Driven Deep Parameterized Constitutive Models for Metamaterials

Li Zheng, Dennis M. Kochmann, Siddhant Kumar

AI总结:

提出 HyperCAN 框架,通过超网络动态生成遵循力学原理的凸本构神经网络,实现未见桁架超材料与加载场景的高精度预测,并支持低成本多尺度仿真与优化。

摘要:

我们提出 HyperCAN,这是一个机器学习框架,利用超网络为多种在有限变形下表现出不同力学行为的梁基超材料构建可适应的本构人工神经网络。HyperCAN 集成了一个输入凸网络,用于建模桁架晶格的非线性应力-应变映射,同时确保遵循基本力学原理;该框架还包含一个超网络,可根据晶格拓扑和几何形状动态调整凸网络的参数。这一统一框架在预测训练域之外、此前未见过的超材料设计和加载场景的力学行为方面表现出稳健的泛化能力。我们展示了如何将 HyperCAN 集成到多尺度仿真中,以准确捕捉大规模桁架超材料的高度非线性响应,其结果与完全解析仿真高度吻合,同时显著降低计算成本。这为桁架超材料的多尺度设计和优化提供了新的高效途径。

英文摘要:

We introduce HyperCAN, a machine learning framework that utilizes hypernetworks to construct adaptable constitutive artificial neural networks for a wide range of beam-based metamaterials exhibiting diverse mechanical behavior under finite deformations. HyperCAN integrates an input convex network that models the nonlinear stress-strain map of a truss lattice, while ensuring adherence to fundamental mechanics principles, along with a hypernetwork that dynamically adjusts the parameters of the convex network as a function of the lattice topology and geometry. This unified framework demonstrates robust generalization in predicting the mechanical behavior of previously unseen metamaterial designs and loading scenarios well beyond the training domain. We show how HyperCAN can be integrated into multiscale simulations to accurately capture the highly nonlinear responses of large-scale truss metamaterials, closely matching fully resolved simulations while significantly reducing computational costs. This offers new efficient opportunities for the multiscale design and optimization of truss metamaterials.

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。

↑