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 2203.09789cs.LGcs.CE
收藏

使用物理学信息的深度学习表征和发现本构模型

Constitutive model characterization and discovery using physics-informed deep learning

University of British Columbia(不列颠哥伦比亚大学)

Ehsan Haghighat, Sahar Abouali, Reza Vaziri

摘要:

传统上,材料的力学响应是通过本构模型来描述的,通常是以约束常微分方程的形式。这些模型的参数数量非常有限,但它们在再现实验中观察到的复杂响应方面非常有效。此外,在其离散形式中,它们在计算上非常有效,通常导致简单的代数关系,因此它们已被广泛用于大型显式和隐式有限元模型中。然而,它是非常具有挑战性的,制定新的本构模型,特别是具有复杂的微观结构的材料,如复合材料。本构建模的最近趋势是利用复杂的神经网络架构来构建本构模型尚不存在的复杂材料响应。虽然非常准确,但有两个缺点。首先,它们是插值模型,通常外推效果不佳。其次,由于其复杂的结构和众多的参数,它们是低效的,被用作一个大规模的有限元模型内的本构模型。在这项研究中,我们提出了一种新的方法的基础上的物理知识的学习机的表征和发现的本构模型。与数据驱动的本构模型不同,我们利用弹塑性理论的基础作为总损失函数中的正则化项,以找到理论上合理的参数本构模型。我们证明,我们提出的框架可以有效地识别底层的本构模型描述不同的数据集从冯米塞斯家庭。

英文摘要:

Classically, the mechanical response of materials is described through constitutive models, often in the form of constrained ordinary differential equations. These models have a very limited number of parameters, yet, they are extremely efficient in reproducing complex responses observed in experiments. Additionally, in their discretized form, they are computationally very efficient, often resulting in a simple algebraic relation, and therefore they have been extensively used within large-scale explicit and implicit finite element models. However, it is very challenging to formulate new constitutive models, particularly for materials with complex microstructures such as composites. A recent trend in constitutive modeling leverages complex neural network architectures to construct complex material responses where a constitutive model does not yet exist. Whilst very accurate, they suffer from two deficiencies. First, they are interpolation models and often do poorly in extrapolation. Second, due to their complex architecture and numerous parameters, they are inefficient to be used as a constitutive model within a large-scale finite element model. In this study, we propose a novel approach based on the physics-informed learning machines for the characterization and discovery of constitutive models. Unlike data-driven constitutive models, we leverage foundations of elastoplasticity theory as regularization terms in the total loss function to find parametric constitutive models that are also theoretically sound. We demonstrate that our proposed framework can efficiently identify the underlying constitutive model describing different datasets from the von Mises family.

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。

↑