arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.08363cond-mat.mtrl-scics.LG
收藏

用于速率和温度相关塑性建模的物理信息神经网络

Physics-informed neural networks for modeling rate- and temperature-dependent plasticity

Advanced Micro Devices (AMD)(超威半导体(AMD));Siemens Technology(西门子科技)

Rajat Arora, Pratik Kakkar, Biswadip Dey, Amit Chakraborty

摘要:

这项工作提出了一个物理信息神经网络(PINN)为基础的框架来模拟的应变率和温度依赖性的变形场的弹粘塑性固体。为了避免训练过程中不平衡的反向传播梯度,所提出的框架使用了一种简单的策略,没有增加计算复杂性,用于选择标量权重,以平衡基于物理的损失函数中不同项之间的相互作用。此外,我们强调了一个基本的挑战,涉及选择适当的模型输出,使机械问题可以忠实地解决使用基于PINN的方法。我们证明了这种方法的有效性,通过研究两个测试问题建模在不同的应变速率和温度下,分别在固体中的弹粘塑性变形。我们的研究结果表明,所提出的PINN为基础的方法可以准确地预测在弹粘塑性材料的变形的时空演化。

英文摘要:

This work presents a physics-informed neural network (PINN) based framework to model the strain-rate and temperature dependence of the deformation fields in elastic-viscoplastic solids. To avoid unbalanced back-propagated gradients during training, the proposed framework uses a simple strategy with no added computational complexity for selecting scalar weights that balance the interplay between different terms in the physics-based loss function. In addition, we highlight a fundamental challenge involving the selection of appropriate model outputs so that the mechanical problem can be faithfully solved using a PINN-based approach. We demonstrate the effectiveness of this approach by studying two test problems modeling the elastic-viscoplastic deformation in solids at different strain rates and temperatures, respectively. Our results show that the proposed PINN-based approach can accurately predict the spatio-temporal evolution of deformation in elastic-viscoplastic materials.

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。

↑