Convolutional Neural Networks for the Localization of Plastic Velocity Gradient Tensor in Polycrystalline Microstructures

Convolutional Neural Networks for the Localization of Plastic Velocity Gradient Tensor in Polycrystalline Microstructures
复制标题

用于多晶微结构中塑性速度梯度张量定位的卷积神经网络

DOI:
10.1115/1.4051085
复制
发表时间:
2022
期刊:
Journal of Engineering Materials and Technology
影响因子:
--
通讯作者:
Kalidindi, Surya R.
Kalidindi, Surya R.
中科院分区:
--
文献类型:
--
作者:
Montes de Oca Zapiain, David;Shanker, Apaar;Kalidindi, Surya R.

文献摘要

参考文献

被引文献

相似文献

最近的工作已经证明了卷积神经网络(cnn)在产生低计算成本的替代模型来定位两相微观结构中的力学场方面的潜力。由于缺乏一种有效的形式来表示cnn输入通道中的晶格取向,阻碍了同样的cnn向多晶微结构的扩展。在本文中,我们展示了使用广义球面谐波(GSH)来解决这一挑战的好处。通过训练CNN模型,成功地预测了宏观加载条件下多晶微结构的局部塑性速度梯度场。具体来说,与直接使用Bunge-Euler角来表示输入通道中的晶体取向相比,该方法显著提高了CNN模型的精度。由于该方法隐含地满足了CNN输入微观结构规范中预期的晶体对称性,为采用CNN解决广泛的多晶微观结构设计和优化问题开辟了新的研究方向。
Recent work has demonstrated the potential of convolutional neural networks (CNNs) in producing low-computational cost surrogate models for the localization of mechanical fields in two-phase microstructures. The extension of the same CNNs to polycrystalline microstructures is hindered by the lack of an efficient formalism for the representation of the crystal lattice orientation in the input channels of the CNNs. In this paper, we demonstrate the benefits of using generalized spherical harmonics (GSH) for addressing this challenge. A CNN model was successfully trained to predict the local plastic velocity gradient fields in polycrystalline microstructures subjected to a macroscopically imposed loading condition. Specifically, it is demonstrated that the proposed approach improves significantly the accuracy of the CNN models when compared with the direct use of Bunge–Euler angles to represent the crystal orientations in the input channels. Since the proposed approach implicitly satisfies the expected crystal symmetries in the specification of the input microstructure to the CNN, it opens new research directions for the adoption of CNNs in addressing a broad range of polycrystalline microstructure design and optimization problems.
DOI: --
发表时间: 2006
期刊:
影响因子: --
作者:
G. Proust;S. Kalidindi
通讯作者: S. Kalidindi
DOI: 10.1016/j.actamat.2017.09.016
发表时间: 2017
期刊: Acta Materialia
影响因子: 9.4
作者:
David Montes Oca de Zapiain;E. Popova;S. Kalidindi
通讯作者: S. Kalidindi
DOI: 10.1016/j.ijplas.2007.05.002
发表时间: 2008
影响因子: 9.8
作者:
M. Knezevic;S. Kalidindi;R. Mishra
通讯作者: R. Mishra
DOI: 10.1088/1361-651x/ab37a5
发表时间: 2019
影响因子: 1.8
作者:
David Montes de Oca Zapiain;S. Kalidindi
通讯作者: S. Kalidindi
DOI: 10.1016/j.actamat.2006.12.010
发表时间: 2007
期刊: Acta Materialia
影响因子: 9.4
作者:
Xianping Wu;G. Proust;M. Knezevic;S. Kalidindi
通讯作者: S. Kalidindi