arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.05583cond-mat.mtrl-sci
收藏

用于预测多晶材料有效性质的图神经网络:综合分析

Graph Neural Network for Predicting the Effective Properties of Polycrystalline Materials: A Comprehensive Analysis

Minyi Dai, Mehmet F. Demirel, Xuanhan Liu, Yingyu Liang, Jia-Mian Hu

AI总结:

本文提出 PGNN 图神经网络,基于逾5000个三维多晶微结构高通量数据预测 Li7La3Zr2O12 的电导率与弹性质,误差低于1.4%,并分析特征重要性、外推及迁移学习。

摘要:

我们开发了一种多晶图神经网络(PGNN)模型,用于预测多晶材料的有效性质,并以 Li7La3Zr2O12 陶瓷为例。通过 Voronoi 镶嵌以及对电子背散射衍射图像进行处理,我们生成了一个包含超过5000种具有有限宽度晶界的不同三维多晶微结构的大规模数据集。这些微结构的有效离子电导率和弹性刚度系数通过基于物理的高通量模拟计算得到。经优化的 PGNN 模型在预测有效 Li 离子电导率矩阵的全部三个对角分量时实现了低于1.4%的低误差,优于一个线性回归模型和两个基准卷积神经网络模型。顺序前向选择方法被用于量化选择单个晶粒(晶界)特征对提高性质预测精度的相对重要性,由此可以确定关键的和不需要的节点(边)特征。本文还研究了训练后 PGNN 模型的外推性能。通过使用为预测电导率而预训练的 PGNN 模型来预测同一组微结构的弹性质,本文评估了迁移学习性能。

英文摘要:

We develop a polycrystal graph neural network (PGNN) model for predicting the effective properties of polycrystalline materials, using the Li7La3Zr2O12 ceramic as an example. A large-scale dataset with >5000 different three-dimensional polycrystalline microstructures of finite-width grain boundary is generated by Voronoi tessellation and processing of the electron backscatter diffraction images. The effective ion conductivities and elastic stiffness coefficients of these microstructures are calculated by high-throughput physics-based simulations. The optimized PGNN model achieves a low error of <1.4% in predicting all three diagonal components of the effective Li-ion conductivity matrix, outperforming a linear regression model and two baseline convolutional neural network models. Sequential forward selection method is used to quantify the relative importance of selecting individual grain (boundary) features to improving the property prediction accuracy, through which both the critical and unwanted node (edge) feature can be determined. The extrapolation performance of the trained PGNN model is also investigated. The transfer learning performance is evaluated by using the PGNN model pretrained for predicting conductivities to predict the elastic properties of the same set of microstructures.

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。

↑