先进制造业知识服务平台
国家科技图书文献中心机械分馆  工信部产业技术基础公共服务平台  国家中小企业公共服务示范平台

MESH-BASED GRAPH CONVOLUTIONAL NEURAL NETWORKS FOR MODELING MATERIALS WITH MICROSTRUCTURE
参考中译:基于网格的图卷积神经网络在微结构材料建模中的应用


          

刊名:Journal of Machine Learning for Modeling and Computing
作者:Ari Frankel(Sandia National Laboratories)
Cosmin Safta(Sandia National Laboratories)
Coleman Alleman(Sandia National Laboratories)
Reese Jones(Sandia National Laboratories)
刊号:739B0373
ISSN:2689-3967
出版年:2022
年卷期:2022, vol.3, no.1
页码:1-30
总页数:30
分类号:TP181; TP3
关键词:Graph neural networkMaterial microstructureHomogenization
参考中译:图神经网络;材料微观结构;均质化
语种:eng
文摘:Predicting the evolution of a representative sample of a material with microstructure is a fundamental problem in homogenization. In this work we propose a graph convolutional neural network that utilizes the discretized representation of the initial microstructure directly, without segmentation or clustering. Compared to feature-based and pixel-based convolutional neural network models, the proposed method has a number of advantages: (a) it is deep in that it does not require featurization but can benefit from it, (b) it has a simple implementation with standard convolutional filters and layers, (c) it works natively on unstructured and structured grid data without interpolation (unlike pixel-based convolutional neural networks), and (d) it preserves rotational invariance like other graph-based convolutional neural networks. We demonstrate the performance of the proposed network and compare it to traditional pixel-based convolution neural network models and feature-based graph convolutional neural networks on multiple large datasets.
参考中译:预测具有微观结构材料的代表性样品的演化是均匀化中的一个基本问题。在这项工作中,我们提出了一种图卷积神经网络,它直接利用初始微结构的离散化表示,而不需要分割或聚类。与基于特征和基于像素的卷积神经网络模型相比,该方法具有许多优点:(A)它不需要特征化,但可以从中受益;(B)它具有标准的卷积过滤器和层的简单实现;(C)它无需内插即可处理非结构化和结构化的网格数据(不同于基于像素的卷积神经网络);(D)它像其他基于图的卷积神经网络一样保持旋转不变性。我们在多个大数据集上验证了该网络的性能,并与传统的基于像素的卷积神经网络模型和基于特征的图卷积神经网络进行了比较。