Development of a Robust CNN Model for Capturing Microstructure-Property Linkages and Building Property Closures Supporting Material Design

Development of a Robust CNN Model for Capturing Microstructure-Property Linkages and Building Property Closures Supporting Material Design
复制标题

DOI:
10.3389/fmats.2022.851085
复制
发表时间:
2022-03-11
影响因子:
3.2
通讯作者:
Kalidindi, Surya R.
Kalidindi, Surya R.
中科院分区:
材料科学3区
文献类型:
--
作者:
Mann, Andrew;Kalidindi, Surya R.

文献摘要

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)用于捕获高对比度复合材料系统中高度非线性的微观结构-性能联系的可行性。在这项工作中,我们开发了一种新的CNN架构,与当前文献中的基准相比,该架构使用了大量减少的可训练参数来构建这些链接。这是通过创建完全避免使用全连接层的CNN架构来实现的,同时使用微观结构的2点空间相关性作为CNN的输入。除了增加鲁棒性(因为可训练参数的数量要少得多)之外,这项工作中开发的CNN模型还可以以非常低的计算成本构建属性闭包。这是因为它允许容易地探索有效的2点空间相关性的空间,该空间已知是凸船体。因此,可以从先前可用的有效2点空间相关性集合生成新的有效2点空间相关性集合,简单地作为凸组合。这项工作证明了利用2点空间相关性作为CNN的输入,代替当前基准测试中使用的体素离散微结构的显着好处。
Recent works have demonstrated the viability of convolutional neural networks (CNN) for capturing the highly non-linear microstructure-property linkages in high contrast composite material systems. In this work, we develop a new CNN architecture that utilizes a drastically reduced number of trainable parameters for building these linkages, compared to the benchmarks in current literature. This is accomplished by creating CNN architectures that completely avoid the use of fully connected layers, while using the 2-point spatial correlations of the microstructure as the input to the CNN. In addition to increased robustness (because of the much smaller number of trainable parameters), the CNN models developed in this work facilitate the construction of property closures at very low computational cost. This is because it allows for easy exploration of the space of valid 2-point spatial correlations, which is known to be a convex hull. Consequently, one can generate new sets of valid 2-point spatial correlations from previously available valid sets of 2-point spatial correlations, simply as convex combinations. This work demonstrates the significant benefits of utilizing 2-point spatial correlations as the input to the CNN, in place of the voxelated discrete microstructures used in current benchmarks.