基于深度学习方法的结构材料弹性各向同性识别
Identifying the elastic isotropy of architectured materials based on deep learning method
摘要：
随着增材制造技术的发展，可以通过对材料微结构的剪裁来精确设计结构材料的力学性能。弹性各向同性作为设计的主要目标之一，在许多工程应用中具有重要意义。然而，目前流行的实验和数值方法通常是太昂贵和耗时的结构材料的弹性各向同性与成千上万的可能的微结构在设计空间中确定。因此，快速的机械性能表征是先进的结构材料设计所需要的。在这里，开发了一种基于深度学习的方法，作为一种便携式和有效的工具，直接从具有任意成分分布的代表性微结构的图像中识别结构材料的弹性各向同性。本文首先推导了结构材料弹性各向同性的度量，并以此建立了一个具有相关微结构图像的数据库。然后用数据库训练卷积神经网络。结果表明，卷积神经网络在各向同性识别方面表现出良好的性能。同时，它表现出足够的鲁棒性，以保持在实际制造中的材料属性波动的性能。此外，经过良好训练的卷积神经网络可以在不同类型的结构材料之间成功传输，包括两相复合材料和多孔材料，这大大提高了基于深度学习的方法的效率。该研究为大数据驱动的结构材料设计提供了新的思路。
英文摘要：
With the achievement on the additive manufacturing, the mechanical properties of architectured materials can be precisely designed by tailoring microstructures. As one of the primary design objectives, the elastic isotropy is of great significance for many engineering applications. However, the prevailing experimental and numerical methods are normally too costly and time-consuming to determine the elastic isotropy of architectured materials with tens of thousands of possible microstructures in design space. The quick mechanical characterization is thus desired for the advanced design of architectured materials. Here, a deep learning-based approach is developed as a portable and efficient tool to identify the elastic isotropy of architectured materials directly from the images of their representative microstructures with arbitrary component distributions. The measure of elastic isotropy for architectured materials is derived firstly in this paper to construct a database with associated images of microstructures. Then a convolutional neural network is trained with the database. It is found that the convolutional neural network shows good performance on the isotropy identification. Meanwhile, it exhibits enough robustness to maintain the performance under fluctuated material properties in practical fabrications. Moreover, the well-trained convolutional neural network can be successfully transferred among different types of architectured materials, including two-phase composites and porous materials, which greatly enhance the efficiency of the deep learning-based approach. This study can give new inspirations on the fast mechanical characterization for the big-data driven design of architectured 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。
