深度学习:材料微结构与物性研究中的新动力  

Deep Learning: New Engine for the Study of Material Microstructures and Physical Properties

作　　者：卢果[1] 段素青[1] 

机构地区：[1]北京应用物理与计算数学研究所,计算物理重点实验室,北京

出　　处：《现代物理》2019年第6期263-276,共14页Modern Physics

基　　金：国防基础研究挑战计划(项目号:TZ2018001).

摘　　要：材料的微结构决定了其宏观性质。传统的自下而上的多尺度方法提供了研究微结构和物性关联的整体思路,但针对材料的微观、介观和宏观建模都存在诸多困难,其中不同尺度描述的衔接就极具挑战。随着计算能力以摩尔定律式的提升,和人工智能特别是深度学习的爆炸式进展,基于数据驱动的材料研究成当今世界的研究热点,并在晶体结构预测、稳定性分析、状态方程、光学性质、化学合成等领域都取得了很好的应用效果。深度学习的快速计算和可靠的预测能力能够极大的提升材料模拟效率。其广泛适用性为材料微结构与多尺度模拟中的一些传统难题提供了新的研究思路,有望促进材料微结构与物性的研究,为基于微介观机理的宏观物性建模、满足工程应用要求的材料性质预测提供了新的研究方向。本文将简要介绍深度学习的原理及常用的神经网络类型,概述材料微结构与多尺度建模中的主要方法,随后介绍深度学习在材料微结构与物性研究中的进展,并展望该方法在材料多尺度模拟领域中的发展。The microstructures of materials determine their macroscopic properties. The traditional bottom-up multi-scale approach provides a general strategy for studying the relationship between microstructures and physical properties. However, there are still many difficulties in microscopic, mesoscopic and macroscopic modeling of materials, and the bridging of different scale models is extremely challenging. With the advancement of computing power in Moore’s Law, and the explosive development of artificial intelligence, especially deep learning, data-driven methods are commonly used, and in crystal structure prediction, stability analysis, equation of states, optical properties, chemical synthesis, etc. have achieved good application results. The fast calculation speed and reliable prediction capabilities of deep learning can greatly improve the efficiency of material simulation. Its wide applicability provides new research ideas for some traditional problems in material microstructures and multi-scale simulations. It is expected to promote the study of material microstructures and physical properties, and to provide new research directions for modelling macroscopic physical properties based on micro-mesoscopic mechanism and prediction of material properties to meet engineering application requirements. This review article will briefly introduce the basic principles of deep learning and main types of commonly used neural networks, outline the main methods of material microstructures and multi-scale modeling, and then introduce the recent progress of deep learning method in the study of material microstructure and physical properties, and review the developments and prospects of deep learning method in the field of multi-scale simulation of materials.

关 键 词：深度学习 材料微结构与物性 多尺度模拟 

分 类 号：G63[文化科学—教育学]