摘要
大数据和人工智能技术的快速发展推动数据驱动的材料研发快速发展成为变革传统试错法的新模式,即所谓的材料研发第四范式。新模式将大幅度提升材料研发效率和工程化应用水平,推动新材料快速发展。本文聚焦机器学习辅助材料研发这一新兴领域,以材料预测和优化设计为主线,在简述材料特征构建与筛选的基础上,综述了机器学习在材料相结构、显微组织、成分-工艺-性能、服役行为预测等方面的研究进展;针对材料数据样本量少、噪音高、质量差,以及新材料探索空间巨大的特点,综述了机器学习模型与优化算法和策略融合,在新材料优化设计中的研究进展和典型应用。最后,讨论了机器学习在材料领域的发展机遇和挑战,展望了发展前景。
The rapid advancement of big data and artificial intelligence has resulted in new datadriven materials research and development(R&D),which has achieved substantial progress.This fourth paradigm is believed to improve materials design efficiency and industrialized application and stimulate the discovery of new materials.The focus of this work is on the emerging field of machine learning-assisted material R&D,with an emphasis on machine learning predictions and optimization design.Following a brief description of feature construction and selection,recent developments in material predictions on phases/structures,processing-structure-property relationships,microstructure,and material performance are reviewed.This paper also summarizes the research progress on optimization algorithms with machine learning models,which is expected to overcome the bottlenecks such as the small size and high noise level of material data samples and huge space for exploration.The challenges and future opportunities for machine learning applications in materials R&D are discussed and prospected.
作者
谢建新
宿彦京
薛德祯
姜雪
付华栋
黄海友
XIE Jianxin;SU Yanjing;XUE Dezhen;JIANG Xue;FU Huadong;HUANG Haiyou(Beijing Advanced Innovation Center for Materials Genome Engineering,Institute for Advanced Materials and Technology,University of Science and Technology Beijing,Beijing 100083,China;State Key Laboratory for Mechanical Behavior of Materials,Xian Jiaotong University,Xian 710049,China)
出处
《金属学报》
SCIE
EI
CAS
CSCD
北大核心
2021年第11期1343-1361,共19页
Acta Metallurgica Sinica
关键词
材料数据
数据挖掘
机器学习
材料设计
材料基因工程
materials data
data mining
machine learning
material design
material genome engineering