机器学习型分子力场在金属材料相变与变形领域的研究进展  

Machine-Learning Force Fields for Metallic Materials:Phase Transformations and Deformations

作　　者：李志尚 赵龙 宗洪祥 丁向东[1] LI Zhishang;ZHAO Long;ZONG Hongxiang;DING Xiangdong(State Key Laboratory for Mechanical Behavior of Materials,Xi'an Jiaotong University,Xi'an 710049,China)

机构地区：[1]西安交通大学金属材料强度国家重点实验室,西安710049

出　　处：《金属学报》2024年第10期1388-1404,共17页Acta Metallurgica Sinica

基　　金：国家重点研发计划项目No.2022YFB3707601;国家自然科学基金项目Nos.52171011;52322103和12304026。

摘　　要：金属材料在服役过程中通常伴随着相变与形变,深入理解其背后的微观机制,对于开发能够满足国家重大需求的新型金属材料至关重要。分子动力学模拟技术,特别是机器学习型分子力场赋能的分子动力学模拟技术,作为一种新的原子模拟范式,正逐渐成为从原子尺度理解金属相变与形变的强有力工具。本文综述了近年来机器学习型分子力场在金属材料相变与形变中的研究进展。首先简述了机器学习型分子力场的基本原理与发展历程;聚焦金属材料的相变与形变过程,着重阐述了机器学习型分子力场对其相变动力学与形变微观机制在原子尺度上的理解;针对现有机器学习型分子力场在金属材料相变与形变研究中存在的壁垒进行总结,并对未来可能的发展方向提出了展望。A comprehensive understanding of the microscopic mechanisms underlying phase transitions and deformations in metallic materials is crucial for developing new materials that meet the nations essential needs.Molecular dynamic simulation techniques,particularly those powered by machinelearning molecular force fields,are emerging as potent tools for unraveling atomic-scale phenomena.In this study,recent advancements in machine-learning molecular force fields were reviewed to investigate metallic phase transitions and deformations.First,the fundamental principles and evolution of machinelearning molecular force fields were introduced.Then,the phase transformation and deformation of metals were examined,providing insights into the kinetics of phase transitions and microscopic mechanisms.Finally,the challenges faced by current machine-learning molecular force fields in studying metallic phase transformations and deformations were identified,and a glimpse into future research directions was discussed.

关 键 词：机器学习型分子力场 相变与形变 分子动力学模拟 金属材料 

分 类 号：TB31[一般工业技术—材料科学与工程]