中国物理B ›› 2022, Vol. 31 ›› Issue (12): 126402-126402.doi: 10.1088/1674-1056/ac98a4

• • 上一篇    下一篇

Learning physical states of bulk crystalline materials from atomic trajectories in molecular dynamics simulation

Tian-Shou Liang(梁添寿)1,2, Peng-Peng Shi(时朋朋)2,†, San-Qing Su(苏三庆)2,‡, and Zhi Zeng(曾志)3   

  1. 1 School of Mechanical and Electrical Engineering, Xi'an University of Architecture and Technology, Xi'an 710055, China;
    2 School of Civil Engineering, Xi'an University of Architecture and Technology, Xi'an 710055, China;
    3 School of Mechano-Electronic Engineering, Xidian University, Xi'an 710071, China
  • 收稿日期:2022-07-21 修回日期:2022-10-06 接受日期:2022-10-10 出版日期:2022-11-11 发布日期:2022-11-11
  • 通讯作者: Peng-Peng Shi, San-Qing Su E-mail:shipengpeng@xjtu.edu.cn;sussqx@xauat.edu.cn
  • 基金资助:
    Project supported by the China Postdoctoral Science Foundation (Grant No. 2019M663935XB), the Natural Science Foundation of Shaanxi Province, China (Grant No. 2019JQ-261), and the National Natural Science Foundation of China (Grant Nos. 11802225 and 51878548).

Learning physical states of bulk crystalline materials from atomic trajectories in molecular dynamics simulation

Tian-Shou Liang(梁添寿)1,2, Peng-Peng Shi(时朋朋)2,†, San-Qing Su(苏三庆)2,‡, and Zhi Zeng(曾志)3   

  1. 1 School of Mechanical and Electrical Engineering, Xi'an University of Architecture and Technology, Xi'an 710055, China;
    2 School of Civil Engineering, Xi'an University of Architecture and Technology, Xi'an 710055, China;
    3 School of Mechano-Electronic Engineering, Xidian University, Xi'an 710071, China
  • Received:2022-07-21 Revised:2022-10-06 Accepted:2022-10-10 Online:2022-11-11 Published:2022-11-11
  • Contact: Peng-Peng Shi, San-Qing Su E-mail:shipengpeng@xjtu.edu.cn;sussqx@xauat.edu.cn
  • Supported by:
    Project supported by the China Postdoctoral Science Foundation (Grant No. 2019M663935XB), the Natural Science Foundation of Shaanxi Province, China (Grant No. 2019JQ-261), and the National Natural Science Foundation of China (Grant Nos. 11802225 and 51878548).

摘要: Melting of crystalline material is a common physical phenomenon, yet it remains elusive owing to the diversity in physical pictures. In this work, we proposed a deep learning architecture to learn the physical states (solid- or liquid-phase) from the atomic trajectories of the bulk crystalline materials with four typical lattice types. The method has ultra-high accuracy (higher than 95%) for the classification of solid-liquid atoms during the phase transition process and is almost insensitive to temperature. The atomic physical states are identified from atomic behaviors without considering any characteristic threshold parameter, which yet is necessary for the classical methods. The phase transition of bulk crystalline materials can be correctly predicted by learning from the atomic behaviors of different materials, which confirms the close correlation between atomic behaviors and atomic physical states. These evidences forecast that there should be a more general undiscovered physical quantity implicated in the atomic behaviors and elucidate the nature of bulk crystalline melting.

关键词: melting phase transition, crystalline materials, physical states, deep learning, molecular dynamics simulation

Abstract: Melting of crystalline material is a common physical phenomenon, yet it remains elusive owing to the diversity in physical pictures. In this work, we proposed a deep learning architecture to learn the physical states (solid- or liquid-phase) from the atomic trajectories of the bulk crystalline materials with four typical lattice types. The method has ultra-high accuracy (higher than 95%) for the classification of solid-liquid atoms during the phase transition process and is almost insensitive to temperature. The atomic physical states are identified from atomic behaviors without considering any characteristic threshold parameter, which yet is necessary for the classical methods. The phase transition of bulk crystalline materials can be correctly predicted by learning from the atomic behaviors of different materials, which confirms the close correlation between atomic behaviors and atomic physical states. These evidences forecast that there should be a more general undiscovered physical quantity implicated in the atomic behaviors and elucidate the nature of bulk crystalline melting.

Key words: melting phase transition, crystalline materials, physical states, deep learning, molecular dynamics simulation

中图分类号:  (General studies of phase transitions)

  • 64.60.-i
64.60.A- (Specific approaches applied to studies of phase transitions) 64.70.D- (Solid-liquid transitions) 64.70.dj (Melting of specific substances)