防务技术2024，Vol.40Issue(10) ：105-124.DOI:10.1016/j.dt.2024.04.012

Data-driven prediction of dimensionless quantities for semi-infinite target penetration by integrating machine-learning and feature selection methods

Qingqing Chen Xinyu Zhang Zhiyong Wang Jie Zhang Zhihua Wang
防务技术2024，Vol.40Issue(10) ：105-124.DOI:10.1016/j.dt.2024.04.012
✕
  • 维普
  • 万方数据

Data-driven prediction of dimensionless quantities for semi-infinite target penetration by integrating machine-learning and feature selection methods

Qingqing Chen 1Xinyu Zhang 1Zhiyong Wang 1Jie Zhang 2Zhihua Wang1
扫码查看

作者信息

  • 1. Institute of Applied Mechanics,College of Mechanical and Vehicle Engineering,Taiyuan University of Technology,Taiyuan 030024,China;Shanxi Key Lab.of Material Strength & structural Impact,College of Mechanical and Vehicle Engineering,Taiyuan 030024,China
  • 2. Institute of Applied Mechanics,College of Mechanical and Vehicle Engineering,Taiyuan University of Technology,Taiyuan 030024,China;Shanxi Key Lab.of Material Strength & structural Impact,College of Mechanical and Vehicle Engineering,Taiyuan 030024,China;Department of Civil and Environmental Engineering,National University of Singapore,1 Engineering Drive 2,117576,Singapore
  • 折叠

Abstract

This study employs a data-driven methodology that embeds the principle of dimensional invariance into an artificial neural network to automatically identify dominant dimensionless quantities in the pene-tration of rod projectiles into semi-infinite metal targets from experimental measurements.The derived mathematical expressions of dimensionless quantities are simplified by the examination of the exponent matrix and coupling relationships between feature variables.As a physics-based dimension reduction methodology,this way reduces high-dimensional parameter spaces to descriptions involving only a few physically interpretable dimensionless quantities in penetrating cases.Then the relative importance of various dimensionless feature variables on the penetration efficiencies for four impacting conditions is evaluated through feature selection engineering.The results indicate that the selected critical dimen-sionless feature variables by this synergistic method,without referring to the complex theoretical equations and aiding in the detailed knowledge of penetration mechanics,are in accordance with those reported in the reference.Lastly,the determined dimensionless quantities can be efficiently applied to conduct semi-empirical analysis for the specific penetrating case,and the reliability of regression functions is validated.

Key words

Data-driven dimensional analysis/Penetration/Semi-infinite metal target/Dimensionless numbers/Feature selection

引用本文复制引用

基金项目

National Natural Science Foundation of China(12272257)

National Natural Science Foundation of China(12102292)

National Natural Science Foundation of China(12032006)

special fund for Science and Technology Innovation Teams of Shanxi Province(202204051002006)

出版年

2024
防务技术
中国兵工学会

防务技术

CSTPCD
影响因子：0.358
ISSN：2214-9147
段落导航相关论文