Calibration of polyvinylidene fluoride (PVDF) stress gauges under high-impact dynamic compression by machine learning

doi:10.1063/5.0066090

CORC > 力学研究所 > 中国科学院力学研究所 > 非线性力学国家重点实验室

	Calibration of polyvinylidene fluoride (PVDF) stress gauges under high-impact dynamic compression by machine learning
	Qin, Shuang 1,2; Yu, Zheng 1; Zhang, Xu 1; Yang, Shuqi 1; Peng, Wenyang 1; Zhao, Feng 1
刊名	JOURNAL OF APPLIED PHYSICS
	2022-01-14
卷号	131 期号:2 页码:8
ISSN号	0021-8979
DOI	10.1063/5.0066090
通讯作者	Zhang, Xu(caepzx@sohu.com) ; Zhao, Feng(ifpzf@163.com)
英文摘要	Calibration of stress gauges is of great importance for understanding the behaviors of materials under high dynamic impacts. However, commonly used calibration models have little transferability due to ignoring the influences of the gauge parameters. In this work, we propose a systematic approach that can generate effective and transferable calibration models including multiple independent variables by machine learning. Specifically, we conduct high-impact dynamic compression experiments using polyvinylidene fluoride (PVDF) stress gauges with two different thicknesses and varying remnant polarizations at shock levels from 0.3 to 10 GPa. To best characterize the comprehensive calibration relationship, we select a set of five features (combined by strain, remnant polarization, and film thickness) by feature engineering and use Lasso with the bagging ensemble as an algorithm to train the machine learning model. For comparison, we also propose semiempirical models that calibrate PVDF gauges effectively, but without including thickness and remnant polarization. Our results show that the machine learning model is more precise and more reasonable in physics. The predicted dependences of the calibration curves on remnant polarization and film thickness by the machine learning model are qualitatively consistent with the physics scenario. This work reveals the potential of machine learning methods to improve gauge calibration for better performance and transferability. The method used in this work is applicable to the calibration of any stress gauges with multiple variables.
资助项目	National Defense Science Foundation of China[JSZL2016212C001] ; Science Challenge Project of China[TZ2018001] ; Science Challenge Project of China[2019-JCJQ-ZD-203]
WOS关键词	SHOCK ; REGRESSION ; PRESSURE ; POLYMERS
WOS研究方向	Physics
语种	英语
WOS记录号	WOS:000747278100015
资助机构	National Defense Science Foundation of China ; Science Challenge Project of China
内容类型	期刊论文
源URL	[http://dspace.imech.ac.cn/handle/311007/88411]
专题	力学研究所_非线性力学国家重点实验室
通讯作者	Zhang, Xu; Zhao, Feng
作者单位	1.China Acad Engn Phys, Inst Fluid Phys, Natl Lab Shock Wave & Detonat Phys, Mianyang 621900, Sichuan, Peoples R China 2.Chinese Acad Sci, Inst Mech, State Key Lab Nonlinear Mech, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Qin, Shuang,Yu, Zheng,Zhang, Xu,et al. Calibration of polyvinylidene fluoride (PVDF) stress gauges under high-impact dynamic compression by machine learning[J]. JOURNAL OF APPLIED PHYSICS,2022,131(2):8.
APA	Qin, Shuang,Yu, Zheng,Zhang, Xu,Yang, Shuqi,Peng, Wenyang,&Zhao, Feng.(2022).Calibration of polyvinylidene fluoride (PVDF) stress gauges under high-impact dynamic compression by machine learning.JOURNAL OF APPLIED PHYSICS,131(2),8.
MLA	Qin, Shuang,et al."Calibration of polyvinylidene fluoride (PVDF) stress gauges under high-impact dynamic compression by machine learning".JOURNAL OF APPLIED PHYSICS 131.2(2022):8.