Establishing a data-driven strength model for ??????-tin by performing symbolic regression using genetic programming

被引：10

作者：

Zapiain, David Montes de Oca ^{[1
]}

Lane, J. Matthew D. ^{[1
]}

Carroll, Jay D. ^{[1
]}

Casias, Zachary ^{[1
]}

Battaile, Corbett C. ^{[1
]}

Fensin, Saryu ^{[2
]}

Lim, Hojun ^{[1
]}

机构：

[1] Sandia Natl Labs, Albuquerque, NM 87185 USA

[2] Los Alamos Natl Lab, Los Alamos, NM 87545 USA

来源：

COMPUTATIONAL MATERIALS SCIENCE | 2023年 / 218卷

关键词：

Genetic programming; Tin; Strength; Symbolic regression; MODIFIED JOHNSON-COOK; MODIFIED ZERILLI-ARMSTRONG; HOT DEFORMATION-BEHAVIOR; CONSTITUTIVE MODELS; PLASTIC-DEFORMATION; STRAIN RATES; TEMPERATURE; PREDICT;

D O I：

10.1016/j.commatsci.2022.111967

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

Tin (Sn) exhibits complex deformation behavior characterized by significant dependence of strength on temperature and strain rate. This work develops a strength model for tin by using genetic programming to perform symbolic regression on a set of compression tests at various strain rates and temperatures. The strength model developed in this work showed increased accuracy compared to traditional strength models. Furthermore, the developed strength model adequately predicted independent experimental data (i.e., data that was not used to train the model). Results demonstrate that genetic programming successfully established a valid analytical function that adequately characterizes the temperature and strain rate dependent strength behavior of tin. Therefore, demonstrating that the developed framework provides robust and accurate formulations of strength models.

引用

页数：11

共 45 条

[31] Distilling Free-Form Natural Laws from Experimental Data [J].