Conditions for void formation in friction stir welding from machine learning

Yang Du, Tuhin Mukherjee, Tarasankar DebRoy

Research output: Contribution to journalArticle

Abstract

Friction stir welded joints often contain voids that are detrimental to their mechanical properties. Here we investigate the conditions for void formation using a decision tree and a Bayesian neural network. Three types of input data sets including unprocessed welding parameters and computed variables using an analytical and a numerical model of friction stir welding were examined. One hundred and eight sets of independent experimental data on void formation for the friction stir welding of three aluminum alloys, AA2024, AA2219, and AA6061, were analyzed. The neural network-based analysis with welding parameters, specimen and tool geometries, and material properties as input predicted void formation with 83.3% accuracy. When the potential causative variables, i.e., temperature, strain rate, torque, and maximum shear stress on the tool pin were computed from an approximate analytical model of friction stir welding, 90 and 93.3% accuracies of prediction were obtained using the decision tree and the neural network, respectively. When the same causative variables were computed from a rigorous numerical model, both the neural network and the decision tree predicted void formation with 96.6% accuracy. Among these four causative variables, the temperature and maximum shear stress showed the maximum influence on void formation.

Original languageEnglish (US)
Article number68
Journalnpj Computational Materials
Volume5
Issue number1
DOIs
StatePublished - Dec 1 2019

Fingerprint

Friction Stir Welding
Friction stir welding
Voids
Learning systems
Machine Learning
Decision trees
Neural networks
Decision tree
Neural Networks
Shear stress
Numerical models
Welding
Shear Stress
Strain rate
Welded Joints
Analytical models
Aluminum alloys
Materials properties
Welds
Torque

All Science Journal Classification (ASJC) codes

  • Modeling and Simulation
  • Materials Science(all)
  • Mechanics of Materials
  • Computer Science Applications

Cite this

@article{ad7e5488e80e4ae7aa9cbeb16050678f,
title = "Conditions for void formation in friction stir welding from machine learning",
abstract = "Friction stir welded joints often contain voids that are detrimental to their mechanical properties. Here we investigate the conditions for void formation using a decision tree and a Bayesian neural network. Three types of input data sets including unprocessed welding parameters and computed variables using an analytical and a numerical model of friction stir welding were examined. One hundred and eight sets of independent experimental data on void formation for the friction stir welding of three aluminum alloys, AA2024, AA2219, and AA6061, were analyzed. The neural network-based analysis with welding parameters, specimen and tool geometries, and material properties as input predicted void formation with 83.3{\%} accuracy. When the potential causative variables, i.e., temperature, strain rate, torque, and maximum shear stress on the tool pin were computed from an approximate analytical model of friction stir welding, 90 and 93.3{\%} accuracies of prediction were obtained using the decision tree and the neural network, respectively. When the same causative variables were computed from a rigorous numerical model, both the neural network and the decision tree predicted void formation with 96.6{\%} accuracy. Among these four causative variables, the temperature and maximum shear stress showed the maximum influence on void formation.",
author = "Yang Du and Tuhin Mukherjee and Tarasankar DebRoy",
year = "2019",
month = "12",
day = "1",
doi = "10.1038/s41524-019-0207-y",
language = "English (US)",
volume = "5",
journal = "npj Computational Materials",
issn = "2057-3960",
publisher = "Nature Publishing Group",
number = "1",

}

Conditions for void formation in friction stir welding from machine learning. / Du, Yang; Mukherjee, Tuhin; DebRoy, Tarasankar.

In: npj Computational Materials, Vol. 5, No. 1, 68, 01.12.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Conditions for void formation in friction stir welding from machine learning

AU - Du, Yang

AU - Mukherjee, Tuhin

AU - DebRoy, Tarasankar

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Friction stir welded joints often contain voids that are detrimental to their mechanical properties. Here we investigate the conditions for void formation using a decision tree and a Bayesian neural network. Three types of input data sets including unprocessed welding parameters and computed variables using an analytical and a numerical model of friction stir welding were examined. One hundred and eight sets of independent experimental data on void formation for the friction stir welding of three aluminum alloys, AA2024, AA2219, and AA6061, were analyzed. The neural network-based analysis with welding parameters, specimen and tool geometries, and material properties as input predicted void formation with 83.3% accuracy. When the potential causative variables, i.e., temperature, strain rate, torque, and maximum shear stress on the tool pin were computed from an approximate analytical model of friction stir welding, 90 and 93.3% accuracies of prediction were obtained using the decision tree and the neural network, respectively. When the same causative variables were computed from a rigorous numerical model, both the neural network and the decision tree predicted void formation with 96.6% accuracy. Among these four causative variables, the temperature and maximum shear stress showed the maximum influence on void formation.

AB - Friction stir welded joints often contain voids that are detrimental to their mechanical properties. Here we investigate the conditions for void formation using a decision tree and a Bayesian neural network. Three types of input data sets including unprocessed welding parameters and computed variables using an analytical and a numerical model of friction stir welding were examined. One hundred and eight sets of independent experimental data on void formation for the friction stir welding of three aluminum alloys, AA2024, AA2219, and AA6061, were analyzed. The neural network-based analysis with welding parameters, specimen and tool geometries, and material properties as input predicted void formation with 83.3% accuracy. When the potential causative variables, i.e., temperature, strain rate, torque, and maximum shear stress on the tool pin were computed from an approximate analytical model of friction stir welding, 90 and 93.3% accuracies of prediction were obtained using the decision tree and the neural network, respectively. When the same causative variables were computed from a rigorous numerical model, both the neural network and the decision tree predicted void formation with 96.6% accuracy. Among these four causative variables, the temperature and maximum shear stress showed the maximum influence on void formation.

UR - http://www.scopus.com/inward/record.url?scp=85068782590&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068782590&partnerID=8YFLogxK

U2 - 10.1038/s41524-019-0207-y

DO - 10.1038/s41524-019-0207-y

M3 - Article

AN - SCOPUS:85068782590

VL - 5

JO - npj Computational Materials

JF - npj Computational Materials

SN - 2057-3960

IS - 1

M1 - 68

ER -