Neural network models of peak temperature, torque, traverse force, bending stress and maximum shear stress during friction stir welding

V. D. Manvatkar, A. Arora, A. De, Tarasankar Debroy

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

Tool and workpiece temperatures, torque, traverse force and stresses on the tools are affected by friction stir welding (FSW) variables such as plate thickness, welding speed, tool rotational speed, shoulder and pin diameters, pin length and tool material. Because of the large number of these welding variables, their effects cannot be realistically mapped by experiments. Here, we develop, test and make available a set of five neural networks to calculate the peak temperature, torque, traverse force and bending and equivalent stresses on the tool pin for the FSW of an aluminium alloy. The neural networks are trained and tested with the results from a well tested, comprehensive, three-dimensional heat and material flow model. The predictions of peak temperature and torque are also compared with appropriate experimental data for various values of shoulder radius and tool revolutions per minute. The models can be used even beyond the range of training with predictable levels of uncertainty.

Original languageEnglish (US)
Pages (from-to)460-466
Number of pages7
JournalScience and Technology of Welding and Joining
Volume17
Issue number6
DOIs
StatePublished - Aug 1 2012

Fingerprint

friction stir welding
Friction stir welding
shear stress
torque
Shear stress
Torque
Neural networks
shoulders
welding
Temperature
temperature
Welding
heat transmission
aluminum alloys
Aluminum alloys
education
radii
predictions

All Science Journal Classification (ASJC) codes

  • Materials Science(all)
  • Condensed Matter Physics

Cite this

@article{3f119c746b28408c897d940332f7c29e,
title = "Neural network models of peak temperature, torque, traverse force, bending stress and maximum shear stress during friction stir welding",
abstract = "Tool and workpiece temperatures, torque, traverse force and stresses on the tools are affected by friction stir welding (FSW) variables such as plate thickness, welding speed, tool rotational speed, shoulder and pin diameters, pin length and tool material. Because of the large number of these welding variables, their effects cannot be realistically mapped by experiments. Here, we develop, test and make available a set of five neural networks to calculate the peak temperature, torque, traverse force and bending and equivalent stresses on the tool pin for the FSW of an aluminium alloy. The neural networks are trained and tested with the results from a well tested, comprehensive, three-dimensional heat and material flow model. The predictions of peak temperature and torque are also compared with appropriate experimental data for various values of shoulder radius and tool revolutions per minute. The models can be used even beyond the range of training with predictable levels of uncertainty.",
author = "Manvatkar, {V. D.} and A. Arora and A. De and Tarasankar Debroy",
year = "2012",
month = "8",
day = "1",
doi = "10.1179/1362171812Y.0000000035",
language = "English (US)",
volume = "17",
pages = "460--466",
journal = "Science and Technology of Welding and Joining",
issn = "1362-1718",
publisher = "Maney Publishing",
number = "6",

}

Neural network models of peak temperature, torque, traverse force, bending stress and maximum shear stress during friction stir welding. / Manvatkar, V. D.; Arora, A.; De, A.; Debroy, Tarasankar.

In: Science and Technology of Welding and Joining, Vol. 17, No. 6, 01.08.2012, p. 460-466.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Neural network models of peak temperature, torque, traverse force, bending stress and maximum shear stress during friction stir welding

AU - Manvatkar, V. D.

AU - Arora, A.

AU - De, A.

AU - Debroy, Tarasankar

PY - 2012/8/1

Y1 - 2012/8/1

N2 - Tool and workpiece temperatures, torque, traverse force and stresses on the tools are affected by friction stir welding (FSW) variables such as plate thickness, welding speed, tool rotational speed, shoulder and pin diameters, pin length and tool material. Because of the large number of these welding variables, their effects cannot be realistically mapped by experiments. Here, we develop, test and make available a set of five neural networks to calculate the peak temperature, torque, traverse force and bending and equivalent stresses on the tool pin for the FSW of an aluminium alloy. The neural networks are trained and tested with the results from a well tested, comprehensive, three-dimensional heat and material flow model. The predictions of peak temperature and torque are also compared with appropriate experimental data for various values of shoulder radius and tool revolutions per minute. The models can be used even beyond the range of training with predictable levels of uncertainty.

AB - Tool and workpiece temperatures, torque, traverse force and stresses on the tools are affected by friction stir welding (FSW) variables such as plate thickness, welding speed, tool rotational speed, shoulder and pin diameters, pin length and tool material. Because of the large number of these welding variables, their effects cannot be realistically mapped by experiments. Here, we develop, test and make available a set of five neural networks to calculate the peak temperature, torque, traverse force and bending and equivalent stresses on the tool pin for the FSW of an aluminium alloy. The neural networks are trained and tested with the results from a well tested, comprehensive, three-dimensional heat and material flow model. The predictions of peak temperature and torque are also compared with appropriate experimental data for various values of shoulder radius and tool revolutions per minute. The models can be used even beyond the range of training with predictable levels of uncertainty.

UR - http://www.scopus.com/inward/record.url?scp=84863894716&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863894716&partnerID=8YFLogxK

U2 - 10.1179/1362171812Y.0000000035

DO - 10.1179/1362171812Y.0000000035

M3 - Article

VL - 17

SP - 460

EP - 466

JO - Science and Technology of Welding and Joining

JF - Science and Technology of Welding and Joining

SN - 1362-1718

IS - 6

ER -