Identification of key GMAW fillet weld parameters and interactions using artificial neural networks

J.W.P. Cairns, N.A. McPherson, A.M. Galloway

Research output: Contribution to journalArticle

Abstract

Fillet welds are one of the most commonly used weld joints but one of the most difficult to weld consistently. This paper presents a technique using Artificial Neural Networks (ANN) to identify the key Gas Metal Arc Welding (GMAW) fillet weld parameters and interactions that impact on the resultant geometry, when using a metal cored wire. The input parameters to the model were current, voltage, travel speed; gun angle and travel angle and the outputs of the model were penetration and leg length. The model was in good agreement with experimental data collected and the subsequent sensitivity analysis showed that current was the most influential parameter in determining penetration and that travel speed, followed closely by current and voltage were most influential in determining the leg length. The paper also concludes that a ‘pushing’ travel angle is preferred when trying to control the resultant geometry mainly because both the resultant leg length and penetration appear to be less sensitive to changes in heat input.
LanguageEnglish
Pages51-57
Number of pages7
JournalWelding and Cutting
Volume15
Issue number1
Publication statusAccepted/In press - 7 Dec 2015

Fingerprint

Gas metal arc welding
Welds
Neural networks
Geometry
Electric potential
Sensitivity analysis
Metals
Wire

Keywords

  • ANN
  • GMAW
  • design of experiments (DoE)
  • fillet welding

Cite this

@article{a60186aee2974c1ba0f66e5cecbf1d46,
title = "Identification of key GMAW fillet weld parameters and interactions using artificial neural networks",
abstract = "Fillet welds are one of the most commonly used weld joints but one of the most difficult to weld consistently. This paper presents a technique using Artificial Neural Networks (ANN) to identify the key Gas Metal Arc Welding (GMAW) fillet weld parameters and interactions that impact on the resultant geometry, when using a metal cored wire. The input parameters to the model were current, voltage, travel speed; gun angle and travel angle and the outputs of the model were penetration and leg length. The model was in good agreement with experimental data collected and the subsequent sensitivity analysis showed that current was the most influential parameter in determining penetration and that travel speed, followed closely by current and voltage were most influential in determining the leg length. The paper also concludes that a ‘pushing’ travel angle is preferred when trying to control the resultant geometry mainly because both the resultant leg length and penetration appear to be less sensitive to changes in heat input.",
keywords = "ANN, GMAW, design of experiments (DoE), fillet welding",
author = "J.W.P. Cairns and N.A. McPherson and A.M. Galloway",
year = "2015",
month = "12",
day = "7",
language = "English",
volume = "15",
pages = "51--57",
journal = "Welding and Cutting",
issn = "1612-3433",
publisher = "Deutscher Verlag fur Schweisstechnik GmbH",
number = "1",

}

Identification of key GMAW fillet weld parameters and interactions using artificial neural networks. / Cairns, J.W.P.; McPherson, N.A.; Galloway, A.M.

In: Welding and Cutting, Vol. 15, No. 1, 07.12.2015, p. 51-57.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Identification of key GMAW fillet weld parameters and interactions using artificial neural networks

AU - Cairns, J.W.P.

AU - McPherson, N.A.

AU - Galloway, A.M.

PY - 2015/12/7

Y1 - 2015/12/7

N2 - Fillet welds are one of the most commonly used weld joints but one of the most difficult to weld consistently. This paper presents a technique using Artificial Neural Networks (ANN) to identify the key Gas Metal Arc Welding (GMAW) fillet weld parameters and interactions that impact on the resultant geometry, when using a metal cored wire. The input parameters to the model were current, voltage, travel speed; gun angle and travel angle and the outputs of the model were penetration and leg length. The model was in good agreement with experimental data collected and the subsequent sensitivity analysis showed that current was the most influential parameter in determining penetration and that travel speed, followed closely by current and voltage were most influential in determining the leg length. The paper also concludes that a ‘pushing’ travel angle is preferred when trying to control the resultant geometry mainly because both the resultant leg length and penetration appear to be less sensitive to changes in heat input.

AB - Fillet welds are one of the most commonly used weld joints but one of the most difficult to weld consistently. This paper presents a technique using Artificial Neural Networks (ANN) to identify the key Gas Metal Arc Welding (GMAW) fillet weld parameters and interactions that impact on the resultant geometry, when using a metal cored wire. The input parameters to the model were current, voltage, travel speed; gun angle and travel angle and the outputs of the model were penetration and leg length. The model was in good agreement with experimental data collected and the subsequent sensitivity analysis showed that current was the most influential parameter in determining penetration and that travel speed, followed closely by current and voltage were most influential in determining the leg length. The paper also concludes that a ‘pushing’ travel angle is preferred when trying to control the resultant geometry mainly because both the resultant leg length and penetration appear to be less sensitive to changes in heat input.

KW - ANN

KW - GMAW

KW - design of experiments (DoE)

KW - fillet welding

M3 - Article

VL - 15

SP - 51

EP - 57

JO - Welding and Cutting

T2 - Welding and Cutting

JF - Welding and Cutting

SN - 1612-3433

IS - 1

ER -