Using artificial neural networks to identify and optimise the key parameters affecting geometry of a GMAW fillet weld

Research output: Contribution to conferencePaper

Abstract

Control of Gas Metal Arc Welding (GMAW) parameters is key to maintaining good quality and consistent fillet weld geometry. The external geometry of the fillet weld can be easily measured, however the internal geometry (i.e. penetration), which is critical in determining the structural integrity of the joint, is difficult to measure without destructively testing the workpiece. Consequently the most cost effective way to ensure adequate penetration is to maintain close control of the input parameters. Furthermore if we can demonstrate tight control of the parameters and interactions that affect the joint penetration then we can increase the confidence that sufficient penetration is being achieved.Previous studies have shown that the variation in set up parameters between welders and the guidance given by industry/suppliers can vary widely and in some cases be contradictory. Also in practice there are several characteristics of the manual/semi-automatic GMAW fillet weld process that are difficult to control (e.g. gun angle, travel angle and gap) but yet have an impact on the resultant geometry.This paper will document a programme of work which has used an Artificial Neural Network (ANN) to identify the parameters, and specific interactions that have an impact on the resultant fillet weld geometry. The variables that will be assessed in this paper will include current, voltage, travel speed, gun angle, travel angle. Further follow on studies will take place to understand the impact of gap, gas flow & nozzle diameters.

Conference

Conference18th International Conference on Joining Materials, JOM-18
CountryDenmark
CityHelsingør
Period26/04/1529/04/15

Fingerprint

Gas metal arc welding
Welds
Neural networks
Geometry
Structural integrity
Flow of gases
Nozzles
Testing
Electric potential
Costs
Industry

Keywords

  • artificial neural network (ANN)
  • fillet welding
  • GMAW
  • travel angle
  • gun angle
  • penetration depth
  • leg length

Cite this

Cairns, J., McPherson, N., & Galloway, A. (2015). Using artificial neural networks to identify and optimise the key parameters affecting geometry of a GMAW fillet weld. Paper presented at 18th International Conference on Joining Materials, JOM-18, Helsingør, Denmark.
Cairns, Jonathan ; McPherson, Norman ; Galloway, Alexander. / Using artificial neural networks to identify and optimise the key parameters affecting geometry of a GMAW fillet weld. Paper presented at 18th International Conference on Joining Materials, JOM-18, Helsingør, Denmark.13 p.
@conference{7d9149a8b59f4304b29b4b42bdef557a,
title = "Using artificial neural networks to identify and optimise the key parameters affecting geometry of a GMAW fillet weld",
abstract = "Control of Gas Metal Arc Welding (GMAW) parameters is key to maintaining good quality and consistent fillet weld geometry. The external geometry of the fillet weld can be easily measured, however the internal geometry (i.e. penetration), which is critical in determining the structural integrity of the joint, is difficult to measure without destructively testing the workpiece. Consequently the most cost effective way to ensure adequate penetration is to maintain close control of the input parameters. Furthermore if we can demonstrate tight control of the parameters and interactions that affect the joint penetration then we can increase the confidence that sufficient penetration is being achieved.Previous studies have shown that the variation in set up parameters between welders and the guidance given by industry/suppliers can vary widely and in some cases be contradictory. Also in practice there are several characteristics of the manual/semi-automatic GMAW fillet weld process that are difficult to control (e.g. gun angle, travel angle and gap) but yet have an impact on the resultant geometry.This paper will document a programme of work which has used an Artificial Neural Network (ANN) to identify the parameters, and specific interactions that have an impact on the resultant fillet weld geometry. The variables that will be assessed in this paper will include current, voltage, travel speed, gun angle, travel angle. Further follow on studies will take place to understand the impact of gap, gas flow & nozzle diameters.",
keywords = "artificial neural network (ANN), fillet welding, GMAW, travel angle, gun angle, penetration depth, leg length",
author = "Jonathan Cairns and Norman McPherson and Alexander Galloway",
note = "Published as CD-ROM, on first day of conference.; 18th International Conference on Joining Materials, JOM-18 ; Conference date: 26-04-2015 Through 29-04-2015",
year = "2015",
month = "4",
day = "26",
language = "English",

}

Cairns, J, McPherson, N & Galloway, A 2015, 'Using artificial neural networks to identify and optimise the key parameters affecting geometry of a GMAW fillet weld' Paper presented at 18th International Conference on Joining Materials, JOM-18, Helsingør, Denmark, 26/04/15 - 29/04/15, .

Using artificial neural networks to identify and optimise the key parameters affecting geometry of a GMAW fillet weld. / Cairns, Jonathan; McPherson, Norman; Galloway, Alexander.

2015. Paper presented at 18th International Conference on Joining Materials, JOM-18, Helsingør, Denmark.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Using artificial neural networks to identify and optimise the key parameters affecting geometry of a GMAW fillet weld

AU - Cairns, Jonathan

AU - McPherson, Norman

AU - Galloway, Alexander

N1 - Published as CD-ROM, on first day of conference.

PY - 2015/4/26

Y1 - 2015/4/26

N2 - Control of Gas Metal Arc Welding (GMAW) parameters is key to maintaining good quality and consistent fillet weld geometry. The external geometry of the fillet weld can be easily measured, however the internal geometry (i.e. penetration), which is critical in determining the structural integrity of the joint, is difficult to measure without destructively testing the workpiece. Consequently the most cost effective way to ensure adequate penetration is to maintain close control of the input parameters. Furthermore if we can demonstrate tight control of the parameters and interactions that affect the joint penetration then we can increase the confidence that sufficient penetration is being achieved.Previous studies have shown that the variation in set up parameters between welders and the guidance given by industry/suppliers can vary widely and in some cases be contradictory. Also in practice there are several characteristics of the manual/semi-automatic GMAW fillet weld process that are difficult to control (e.g. gun angle, travel angle and gap) but yet have an impact on the resultant geometry.This paper will document a programme of work which has used an Artificial Neural Network (ANN) to identify the parameters, and specific interactions that have an impact on the resultant fillet weld geometry. The variables that will be assessed in this paper will include current, voltage, travel speed, gun angle, travel angle. Further follow on studies will take place to understand the impact of gap, gas flow & nozzle diameters.

AB - Control of Gas Metal Arc Welding (GMAW) parameters is key to maintaining good quality and consistent fillet weld geometry. The external geometry of the fillet weld can be easily measured, however the internal geometry (i.e. penetration), which is critical in determining the structural integrity of the joint, is difficult to measure without destructively testing the workpiece. Consequently the most cost effective way to ensure adequate penetration is to maintain close control of the input parameters. Furthermore if we can demonstrate tight control of the parameters and interactions that affect the joint penetration then we can increase the confidence that sufficient penetration is being achieved.Previous studies have shown that the variation in set up parameters between welders and the guidance given by industry/suppliers can vary widely and in some cases be contradictory. Also in practice there are several characteristics of the manual/semi-automatic GMAW fillet weld process that are difficult to control (e.g. gun angle, travel angle and gap) but yet have an impact on the resultant geometry.This paper will document a programme of work which has used an Artificial Neural Network (ANN) to identify the parameters, and specific interactions that have an impact on the resultant fillet weld geometry. The variables that will be assessed in this paper will include current, voltage, travel speed, gun angle, travel angle. Further follow on studies will take place to understand the impact of gap, gas flow & nozzle diameters.

KW - artificial neural network (ANN)

KW - fillet welding

KW - GMAW

KW - travel angle

KW - gun angle

KW - penetration depth

KW - leg length

UR - http://www.iiwelding.org/News/Attachments/71/JOM%2018%20final%20programme%20PDF.pdf

M3 - Paper

ER -

Cairns J, McPherson N, Galloway A. Using artificial neural networks to identify and optimise the key parameters affecting geometry of a GMAW fillet weld. 2015. Paper presented at 18th International Conference on Joining Materials, JOM-18, Helsingør, Denmark.