Parameter Analysis of Gas Metal Arc Welding (GMAW) in Determining Defects by Comparing the Response Surface Method (RSM) and Artificial Neuron Network (ANN)

Dendi Prajadhiana Ishak; Salman  Hadi; Keval Priapratama  Prajadhiana; Mohd Shahriman  Adenan

doi:10.24191/jaeds.v6i1.169

Authors

Dendi Prajadhiana Ishak Department of Industrial Engineering, Faculty of Engineering, University of Indonesia, Depok Indonesia
Salman Hadi Department of Industrial Engineering, Faculty of Engineering, University of Indonesia, Depok Indonesia
Keval Priapratama Prajadhiana Study Program of Mechanical Engineering , Faculty of Engineering, President University, Cikarang, Indonesia
Mohd Shahriman Adenan Smart Manufacturing Research Institute, Universiti Teknologi MARA, Shah Alam, Malaysia

DOI:

https://doi.org/10.24191/jaeds.v6i1.169

Keywords:

GMAW, Welding Simulation, ANN, RSM, Process Parameters

Abstract

Welding is a critical manufacturing process widely employed in industry for joining two or more materials through localized melting and subsequent solidification. Among the various welding techniques, Gas Metal Arc Welding (GMAW) is extensively used due to its high efficiency, versatility, and suitability for joining both ferrous and nonferrous materials. Optimizing GMAW process parameters is essential for improving weld quality, minimizing defects, and enhancing structural integrity in industrial applications. However, existing studies often rely on either statistical methods or machine learning approaches independently, with limited comparative analysis of their predictive capabilities, particularly within a simulation-based framework. This study aims to analyse and optimize key GMAW process parameters and to evaluate the predictive performance of Response Surface Methodology (RSM) and Artificial Neural Network (ANN) models. Finite element simulations are performed using Simufact Welding software to investigate the influence of welding current, arc voltage, and welding speed on output responses, including peak temperature, welding-induced deformation (distortion), and maximum residual stress. The simulated data are further analyzed using RSM to develop predictive mathematical models and examine interaction effects among input parameters, while an ANN model is implemented to enhance prediction and validation. The results indicate that both approaches are effective in modelling the process; however, RSM demonstrates superior predictive accuracy, as evidenced by a lower root mean square error (RMSE) compared to the ANN model. The key finding of this study highlights the effectiveness of RSM as a reliable and accurate tool for optimizing GMAW process parameters within a numerical simulation framework.

Downloads

Download data is not yet available.

References

J. Goldak and M. Akhlaghi, Computational Welding Mechanics, 2nd ed. Springer, 2021.

Y. Zhang, H. Shen, and X. Wang, “Numerical simulation for gas metal arc welding: A review,” Int. J. Adv. Manuf. Technol., vol. 124, no. 1–4, pp. 1–20, 2024.

A. Kumar and R. S. Parameswaran, “Finite element simulation of heat transfer and weld bead geometry in GMAW,” J. Manuf. Process., vol. 68, pp. 1380–1392, 2021.

L. Deng, Q. Chen, and J. Li, “Thermo-mechanical modeling of residual stress and distortion in GMAW joints,” Materials, vol. 15, no. 3, pp. 1–15, 2022.

M. Farshidianfar, A. Khajepour, and J. Gerlich, “Multi-physics modeling of arc welding processes: Recent developments,” Weld. World, vol. 66, pp. 1–18, 2022.

X. Liu et al., “Hybrid physics-based and data-driven modeling for intelligent arc welding,” IEEE Access, vol. 11, pp. 112345–112356, 2023.

D. C. Montgomery, Introduction to Statistical Quality Control, 8th ed. Hoboken, NJ, USA: Wiley, 2021.

S. Kumar and R. Singh, “Statistical process control applied to arc welding quality monitoring,” J. Manuf. Process., vol. 63, pp. 23–34, 2021.

R. Sharma and P. K. Pal, “Artificial neural network-based prediction of weld bead geometry in GMAW,” J. Intell. Manuf., vol. 34, no. 1, pp. 173–186, 2023.

X. Liu, Y. Zhang, and H. Wang, “Hybrid FEM–ANN modeling for prediction of weld penetration and thermal cycles,” Materials, vol. 15, no. 18, pp. 1–15, 2022.

S. Haykin, Neural Networks and Learning Machines, 4th ed. New York, NY, USA: Pearson, 2021.

D. C. Montgomery, Design and Analysis of Experiments, 10th ed. Hoboken, NJ, USA: Wiley, 2023.

M. Farooq and A. K. Nath, “Optimization of GMAW parameters using response surface methodology,” J. Mater. Process. Technol., vol. 301, pp. 1–10, 2022.

J. Zhou et al., “Data-driven and physics-based hybrid modeling for intelligent welding,” IEEE Access, vol. 11, pp. 99821–99833, 2023.

H.-Y. Chen and C. Chen, “A Study of the Response Surface Methodology Model with Regression Analysis in Three Fields of Engineering,” Appl. Syst. Innov., vol. 8, no. 4, p. 99, 2025, doi:10.3390/asi8040099