Hybrid ANN–PSO-intelligent model for Optimization of Tensile Strength in Shielded Metal Arc Welding of Carbon Steel
DOI:
https://doi.org/10.36602/ijeit.v14i2.627Keywords:
arc force (AF), ultimate tensile strength (UTS), base metal (BM), heat-affected zone (HAZ), weld metal (WM), Artificial Neural Network (ANN), Particle swarm optimization (PSO),Root mean squared error (RMSE)Abstract
Welding is a critical manufacturing process extensively used in structural and heavy industrial applications, where the mechanical performance of joints directly impacts safety, reliability, and operational efficiency. This study systematically investigates the combined effects of welding current, arc force, and electrode diameter on the ultimate tensile strength (UTS) and hardness distribution across the base metal (BM), heat-affected zone (HAZ), and weld metal (WM) of low-carbon steel joints. This study provides a novel integration of experimental Taguchi design with ANN–PSO optimization for shielded metal arc welding (SMAW) under realistic industrial conditions. A Taguchi L27 experimental design was employed to evaluate the influence of process parameters. Tensile tests and hardness measurements were conducted to characterize joint performance. An artificial neural network (ANN) model was developed to predict UTS, and particle swarm optimization (PSO) was applied to identify optimal process parameters. The proposed ANN–PSO framework predicted an optimal UTS of 209.33 MPa at a welding current of 86.5763 A, arc force of 17.2486%, and electrode diameter of 3.3545 mm. The model demonstrated acceptable predictive capability, with a correlation coefficient (R) of 0.79241 and RMSE of 10.488. The findings provide practical insights into welding parameter selection and demonstrate the potential of hybrid optimization techniques for improving joint performance in industrial applications.
Downloads
References
[2] Lancaster, J.F., the Physics of Welding, Pergamon Press, 1986.
[3] Kim, I.S. et al., “Optimization of welding parameters for tensile strength in GMA welding”, Journal of Materials Processing Technology, 2003.
[4] Murugan, N., Parmar, R.S., “Effects of MIG process parameters on the geometry of the bead in steel plates”, Journal of Materials Processing Technology, 1994.
[5] Ross, P.J., Taguchi Techniques for Quality Engineering, McGraw-Hill, 1996.
[6] Lakshminarayanan, A.K., Balasubramanian, V., “Process parameter optimization for friction stir welding using Taguchi technique”, Materials & Design, 2008.
[7] Alkhwaji, A. I., BenIsa, M. M., & Aswihli, H. A. (2024). Estimating tool life from measurements during longitudinal turning process using linear least squares. Sebha University Journal of Pure & Applied Sciences, 23(1). https://doi.org/10.51984/JOPAS.V23I1.2888.
[8] Ben Isa, M. M., Aswihli, H. A., & Alkhwaji, A. I. (2021). Experimental Investigation of Cutting Parameters Effect on Surface Roughness During Wet and Dry Turning of Low Carbon Steel Material. Journal of Academic Research (Applied Sciences), 17.
[9] Akhtar, M., Alkhwaji, A. I., et al. (2021). Optimization of Process Parameters in CNC Turning of Aluminum 7075 Alloy Using L27 Array-Based Taguchi Method. Materials, 14(4470). https://doi.org/10.3390/ma14164470.
[10] Sivaraman, R., et al. (2020). A Study of the Optimum Cutting Parameters for The Surface Roughness in A Longitudinal Turning of Aluminum Alloy Using Taguchi Method. Journal of Alasmarya University: Basic and Applied Sciences, 6(5).
[11] Benyounis, K.Y., Olabi, A.G., “Optimization of different welding processes using statistical and numerical approaches”, Advances in Engineering Software, 2008.
[12] Tarng, Y.S., Yang, W.H., “Optimization of the weld bead geometry in gas tungsten arc welding by the Taguchi method”, International Journal of Advanced Manufacturing Technology, 1998.
[13] Rao, R.S., Kumar, C.G., Prakasham, R.S., Hobbs, P.J., “The Taguchi methodology as a statistical tool for biotechnological applications”, Biotechnology Journal, 2008.
[14] Haykin, S. Neural Networks and Learning Machines, 3rd ed., Pearson Education, 2009.
[15] Balasubramanian, V., Ravisankar, V., Madhusudhan Reddy, G., “Effect of welding processes on microstructure, tensile and impact properties of high strength low alloy steel joints”, Journal of Materials Engineering and Performance, 2008.
[16] Mattera, G., Chozaki, S. P., Norrish, J., “Advances in machine learning for parameters optimisation and in-situ monitoring of wire arc additive manufacturing,” Welding in the World, Vol. 70, pp. 1173–1202\, 2026. https://doi.org/10.1007/s40194-025-02200-5.
[17] Van, A.-L., Nguyen, T.-T., Dang, X.-B., “A Sustainable Gas Metal Arc Welding Operation: Machine Learning Models-Based Experiment and Optimization of Welded Carbon Steels,” Welding International, Vol. 39, No. 5, pp. 348–366, 2025. https://doi.org/10.1080/09507116.2025.2464696.
Downloads
Published
License
Copyright (c) 2026 The International Journal of Engineering & Information Technology (IJEIT)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
