Advancing Welding Quality through Intelligent TIG Welding: A Hybrid Deep Learning Approach for Defect Detection and Quality Monitoring

Year 2025, Volume: 16 Issue: 3, 677 - 685

Emre Görgün

https://doi.org/10.24012/dumf.1642978

Abstract

Modern welding procedures are intricate, requiring a variety of variables and occasionally lacking a complete understanding of their underlying mechanics. Despite the adoption of intelligent welding processes in a few applications, there are still several obstacles. By combining advanced search, combinatorial optimisation, geometric reasoning techniques, and comprehensive Artificial Intelligence (AI) modelling cognitive capabilities, the proposed research aims to build intelligent welding. The three main scientific foci of the research are feature correlation to forecast process performance and facilitate corrective actions, feature extraction utilising intense signal analysis, and the use of simulated or supplied data for analysis. Previous research led to the development of an intelligent Tungsten Inert Gas (TIG) welding platform for materials made of aluminium. On the other hand, TIG welding is susceptible to fluctuations in the root gap, which affect the quality of the weld and could result in electrode contamination. Common welding errors include excessive heat-affected zone width, fusion width, bead height, and inadequate penetration. These errors directly affect the strength and load-bearing capacity of the joint while also making it more susceptible to stress and fracture propagation. The proposed AI-powered welding tool is made to overcome common weld imperfections. Therefore, the research's objective is to develop a hybrid deep learning-powered platform for TIG welding. Convolutional Neural Networks (CNNs) will be employed to extract discrete visual characteristics linked to each type of weld defect, establish correlations between these features, and give weld images to identify the types of defects or their absence. The objective of the research is to create a neural network model that can determine whether a given weld image is good or bad due to contamination, burn-through, or lack of fusion. These findings will make precise weld quality monitoring and process improvement possible.

Keywords

Artificial Intelligence , Convolutional Neural Networks , Deep Learning , Tungsten Inert Gas , Welding

References

• [1] A. W. Fande, R. V. Taiwade, and L. Raut, ‘Development of activated tungsten inert gas welding and its current status: A review’, Jun. 11, 2022, Taylor & Francis. doi: 10.1080/10426914.2022.2039695.
• [2] E. A. Gyasi, H. Handroos, and P. Kah, ‘Survey on artificial intelligence (AI) applied in welding: A future scenario of the influence of AI on technological, economic, educational and social changes’, in Procedia Manufacturing, Elsevier, Jan. 2019, pp. 702–714. doi: 10.1016/j.promfg.2020.01.095.
• [3] D. Sarwinda, R. H. Paradisa, A. Bustamam, and P. Anggia, ‘Deep Learning in Image Classification using Residual Network (ResNet) Variants for Detection of Colorectal Cancer’, in Procedia Computer Science, Elsevier, Jan. 2021, pp. 423–431. doi: 10.1016/j.procs.2021.01.025.
• [4] A. Sirco, A. Almisreb, N. M. Tahir, and J. Bakri, ‘Liver Tumour Segmentation based on ResNet Technique’, in ICCSCE 2022 - Proceedings: 2022 12th IEEE International Conference on Control System, Computing and Engineering, Institute of Electrical and Electronics Engineers Inc., 2022, pp. 203–208. doi: 10.1109/ICCSCE54767.2022.9935636.
• [5] N. Saleem, J. Gao, M. Irfan, E. Verdu, and J. P. Fuente, ‘E2E-V2SResNet: Deep residual convolutional neural networks for end-to-end video driven speech synthesis’, Image and Vision Computing, vol. 119, p. 104389, Mar. 2022, doi: 10.1016/j.imavis.2022.104389.
• [6] M. H. R. Sobuz, M. K. I. Kabbo, T. S. Alahmari, J. Ashraf, E. Gorgun, and M. M. H. Khan, ‘Microstructural behavior and explainable machine learning aided mechanical strength prediction and optimization of recycled glass-based solid waste concrete’, Case Studies in Construction Materials, p. e04305, 2025.
• [7] A. Mayr, M. Weigelt, M. Masuch, M. Meiners, F. Hüttel, and J. Franke, ‘Application Scenarios of Artificial Intelligence in Electric Drives Production’, in Procedia Manufacturing, Elsevier, Jan. 2018, pp. 40–47. doi: 10.1016/j.promfg.2018.06.006.
• [8] E. Gorgun, ‘Numerical analysis of inflow turbulence intensity impact on the stress and fatigue life of vertical axis hydrokinetic turbine’, Physics of Fluids, vol. 36, no. 1, 2024, Accessed: Mar. 06, 2024. [Online]. Available: https://pubs.aip.org/aip/pof/article/36/1/015111/2932752.
• [9] E. Görgün, ‘Çoklu Yükleme Koşulları Altında Yük Vagonu Şasisinin Topoloji Optimizasyonu’, Karadeniz Fen Bilimleri Dergisi, vol. 12, no. 2, pp. 593–604, Dec. 2022, doi: 10.31466/kfbd.1078425.
• [10] E. Görgün, ‘Ultrasonik Muayene Prob Çaplarının Darbe Yankı Değerine Etkisinin Araştırılması’, Karadeniz Fen Bilimleri Dergisi, vol. 12, no. 1, pp. 381–389, 2022.
• [11] E. Görgün, ‘Investigation of The Effect of SMAW Parameters On Properties of AH36 Joints and The Chemical Composition of Seawater’, International Journal of Innovative Engineering Applications, vol. 8, no. 1, pp. 28–36, 2024.
• [12] E. Gorgun, ‘Ultrasonic testing and surface conditioning techniques for enhanced thermoplastic adhesive bonds’, J Mech Sci Technol, vol. 38, no. 3, pp. 1227–1236, Mar. 2024, doi: 10.1007/s12206-024-0218-6.
• [13] E. Gorgun, A. Ali, and Md. S. Islam, ‘Biocomposites of Poly(Lactic Acid) and Microcrystalline Cellulose: Influence of the Coupling Agent on Thermomechanical and Absorption Characteristics’, ACS Omega, vol. 9, no. 10, pp. 11523–11533, Mar. 2024, doi: 10.1021/acsomega.3c08448.
• [14] D. Vijayan and V. Seshagiri Rao, ‘Process Parameter Optimization in TIG Welding of AISI 4340 Low Alloy Steel Welds by Genetic Algorithm’, in IOP Conference Series: Materials Science and Engineering, IOP Publishing, Jul. 2018, p. 012066. doi: 10.1088/1757-899X/390/1/012066.
• [15] TWI, ‘What is Tungsten Inert Gas (GTAW or TIG) Welding?’, Job Knowledge 6. Accessed: Sep. 28, 2023. [Online]. Available: https://www.twi-global.com/technical-knowledge/job-knowledge/tungsten-inert-gas-tig-or-gta-welding-006
• [16] Z. Abbasi et al., ‘The Detection of Burn-Through Weld Defects Using Noncontact Ultrasonics’, Materials 2018, Vol. 11, Page 128, vol. 11, no. 1, p. 128, Jan. 2018, doi: 10.3390/MA11010128.
• [17] B. Wang, S. J. Hu, L. Sun, and T. Freiheit, ‘Intelligent welding system technologies: State-of-the-art review and perspectives’, Jul. 01, 2020, Elsevier. doi: 10.1016/j.jmsy.2020.06.020.
• [18] R. Tsuzuki, ‘Development of automation and artificial intelligence technology for welding and inspection process in aircraft industry’, Jan. 01, 2022, Springer Science and Business Media Deutschland GmbH. doi: 10.1007/s40194-021-01210-3.
• [19] M. A. Kesse, E. Buah, H. Handroos, and G. K. Ayetor, ‘Development of an artificial intelligence powered tig welding algorithm for the prediction of bead geometry for tig welding processes using hybrid deep learning’, Metals, vol. 10, no. 4, p. 451, Mar. 2020, doi: 10.3390/met10040451.
• [20] S. Wazir, G. S. Kashyap, and P. Saxena, ‘MLOps: A Review’, Aug. 2023.
• [21] N. Marwah, V. K. Singh, G. S. Kashyap, and S. Wazir, ‘An analysis of the robustness of UAV agriculture field coverage using multi-agent reinforcement learning’, International Journal of Information Technology (Singapore), vol. 15, no. 4, pp. 2317–2327, May 2023, doi: 10.1007/s41870-023-01264-0.
• [22] W. Ji and L. Wang, ‘Industrial robotic machining: a review’, International Journal of Advanced Manufacturing Technology, vol. 103, no. 1–4, pp. 1239–1255, Apr. 2019, doi: 10.1007/s00170-019-03403-z.
• [23] S. H. Kim et al., ‘Robotic Machining: A Review of Recent Progress’, International Journal of Precision Engineering and Manufacturing, vol. 20, no. 9, pp. 1629–1642, Sep. 2019, doi: 10.1007/S12541-019-00187-W/FIGURES/12.
• [24] M. H. M. Ali and M. R. Atia, ‘A lead through approach for programming a welding arm robot using machine vision’, Robotica, vol. 40, no. 3, pp. 464–474, Mar. 2022, doi: 10.1017/S026357472100059X.
• [25] N. Oh and H. Rodrigue, ‘Toward the Development of Large-Scale Inflatable Robotic Arms Using Hot Air Welding’, Soft Robotics, vol. 10, no. 1, pp. 88–96, Feb. 2023, doi: 10.1089/soro.2021.0134.
• [26] A. Ghosh, D. Chakraborty, and A. Law, ‘Artificial intelligence in Internet of things’, Dec. 01, 2018, The Institution of Engineering and Technology. doi: 10.1049/trit.2018.1008.
• [27] G. S. Kashyap, K. Malik, S. Wazir, and R. Khan, ‘Using Machine Learning to Quantify the Multimedia Risk Due to Fuzzing’, Multimedia Tools and Applications, vol. 81, no. 25, pp. 36685–36698, Oct. 2022, doi: 10.1007/s11042-021-11558-9.
• [28] Z. Guo, Y. Sun, M. Jian, and X. Zhang, ‘Deep residual network with sparse feedback for image restoration’, Applied Sciences (Switzerland), vol. 8, no. 12, p. 2417, Nov. 2018, doi: 10.3390/app8122417.
• [29] D. Das, D. K. Pratihar, G. G. Roy, and A. R. Pal, ‘Phenomenological model-based study on electron beam welding process, and input-output modeling using neural networks trained by back-propagation algorithm, genetic algorithms, particle swarm optimization algorithm and bat algorithm’, Applied Intelligence, vol. 48, no. 9, pp. 2698–2718, Sep. 2018, doi: 10.1007/s10489-017-1101-2.
• [30] C. Xia, Z. Pan, Z. Fei, S. Zhang, and H. Li, ‘Vision based defects detection for Keyhole TIG welding using deep learning with visual explanation’, Journal of Manufacturing Processes, vol. 56, pp. 845–855, Aug. 2020, doi: 10.1016/j.jmapro.2020.05.033.
• [31] D. Bacioiu, G. Melton, M. Papaelias, and R. Shaw, ‘Automated defect classification of Aluminium 5083 TIG welding using HDR camera and neural networks’, Journal of Manufacturing Processes, vol. 45, pp. 603–613, Sep. 2019, doi: 10.1016/j.jmapro.2019.07.020.