Weld Bead Prediction in Electron Beam Welding Using Machine Learning

Weld Bead Prediction in Electron Beam Welding Using Machine Learning
  IJETT-book-cover           
  
© 2025 by IJETT Journal
Volume-73 Issue-1
Year of Publication : 2025
Author : Varimadugu Sandhya, M. Naga Phani Sastry, K. Hema Chandra Reddy
DOI : 10.14445/22315381/IJETT-V73I1P107

How to Cite?
Varimadugu Sandhya, M. Naga Phani Sastry, K. Hema Chandra Reddy, "Weld Bead Prediction in Electron Beam Welding Using Machine Learning," International Journal of Engineering Trends and Technology, vol. 73, no. 1, pp. 86-92, 2025. Crossref, https://doi.org/10.14445/22315381/IJETT-V73I1P107

Abstract
Machine Learning (ML) enhances the effectiveness of process parameter optimization, even in well-established manufacturing industries. By utilizing this data-centric approach, we can unveil the complex and nonlinear patterns present in the data and transform them into models. These models were subsequently utilized to refine and optimize the process parameters. This study focuses on the utilization of machine learning algorithms for forecasting the weld bead geometry in EBW(electron beam welding) of Ti6Al4V. Input weld process parameters considered included accelerating voltage(kV), beam current(mA), and welding speed(m/min). The weld process parameters varied at three different levels through a series of experiments, and the resulting EBW weld bead geometry was measured for each set of input parameters. The source data were analyzed using machine learning techniques, resulting in the creation of a correlation matrix for the process parameters. The analysis revealed a strong positive correlation with the current as a process variable. An extra tree algorithm yielded a higher coefficient of determination than Random Forest and XG Boost.

Keywords
Machine learning, Process parameters, Bead geometry, Correlation, Coefficient of determination.

References

[1] Mukesh Chandra, K.E.K. Vimal, and Sonu Rajak, “A Comparative Study of Machine Learning Algorithms in the Prediction of Bead Geometry in Wire-Arc Additive Manufacturing,” International Journal on Interactive Design and Manufacturing (IJIDeM), vol. 18, no. 9, pp. 6625-6638, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[2] G.O. Ronsch, M. Kulahcia, and M. Dybdahl, “An Investigation of the Utilisation of Different Data Sources in Manufacturing with Application in Injection Moulding,” International Journal of Production Research, vol. 59, no. 16, pp. 4851-4868, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Meng Zhang et al., “High Cycle Fatigue Life Prediction of Laser Additive Manufactured Stainless Steel: A Machine Learning Approach,” International Journal of Fatigue, vol. 128, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Ziyang Zhang, Zhichao Liu, and Dazhong Wu, “Prediction of Melt Pool Temperature in Directed Energy Deposition Using Machine Learning,” Additive Manufacturing, vol. 37, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Tianqi Chen, and Carlos Guestrin, “XGBoost: A Scalable Tree Boosting System,” Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Min, pp. 785-794, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Song-Jeng Huang, Yudhistira Adityawardhana, and Jeffry Sanjaya, “Predicting Mechanical Properties of Magnesium Matrix Composites with Regression Models by Machine Learning,” Journal of Composites Science, vol. 7, no. 9, pp. 1-18, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Yintang Wen et al., “An Improved Meta Heuristic IT2 Fuzzy Model for Nondestructive Failure Evaluation of Metal Additive Manufacturing Lattice Structure,” Expert Systems with Applications, vol. 242, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Jianxiong Gao et al., “A Novel Machine Learning Method for Multiaxial Fatigue Life Prediction: Improved Adaptive Neuro-Fuzzy Inference System, International Journal of Fatigue, vol. 178, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Jesika Rahman et al., “Data-Driven Shear Strength Prediction of Steel Fiber Reinforced Concrete Beams Using Machine Learning Approach,” Engineering Structures, vol. 233, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Fabian Pedregosa et al., “Machine Learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825-2830, 2011.
[Google Scholar] [Publisher Link]
[11] Xiao-Long Gao et al., “A Comparative Study of Pulsed Nd:YAG Laser Welding and TIG Welding of Thin Ti6Al4V Titanium Alloy Plate,” Materials Science and Engineering: A, vol. 559, pp. 14-21, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Kamlesh Kumar, Manoj Masanta, and Santosh Kumar Sahoo, “Microstructure Evolution and Metallurgical Characteristic of Bead-on-Plate TIG Welding of Ti-6Al-4V Alloy,” Journal of Materials Processing Technology, vol. 265, pp. 34-43, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[13] D. Hazen, and David Kazmer, “Multivariate Process Analysis for the Prediction of Injection Molded Part Quality,” ANTEC, Conference Proceedings, vol. 2, 2007.
[Google Scholar]
[14] M.A. Bessa et al., “A Framework for Data-Driven Analysis of Materials under Uncertainty: Countering the Curse of Dimensionality,” Computer Methods in Applied Mechanics and Engineering, vol. 320, pp. 633-667, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Ramin Bostanabad et al., “Stochastic Microstructure Characterization and Reconstruction via Supervised Learning,” Acta Materialia, vol. 103, pp. 89-102, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Mohammed Alarfaj et al., “Machine Learning based Prediction Models for Spilt Tensile Strength of Fiber Reinforced Recycled Aggregate Concrete,” Case Studies in Construction Materials, vol. 20, pp. 1-20, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Won-Jung Oh, Choon-Man Lee, and Dong-Hyeon Kim, “Prediction of Deposition Bead Geometry in Wire Arc Additive Manufacturing Using Machine Learning,” Journal of Materials Research and Technology, vol. 20, pp. 4283-4296, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Ngoc-Hien Tran, Van-Hung Bui, and Van-Thong Hoang, “Development of an Artificial Intelligence-Based System for Predicting Weld Bead Geometry,” Applied Science, vol. 13, no. 7, pp. 1-19, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Junhao Deng et al., “Bead Geometry Prediction for Multi-Layer and Multi-Bead Wire and Arc Additive Manufacturing Based on XGBoost,” Transactions on Intelligent Welding Manufacturing, pp. 125-135, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Vadim Tynchenko et al., “Software for Optimization of Beam Output During Electron Beam Welding of Thin-Walled Structures,” Procedia Computer Science, vol. 200, pp. 843-851, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Vadim S. Tynchenko et al., “Software to Predict the Process Parameters of Electron Beam Welding,” IEEE Access, vol. 9, pp. 92483-92499, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Ran Li, Manshu Dong, and Hongming Gao, “Prediction of Bead Geometry with Changing Welding Speed Using Artificial Neural Network,” Materials, vol. 14, no. 6, pp. 1-9, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Qiyue Wang et al., “A Tutorial on Deep Learning-Based Data Analytics in Manufacturing Through a Welding Case Study,” Journal of Manufacturing Processes, vol. 63, pp. 2-13, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[24] T. DebRoy et al., “Metallurgy, Mechanistic Models and Machine Learning in Metal Printing,” Nature Reviews Materials, vol. 6, no. 1, pp. 48-68, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Ahmed Yaseer, and Heping Chen, “Machine Learning Based Layer Roughness Modeling in Robotic Additive Manufacturing,” Journal of Manufacturing Processes, vol. 70, pp. 543-552, 2021.
[CrossRef] [Google Scholar] [Publisher Link]