The Paton Welding Journal, 2025, №03

2025 №03 (01)

DOI of Article 10.37434/tpwj2025.03.02

2025 №03 (03)

---

The Paton Welding Journal, 2025, #3, 13-23 pages

Employing artificial neural networks to estimate weld bead geometry in A-TIG welds

Samarendra Acharya¹, Soumyadip Patra², Santanu Das²

¹Department of Mechanical Engineering, Global Institute of Management and Technology, Krishnanagar-741101, West Bengal, India
²Department of Mechanical Engineering, Kalyani Government Engineering College, Kalyani, 741235, West Bengal, India E-mail: sdas.me@gmail.com

Abstract
The present research explores the effect of ternary oxide flux on Activated-flux Tungsten Inert gas welding of austenitic stainless steel 304. Butt joint welding was performed using three different fluxes (SiO2, TiO2 and Cr2O3) combined in various ratios. Tungsten Inert Gas welding was used to weld 8 mm thick plate of grade 304 stainless steel. Welding parameters such as penetration depth, weld bead width and reinforcement were observed. The experimental results showed that using fluxes SiO2, TiO2 and Cr2O3 resulted in improved weld penetration. Based on the current findings, centripetal Marangoni convection and constricted arc are proposed as mechanisms for enhancing the penetration of activated flux TIG welding. The microstructure of the weldment was investigated using an optical microscope and a Scanning Electron Microscope. The hardness of the weld bead was determined using the Rockwell Hardness Tester. Maximum value of the hardness was found as 66 HRC. The purpose of this work is to investigate the effect of oxide fluxes on weld morphology and welding parameter. Estimation of output parameters using Artificial Neural Network tool in MATLAB17 was done. The dataset was extracted from the experimental work. Heat input, flux ratio and gas flow rate have been investigated as input factors for predicting weld bead width and depth of penetration. In this research, it was found that using ten nodes in a single hidden layer produced the best outcomes. The estimated values of weld bead width and depth of penetration were found to be pretty similar to the experimental observations.
Keywords: welding, activated-flux, A-TIG welding, weld bead geometry, microstructure, hardness, ANOVA (analysis of variance), artificial neural network

Received: 19.11.2024
Received in revised form: 13.03.2025
Accepted: 26.04.2025

References

1. Akhonin, S.V., Bilous, V.Yu., Selin, R.V., Petrychenko, I.K. (2020) Impact of TIG welding on the structure and mechanical properties of joints of pseudo-β-titanium alloy. The Paton Welding J., 2, 9-15. https://doi.org/10.37434/tpwj2020.02.02
2. Kovalenko, D.V., Pavlyak, D.A., Sudnik, V.A., Kovalenko, I.V. (2010) Adequacy of thermohydrodynamic model of through penetration in TIG and A-TIG welding of Nimonic-75 Nickel alloy. The Paton Welding J., 10, 2-6.
3. Dadfar, M., Fathi, M.H., Karimzadeh, F. et al. (2007) Effect of TIG welding on corrosion behavior of 316L stainless steel. Materials Letters, 61, 2343-2346. https://doi.org/10.1016/j.matlet.2006.09.008
4. Mohan, P. (2014) Study of the effects of welding parameters on TIG welding of aluminium plate. Masters Dissertation, NIT Rourkella.
5. Kovalenko, D.V., Kovalenko, I.V., Zaderii, B.O., Zviagintseva, G.V. (2022) Application of A-TIG welding for improving the technology of manufacturing and repair of units of gas turbine engines and installations from titanium alloys. The Paton Welding J., 10, 3-11. https://doi.org/10.37434/tpwj2022.10.01
6. Yushchenko, K.A., Kovalenko, D.V., Kovalenko, I.V. (2001) Application of activators for TIG welding of steels and alloys. The Paton Welding J., 7, 37-43.
7. Kumar, S.A., Sathiya, P. (2015) Experimental investigation of the A-TIG welding process of Incoloy 800H. Materials and Manufacturing Processes, 30, 1154-1159. https://doi.org/10.1080/10426914.2015.1019092
8. Babbar, A., Kumar, A., Jain, V., Gupta, D. (2019) Enhancement of Activated TIG welding using multi component TiO2-SiO2-Al2O3 hybrid flux, Measurement, 148, 106912/1-16 https://doi.org/10.1016/j.measurement.2019.106912
9. Tathgir, S., Bhattacharya, A. (2015) Activated-TIG welding of different steels: Influence of various flux and shielding gas. Materials and Manufacturing Processes, 31, 335-342. https://doi.org/10.1080/10426914.2015.1037914
10. Saha, S., Das, S. (2018) Investigation on the effect of activating flux on tungsten inert gas welding of austenitic stainless steel using AC polarity. Indian Welding J., 51, 84-92. https://doi.org/10.22486/iwj.v51i2.170313
11. Venkatesan, G., George, J., Sownyasri, M., Muthupandi, V. (2014) Effect of ternary fluxes on depth of penetration in A-TIG welding of AISI 409 ferritic stainless steel. Procedia Materials Sci., 5, 2402-2410. https://doi.org/10.1016/j.mspro.2014.07.485
12. Ganesh, K.C., Balasubramanian, K.R., Vasudevan, M. et al. (2016) Effect of multipass TIG and activated TIG welding process on the thermo-mechanical behavior of 316LN stainless steel weld joints. Metallurgical and Materials Transact. B, 47, 1347-1362. https://doi.org/10.1007/s11663-016-0600-6
13. Pamnani, R., Vasudevan, M., Vasantharaja, P., Jayakumar, T. (2015) Optimization of A-GTAW welding parameters for naval steel (DMR 249 A) by design of experiments approach. J. of Materials Design and Applications, 34, 1-12. https://doi.org/10.1177/1464420715596455
14. Kumar, V.B., Lucas, D., Howse, G. et al. (2009) Investigation of the A-TIG mechanism and the productivity benefits in TIG welding. In: Proc. of the Fifteenth Inter. Conf. on the Joining of Materials, 15.
15. Vora, J.J., Badheka, V.J. (2017) Experimental investigation on microstructure and mechanical properties of activated TIG welded reduced activation ferritic/martensitic steel joints. J. of Manufacturing Processes, 25, 85-93. https://doi.org/10.1016/j.jmapro.2016.11.007
16. Kulkarni, A., Dwivedi, D.K., Vasudevan, M. (2019) Dissimilar metal welding of P91 steel-AISI 316L SS with Inconel 800 and Inconel 600 interlayers by using activated TIG welding process and its effect on the microstructure and mechanical properties. J. of Materials Proc. Technol., 274, 116-128. https://doi.org/10.1016/j.jmatprotec.2019.116280
17. Touileb, K., Hedhibi, A.C., Djoudjou, R. et al. (2022) Mechanical, microstructure, and corrosion characterization of dissimilar austenitic 316L and Duplex 2205 stainless-steel AT IG welded joints. Materials, 15, 1-21. https://doi.org/10.3390/ma15072470
18. Howse, D.S., Lucas, W. (2000) Investigation into arc constriction by active fluxes for tungsten inert gas welding. Sci. and Technol. of Welding and Joining, 5, 189-193. https://doi.org/10.1179/136217100101538191
19. Saha,, S., Paul, B.S., Das, S. (2021) Productivity improvement in butt joining of thick stainless steel plates through the usage of activated TIG welding. SN Applied Sci., 3, 416/1-10. https://doi.org/10.1007/s42452-021-04409-7
20. Acharya, S., Das, S. (2023) A review on the use of activating flux in gas tungsten arc welding towards obtaining high productivity. Manufacturing Technology Today, 22, 12-28. https://doi.org/10.58368/MTT.22.7-8.2023.12-28
21. Vidyarthy, R.S., Dwivedi, D.K. (2016) Activating flux tungsten inert gas welding for enhanced weld penetration. J. of Manufacturing Processes, 22, 211-228. https://doi.org/10.1016/j.jmapro.2016.03.012
22. Nanavati, P.K., Badheka, V.J., Idhariya, J., Solanki, D. (2021) Comparisons of different oxide fluxes in activated gas tungsten arc welding of duplex stainless steels for improved depth of penetration and pitting corrosion resistance. Advances in Materials and Processing Technologies, 8, 2533-2550. https://doi.org/10.1080/2374068X.2021.1916283
23. Acharya, S., Gonda, D., Das, S. (2022). Achieving favourable depth of penetration and productivity of AT IG welds utilising the AHP. Indian Sci. Cruiser, 36, 24-30. https://doi.org/10.24906/isc/2022/v36/i5/218005
24. Acharya, S., Gonda, D., Das, S. et al. (2023) Augmentation of depth of penetration and productivity benefits of ATIG welds using the AHP. Inter. J. of Analytical Hierarchy Process, 15, 1-20. https://doi.org/10.13033/ijahp.v15i3.1120
25. Berthier, A., Paillard, P., Carin, M. et al. (2012) TIG and A-TIG welding experimental investigations and comparison to simulation. Sci. and Technol. of Welding and Joining, 17, 609-615. https://doi.org/10.1179/1362171812Y.0000000024
26. Vora, J.J., Abhishek, K., Srinivasan, S. (2015) Attaining optimized AT IG welding parameters for carbon steels by advanced parameter-less optimization techniques: with experimental validation. J. of the Brazilian Society of Mechanical Sci. and Eng., 41, 260-280. https://doi.org/10.1007/s40430-019-1765-0
27. Gurevich, S.M., Zamkov, V.N., Kushnirenko, N.A. (1965) Improving the penetration of titanium alloys when they are welded by argon tungsten arc process. Avtomaticheskaya Svarka, 9, 1-4.
28. Ates, H. (2007) Prediction of gas metal arc welding parameters based on artificial neural networks. Materials & Design, 28, 2015-2023. https://doi.org/10.1016/j.matdes.2006.06.013
29. Pal, S., Pal, S.K., Samantaray, A.K. (2008) Artificial neural network modelling of weld joint strength prediction of a pulsed metal inert gas welding process using arc signals. J. of Materials Proc. Technology, 202, 464-474. https://doi.org/10.1016/j.jmatprotec.2007.09.039
30. Nagesh,D.S., Datta, G. L. (2010) Genetic algorithm for optimization of welding variables for height to width ratio and application of ANN for prediction in TIG welding process. Applied Soft Computing, 10, 897-907. https://doi.org/10.1016/j.asoc.2009.10.007
31. Owunna, I., Ikpe, A.E. (2019) Modeling and prediction of the mechanical properties of TIG weld joint for AISI 4130 low carbon steel plates using artificial neural network (ANN) approach. Nigerian J. of Technology, 38, 117-126. https://doi.org/10.4314/njt.v38i1.16
32. Acharya, S., Gonda, D., Das, S. (2024) Artificial neural networks based prediction of penetration in activated tungsten inert gas welding. Indian Welding J., 5, 71-79. https://doi.org/10.22486/iwj.v57i1.223729
33. Acharya, S., Patra, S., Das, S. (2024). Predicting A-TIG weld bead geometry using artificial neural networks. 4, 12. https://doi.org/10.21203/rs.3.rs-5277673/v1

---

Suggested Citation

Samarendra Acharya, Soumyadip Patra, Santanu Das (2025) Employing artificial neural networks to estimate weld bead geometry in A-TIG welds. The Paton Welding J., 03, 13-23.

---