The bead profile in the activated tungsten inert gas welding process depends on process parameters and flux composition. Using a conventional statistical-based model, the correlation of these input parameters with the bead shape geometry is complex. Therefore, machine learning-based techniques were implemented to predict the bead shape geometry, that is, penetration (D), width (w), and D/w ratio in the A-TIG welding process of austenitic stainless steel. Random forest regression and classification models were implemented to predict bead shape geometry in the A-TIG welding process. Based on the results, classification-based modeling was appropriate for predicting the bead profile. In addition, the correlation of the process parameters and flux composition with the bead profile was established.
LucasWHowseD. Activating flux-increasing the performance and productivity of the TIG and plasma processes. Weld Metal Fabric2000; 64: 7–10.
2.
LucasW. TIG and plasma welding: process techniques, recommended practices and applications. Cambridge, MA: Woodhead Publishing, 1990.
3.
FujiiHSatoTLuS, et al. Development of an advanced A-TIG (AA-TIG) welding method by control of Marangoni convection. Mater Sci Eng A2008; 495: 296–303.
4.
TsengK-H. Development and application of oxide-based flux powder for tungsten inert gas welding of austenitic stainless steels. Powder Technol2013; 233: 72–79.
5.
VidyarthyRSDwivediDK. Activating flux tungsten inert gas welding for enhanced weld penetration. J Manuf Proc2016; 22: 211–228.
6.
VidyarthyRSDwivediDK. Microstructural and mechanical properties assessment of the P91 A-TIG weld joints. J Manuf Proc2018; 31: 523–535.
7.
VasudevanM. Effect of A-TIG welding process on the weld attributes of type 304LN and 316LN stainless steels. J Mater Eng Perform2017; 26: 1325–1336.
8.
TsengK-HHsuC-Y. Performance of activated TIG process in austenitic stainless steel welds. J Mat Proc Technol2011; 211: 503–512.
9.
VasudevanMBhaduriAKRajB, et al. Genetic-algorithm-based computational models for optimizing the process parameters of A-TIG welding to achieve target bead geometry in type 304 L(N) and 316 L(N) stainless steels. Mat Manuf Proc2007; 22: 641–649.
10.
VidyarthyRSDwivediDKMuthukumaranV. Optimization of A-TIG process parameters using response surface methodology. Mater Manuf Proc2018; 33: 709–717.
11.
AbhilashPMChakradharD. Wire EDM failure prediction and process control based on sensor fusion and pulse train analysis. Int J Adv Manuf Technol2022; 118: 1453–1467.
12.
AbhilashPMChakradharD. Prediction and analysis of process failures by ANN classification during wire-EDM of Inconel 718. Adv Manuf2020; 8: 519–536.
13.
AbhilashPMChakradharD. Performance monitoring and failure prediction system for wire electric discharge machining process through multiple sensor signals. Mach Sci Technol2022; 26: 245–275.
14.
NiyasSWinowlin JappesJTAdamkhanM, et al. An effective approach to predict the minimum tool wear of machining process of Inconel 718. Mat Today Proc2022; 60: 1819–1834.
15.
AbhilashPMChakradharD. ANFIS modelling of mean gap voltage variation to predict wire breakages during wire EDM of Inconel 718. CIRP J Manuf Sci Technol2020; 31: 153–164.
16.
PouraslHHJavidaniMKhojastehnezhadVM, et al. The performance prediction of electrical discharge machining of AISI D6 tool steel using ANN and ANFIS techniques: a comparative study. Crystals2022; 12: 343.
17.
SadaSOIkpeseniSC. Evaluation of ANN and ANFIS modeling ability in the prediction of AISI 1050 steel machining performance. Heliyon2021; 7: e06136.
18.
ThapliyalSMishraA. Machine learning classification-based approach for mechanical properties of friction stir welding of copper. Manuf Lett2021; 29: 52–55.
19.
WangJFYuHDQianYZ, et al. Feature extraction in welding penetration monitoring with arc sound signals. Proc IMechE, Par B: J Engineering Manufacture2011; 225: 1683–1691.
20.
ShahabiHKolahanF. A novel approach for monitoring and improving the quality of welded joint in gas metal arc welding process using adaptive neuro-fuzzy systems. Proc IMechE, Par B: J Engineering Manufacture2016; 230: 1489–1501.
21.
ZhangZLiuWSunX. Image recognition of limited and imbalanced samples based on transfer learning methods for defects in welds. Proc IMechE, Par B: J Engineering Manufacture2022; 236: 1643–1652.
22.
CemernekDCemernekSGurschH, et al. Machine learning in continuous casting of steel: a state-of-the-art survey. J Intell Manuf2022; 33: 1561–1579.
23.
AgrawalADeshpandePDCecenA, et al. Exploration of data science techniques to predict fatigue strength of steel from composition and processing parameters. Integr Mate and Manuf Innov. 2014; 3: 90–108.
24.
DuYMukherjeeTMitraP, et al. Machine learning based hierarchy of causative variables for tool failure in friction stir welding. Acta Materialia2020; 192: 67–77.
25.
DuYMukherjeeTDebRoyT. Conditions for void formation in friction stir welding from machine learning. npj Comput Mat2019; 5: 1–8.
26.
KopperAKarkareRPaffenrothRC, et al. Model selection and evaluation for machine learning: deep learning in materials processing. Integr Mater Manuf Innov2020; 9: 287–300.
27.
PhamDTAfifyAA. Machine-learning techniques and their applications in manufacturing. Proc IMechE, Par B: J Engineering Manufacture2005; 219: 395–412.
28.
VenkatesanGMuthupandiVJustineJ. Activated TIG welding of AISI 304L using mono- and tri-component fluxes. Int J Adv Manuf Technol2017; 93: 329–336.
29.
BodkheSCDolasDR. Optimization of activated tungsten inert gas welding of 304L austenitic stainless steel. Proc Manuf2018; 20: 277–282.
30.
BabbarAKumarAJainV, et al. Enhancement of activated tungsten inert gas (A-TIG) welding using multi-component TiO2-SiO2-Al2O3 hybrid flux. Measurement2019; 148: 106912.
31.
ChandrasekharNVasudevanM. Intelligent modeling for optimization of A-TIG welding process. Mater Manuf Proc2010; 25: 1341–1350.
32.
ShyuSWHuangHYTsengKH, et al. Study of the performance of stainless steel A-TIG welds. J Mat Eng Perform2008; 17: 193–201.
33.
ChandrasekarGKailasanathanCVermaDK, et al. Optimization of welding parameters, influence of activating flux and investigation on the mechanical and metallurgical properties of activated TIG weldments of AISI 316 L stainless steel. Trans Indian Inst Metals2017; 70: 671–684.
34.
DuhanRChoudharyS. Effect of activated flux on properties of SS 304 using TIG welding. Int J Eng2015; 28: 290–295.
35.
RodgersJLNicewanderWA. Thirteen ways to look at the correlation coefficient. Am Stat1988; 42: 59–66.
36.
PedregosaFVaroquauxGGramfortA, et al. Scikit-learn: machine learning in Python. J Mach Learn Res2011; 12: 2825–2830.
37.
KulkarniAChongDBatarsehFA. 5 – Foundations of data imbalance and solutions for a data democracy. In: BatarsehFAYangRBT-DD (eds), Data democracy. Cambridge, MA, US: Academic Press, 2020, pp. 83–106.
38.
MuthukumaranVBhaduriAKRajB. Penetration enhancing flux formulation for tungsten inert gas (TIG) welding of austenitic stainless steel and its application. Patent 8,097,826, USA, 2012.
39.
LuSPQinMPDongWC. Highly efficient TIG welding of Cr13Ni5Mo martensitic stainless steel. J Mat Proc Technol2013; 213: 229–237.
40.
PollardB. The effects of minor elements on the welding characteristics of stainless steel. Weld J1988; 67: 202s–213s.
41.
AidunDKMartinSA. Effect of sulfur and oxygen on weld penetration of high-purity austenitic stainless steels. J Mater Eng Perform1997; 6: 496–502.
42.
BennettWSMillsGS. GTA weldability studies on high manganese stainless steel. Weld J1974; 53: 548–553.
