Abstract
As complete elimination of porosity from the weld is very difficult, the next option available is to minimize this weld porosity, which is crucial for the safe performance of the welded components. However, this investigation through experiments alone is very tedious and time consuming. Additionally, very limited models are available in the literature for accurate prediction of different porosity attributes. The present study, thus, addressees both the experimental as well as modelling aspect on the study of micro-porosity during electron beam welding (EBW) of SS304 plates. Welding parameters are reported to have significant influence on the micro-porosity. Hence, the influences of these parameters on micro-porosity attributes, namely pores number, average diameter, and sphericity are extensively studied experimentally employing optical microscopy (OM), scanning electron microscopy (SEM), X-ray computed tomography (XCT), and Raman spectroscopy. This is followed by an elaborate modelling using seven popular and well-recognized machine learning algorithms (MLAs), namely multi-layer perceptron (MLP), support vector regression (SVR), M5P model trees regression, reduced error pruning tree (REPTree), random forest (RF), instance-based k-nearest neighbor algorithm (IBk), and locally weighted learning (LWL). These different techniques enhance the chance of obtaining the better predictions of the said micro-porosity attributes by overcoming the effect of data-dependence and other limitations of individual MLAs. The different model-predicted micro-porosity data are also validated through experimental data. Statistical tests and Monte-Carlo reliability analysis are additionally utilized to evaluate the performances of the employed algorithms. IBk and MLP are overall found to perform well.
Similar content being viewed by others
Data availability
The data and materials will be made available to others on request, after it is accepted for publications.
Abbreviations
- \({A}_{ar}\) :
-
Pore surface area
- \({D}_{p}\) :
-
Average pore diameter
- E :
-
Heat input per unit length
- I :
-
Beam current
- L :
-
Total number of welding conditions
- \({N}_{p}\) :
-
Number of pores
- \({N}_{success}\) :
-
Number of successful conditions
- \({N}_{total}\) :
-
Total number of conditions
- \({O}_{{ok}^{^{\prime}}l}\) :
-
Predicted outputs
- \({\overline{O} }_{o{k}^{^{\prime}}l}\) :
-
Mean of outputs
- \({P}_{occurrence}\) :
-
Probability of success
- \({R}^{2}\) :
-
Correlation coefficient
- \({S}_{phry}\) :
-
Average pore sphericity
- \({T}_{{ok}^{^{\prime}}l}\) :
-
Target outputs
- U :
-
Welding speed
- V :
-
Accelerating voltage
- \({V}_{ol}\) :
-
Pore volume
- AAPD :
-
Average absolute percent deviation
- ANN :
-
Artificial neural network
- C-LBW :
-
Continuous laser beam welding
- CV :
-
Cross-validation
- DOE :
-
Design of experiments
- EBW :
-
Electron beam welding
- GTAW :
-
Gas tungsten arc welding
- IBk :
-
Instance-based k-nearest neighbor algorithm
- k-NN :
-
k-Nearest neighbor
- LBW :
-
Laser beam welding
- LWL :
-
Locally weighted learning
- M5P :
-
Model trees regression following M5 algorithm
- MLAs :
-
Machine learning algorithms
- MLP :
-
Multi-layer perceptron
- NDT :
-
Non-destructive testing
- OM :
-
Optical microscopy
- P-LBW :
-
Pulsed laser beam welding
- REPTree :
-
Reduced error pruning tree
- RF :
-
Random forest
- RMSE :
-
Root mean square error
- SEM :
-
Scanning electron microscopy
- SVR :
-
Support vector regression
- XCT :
-
X-ray computed tomography
References
Feng S, Zhou H, Dong H (2019) Using deep neural network with small dataset to predict material defects. Mater Des 162:300–310. https://doi.org/10.1016/j.matdes.2018.11.060
Mathew J, Griffin J, Alamaniotis M et al (2018) Prediction of welding residual stresses using machine learning: Comparison between neural networks and neuro-fuzzy systems. Appl Soft Comput J 70:131–146. https://doi.org/10.1016/j.asoc.2018.05.017
Das D, Pal AR, Das AK et al (2020) Nature-inspired optimization algorithm-tuned feed-forward and recurrent neural networks using CFD-based phenomenological model-generated data to model the EBW process. Arab J Sci Eng 45:2779–2797. https://doi.org/10.1007/s13369-019-04142-9
Das D, Pratihar DK, Roy GG, Pal AR (2018) 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. Appl Intell 48:2698–2718. https://doi.org/10.1007/s10489-017-1101-2
Das D, Pratihar DK, Roy GG (2018) Cooling rate predictions and its correlation with grain characteristics during electron beam welding of stainless steel. Int J Adv Manuf Technol 97:2241–2254. https://doi.org/10.1007/s00170-018-2095-6
Vilar R, Zapata J, Ruiz R (2009) An automatic system of classification of weld defects in radiographic images. NDT E Int 42:467–476. https://doi.org/10.1016/j.ndteint.2009.02.004
Hou W, Wei Y, Jin Y, Zhu C (2019) Deep features based on a DCNN model for classifying imbalanced weld flaw types. Measurement 131:482–489. https://doi.org/10.1016/j.measurement.2018.09.011
Lu F, Li X, Li Z et al (2015) Formation and influence mechanism of keyhole-induced porosity in deep-penetration laser welding based on 3D transient modeling. Int J Heat Mass Transf 90:1143–1152. https://doi.org/10.1016/j.ijheatmasstransfer.2015.07.041
Sun J, Nie P, Lu F et al (2017) The characteristics and reduction of porosity in high-power laser welds of thick AISI 304 plate. Int J Adv Manuf Technol 93:3517–3530. https://doi.org/10.1007/s00170-017-0734-y
Wang J, Wang GZ, Wang CM (2015) Mechanisms of the porosity formation during the fiber laser lap welding of aluminium alloy. Metalurgija 54:683–686
Junaid M, Rahman K, Khan FN et al (2019) Comparison of microstructure, mechanical properties, and residual stresses in tungsten inert gas, laser, and electron beam welding of Ti–5Al–2.5Sn titanium alloy. Proc Inst Mech Eng Part L J Mater Des Appl 233:1336–1351. https://doi.org/10.1177/1464420717748345
Hou J, Li R, Xu C et al (2021) A comparative study on microstructure and properties of pulsed laser welding and continuous laser welding of Al-25Si-4Cu-Mg high silicon aluminum alloy. J Manuf Process 68:657–667. https://doi.org/10.1016/j.jmapro.2021.05.064
Short AB (2009) Gas tungsten arc welding of α + β titanium alloys: A review. Mater Sci Technol 25:309–324. https://doi.org/10.1179/174328408X389463
Ragavendran M, Vasudevan M (2020) Laser and hybrid laser welding of type 316L(N) austenitic stainless steel plates. Mater Manuf Process 35:922–934. https://doi.org/10.1080/10426914.2020.1745231
Dinda SK, Warnett JM, Williams MA et al (2016) 3D imaging and quantification of porosity in electron beam welded dissimilar steel to Fe-Al alloy joints by X-ray tomography. Mater Des 96:224–231. https://doi.org/10.1016/j.matdes.2016.02.010
Elmer JW, Vaja J, Carlton HD, Pong R (2015) The effect of Ar and N 2 shielding gas on laser weld porosity in steel, stainless steels, and nickel. Weld J 94:313–325
Lisiecki A (2016) Effect of heat input during disk laser bead-on-plate welding of thermomechanically rolled steel on penetration characteristics and porosity formation in the weld metal. Arch Metall Mater 61:93–102. https://doi.org/10.1515/amm-2016-0019
Blecher J, Palmer T, Debroy T (2015) Mitigation of root defect in laser and hybrid laser-arc welding. Weld Res 94:73-s-82-s
Bandi B, Dinda SK, Kar J et al (2018) Effect of weld parameters on porosity formation in electron beam welded Zircaloy-4 joints: X-ray tomography study. Vacuum 158:172–179. https://doi.org/10.1016/j.vacuum.2018.09.060
Dinda SK, kar J, Jana S, et al (2019) Effect of beam oscillation on porosity and intermetallics of electron beam welded DP600-steel to Al 5754-alloy. J Mater Process Technol 265:191–200. https://doi.org/10.1016/j.jmatprotec.2018.10.026
Ramanujam T, Devai HP, Gopi M et al (2018) Porosity studies on electron beam welding of copper alloys. Int J Mech Eng Technol 9:586–593
Alshaer AW, Li L, Mistry A (2014) Understanding the effect of heat input and sheet gap on porosity formation in fillet edge and flange couch laser welding of AC-170PX aluminum alloy for automotive component manufacture. J Manuf Sci Eng 137:021011. https://doi.org/10.1115/1.4028900
Zhan X, Qi C, Gao Z et al (2019) The influence of heat input on microstructure and porosity during laser cladding of Invar alloy. Opt Laser Technol 113:453–461. https://doi.org/10.1016/j.optlastec.2019.01.015
Xie MX, Li YX, Shang XT et al (2019) Effect of heat input on porosity defects in a fiber laser welded socket-joint made of powder metallurgy molybdenum alloy. Materials (Basel). https://doi.org/10.3390/ma12091433
Jha MN, Pratihar DK, Dey V et al (2011) Study on electron beam butt welding of austenitic stainless steel 304 plates and its input-output modelling using neural networks. Proc Inst Mech Eng Part B-J Eng Manuf 225:2051–2070. https://doi.org/10.1177/0954405411404856
Petkovi D (2017) Prediction of laser welding quality by computational intelligence approaches. Optik (Stuttg) 140:597–600. https://doi.org/10.1016/j.ijleo.2017.04.088
Liang R, Yu R, Luo Y, Zhang YM (2019) Machine learning of weld joint penetration from weld pool surface using support vector regression. J Manuf Process 41:23–28. https://doi.org/10.1016/j.jmapro.2019.01.039
Boersch I, Füssel U, Gresch C et al (2018) Data mining in resistance spot welding: A non-destructive method to predict the welding spot diameter by monitoring process parameters. Int J Adv Manuf Technol 99:1085–1099. https://doi.org/10.1007/s00170-016-9847-y
Ghanty P, Paul S, Mukherjee DP et al (2007) Modelling weld bead geometry using neural networks for GTAW of austenitic stainless steel. Sci Technol Weld Join 12:649–658. https://doi.org/10.1179/174329307X238399
Munir N, Kim H, Park J et al (2018) Convolutional neural network for ultrasonic weldment flaw classification in noisy conditions. Ultrasonics. https://doi.org/10.1016/j.ultras.2018.12.001
Wang G, Liao TW (2002) Automatic identification of different types of welding defects in radiographic images. Ndt E Int 35:519–528
Liao TW, Triantaphyllou E, Chang PC (2003) Detection of Welding Flaws With MLP Neural Network and Case Based Reasoning. Intell Autom Soft Comput 4:259–267. https://doi.org/10.1080/10798587.2000.10642858
Das D, Jaypuria S, Pratihar DK, Roy GG (2021) Weld optimisation (Review). Sci Technol Weld Join. https://doi.org/10.1080/13621718.2021.1872856
Namlı E, Erdal H, Erdal HI (2019) Artificial intelligence-based prediction models for energy performance of residential buildings. In: Balkaya N, Guneysu S (eds) Recycling and Reuse Approaches for Better Sustainability. Springer International Publishing, Cham, Switzerland, p 304
Özçift A (2014) Forward stage-wise ensemble regression algorithm to improve base regressors prediction ability: An empirical study. Expert Syst 31:1–8. https://doi.org/10.1111/j.1468-0394.2012.00643.x
Maji K (2014) Analysis and Synthesis of Sheet Metal Forming by Laser Heating Using Finite Element Method and Soft Computing (Doctoral dissertation, IIT Kharagpur). http://www.idr.iitkgp.ac.in/xmlui/handle/123456789/3780
Haykin S (2005) Neural networks - a comprehensive foundation. Pearson Education (Singapore) Pte. Ltd., New-Delhi, India, 2001
Das D, Das AK, Pratihar DK, Roy GG (2021) Prediction of residual stress in electron beam welding of stainless steel from process parameters and natural frequency of vibrations using machine-learning algorithms. Proc Inst Mech Eng Part C J Mech Eng Sci 235:2008–2021. https://doi.org/10.1177/0954406220950343
Xia X, Wu J, Liu Z et al (2019) Study of microstructure difference properties of electron beam welds with beam oscillation of 50 mm 316L in CFETR. Fusion Eng Des 138:339–346. https://doi.org/10.1016/j.fusengdes.2018.12.011
Fu P, Mao Z, Zuo C et al (2014) Microstructures and fatigue properties of electron beam welds with beam oscillation for heavy section TC4-DT alloy. Chinese J Aeronaut 27:1015–1021. https://doi.org/10.1016/j.cja.2014.03.020
Das D, Pratihar DK, Roy GG (2020) Establishing a correlation between residual stress and natural frequency of vibration for electron beam butt weld of AISI 304 stainless steel. Arab J Sci Eng 45:5769–5781. https://doi.org/10.1007/s13369-020-04560-0
Das D, Pratihar DK, Roy GG (2022) Modeling of beam divergence Optik (Stuttg) 256:168747. https://doi.org/10.1016/j.ijleo.2022.168747
Das D, Pratihar DK, Roy GG (2016) Electron beam melting of steel plates: Temperature measurement using thermocouples and prediction through finite element analysis. In: Mandal DK, Syan CS (eds) CAD/CAM, Robotics and Factories of the Future. Springer, New Delhi, pp 579–588
Chen YY, Duval T, Hung UD et al (2005) Microstructure and electrochemical properties of high entropy alloys-a comparison with type-304 stainless steel. Corros Sci 47:2257–2279. https://doi.org/10.1016/j.corsci.2004.11.008
Kumar S, Shahi AS (2011) Effect of heat input on the microstructure and mechanical properties of gas tungsten arc welded AISI 304 stainless steel joints. Mater Des 32:3617–3623. https://doi.org/10.1016/j.matdes.2011.02.017
Das D (2020) Predictive tools for bead-geometry, cooling rate, micro-porosity, natural frequency of vibration and residual stress in electron beam welded stainless steel plates (Doctoral dissertation, IIT Kharagpur). Indian Institute of Technology Kharagpur, India
James TM, Rupp S, Telle HH (2015) Trace gas and dynamic process monitoring by Raman spectroscopy in metal-coated hollow glass fibres. Anal Methods 7:2568–2576. https://doi.org/10.1039/c4ay02597k
Buric MP (2011) Gas phase raman spectroscopy using hollow waveguides (Doctoral dissertation, Swanson School of Engineering). University of Pittsburgh, United States
Leitch AWR, Alex V, Weber J (1998) Raman spectroscopy of hydrogen molecules in crystalline silicon. Phys Rev Lett 81:421
Das D, Pratihar DK, Roy GG (2020) Effects of space charge on weld geometry and cooling rate during electron beam welding of stainless steel. Optik (Stuttg) 206:163722. https://doi.org/10.1016/j.ijleo.2019.163722
Ren W, Lu F, Yang R et al (2015) A comparative study on fiber laser and CO2 laser welding of Inconel 617. Mater Des 76:207–214. https://doi.org/10.1016/j.matdes.2015.03.033
OdabaşI A, Ünlü N, Göller G, Eruslu MN (2010) A study on laser beam welding (LBW) technique: Effect of heat input on the microstructural evolution of superalloy inconel 718. Metall Mater Trans A Phys Metall Mater Sci 41:2357–2365. https://doi.org/10.1007/s11661-010-0319-y
Graczyk M, Lasota T, Trawinski B (2009) Comparative analysis of premises valuation models using KEEL, RapidMiner, and WEKA. International conference on computational collective intelligence. Springer, Berlin Heidelberg, pp 800–812
Hsieh CH, Lu RH, Lee NH et al (2011) Novel solutions for an old disease: Diagnosis of acute appendicitis with random forest, support vector machines, and artificial neural networks. Surgery 149:87–93. https://doi.org/10.1016/j.surg.2010.03.023
Amrehn M, Mualla F, Angelopoulou E et al (2018) The random forest classifier in WEKA: Discussion and new developments for imbalanced data. arXiv Prepr arXiv:1812.08102
Zahara SI, Ilyas M, Zia T (2013) A study of comparative analysis of regression algorithms for reusability evaluation of object oriented based software components. ICOSST 2013 - 2013 Int Conf Open Source Syst Technol Proc 1:75–80. https://doi.org/10.1109/ICOSST.2013.6720609
Alam I, Farid DM, Rossetti RJF (2019) The prediction of traffic flow with regression analysis. In emerging technologies in data mining and information security. Springer Singapore, pp 661–671
Martín Ó, Pereda M, Santos JI, Galán JM (2014) Assessment of resistance spot welding quality based on ultrasonic testing and tree-based techniques. J Mater Process Technol 214:2478–2487. https://doi.org/10.1016/j.jmatprotec.2014.05.021
Xing B, Xiao Y, Qin QH, Cui H (2018) Quality assessment of resistance spot welding process based on dynamic resistance signal and random forest based. Int J Adv Manuf Technol 94:327–339. https://doi.org/10.1007/s00170-017-0889-6
Göndör M, Bresfelean VP (2012) REPTree and M5P for measuring fiscal policy influences on the Romanian capital market during 2003–2010. Int J Math Comput Simul 6:378–386
Vapnik V (2013) The nature of statistical learning theory. Springer-Verlag, New York Inc
Chen J, Wang T, Gao X, Li W (2018) Real-time monitoring of high-power disk laser welding based on support vector machine. Comput Ind 94:75–81. https://doi.org/10.1016/j.compind.2017.10.003
Zhan C, Gan A, Hadi M (2011) Prediction of lane clearance time of freeway incidents using the M5P tree algorithm. IEEE Trans Intell Transp Syst 12:1549–1557. https://doi.org/10.1109/TITS.2011.2161634
Schaal S, Atkeson CG, Vijayakumar S (2002) Real-time robot learning with locally weighted statistical learning. 288–293. https://doi.org/10.1109/robot.2000.844072
Katayama S, Kawahito Y, Mizutani M (2007) Collaboration of physical and metallurgical viewpoints for understanding and process development of laser welding. In 26th International Congress on Applications of Lasers & Electro-Optics (ICALEO). Orlando, LIA, pp 360–369
Dinda SK, Srirangam P, Roy GG (2019) Effects of Beam Oscillation on Porosity and Intermetallic Compounds Formation of Electron Beam Welded DP600 Steel to Al-5754 Alloy Joints. In 148th Annual Meeting & Exhibition Supplemental Proceedings, The Minerals, Metals & Materials Series (TMS ). Springer International Publishing, pp 239–249
Huang JL, Warnken N, Gebelin J et al (2012) On the mechanism of porosity formation during welding of titanium alloys. Acta Mater 60:3215–3225. https://doi.org/10.1016/j.actamat.2012.02.035
Tammas-williams S, Zhao H, Léonard F et al (2015) XCT analysis of the in fluence of melt strategies on defect population in Ti – 6Al – 4V components manufactured by Selective Electron Beam Melting. Mater Charact 102:47–61. https://doi.org/10.1016/j.matchar.2015.02.008
Novakovic JĐ, Veljovic A, Ilic SS, Papic M (2016) Experimental study of using the k-nearest neighbour classifier experimental study of using the k-nearest neighbour classifier with filter methods. In Computer Science and Technology. Varna, Bulgaria, pp 90–99
Pan R, Yang T, Cao J et al (2015) Missing data imputation by K nearest neighbours based on grey relational structure and mutual information. Appl Intell 43:614–632. https://doi.org/10.1007/s10489-015-0666-x
Derrac J, García S, Molina D, Herrera F (2011) A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms. Swarm Evol Comput 1:3–18. https://doi.org/10.1016/j.swevo.2011.02.002
Chakri A, Khelif R, Benouaret M, Yang XS (2017) New directional bat algorithm for continuous optimization problems. Expert Syst Appl 69:159–175. https://doi.org/10.1016/j.eswa.2016.10.050
Takeshi M (2013) The Monte Carlo simulation method for system reliability and risk analysis. Nucl Saf Simul 4:44–52. https://doi.org/10.1007/978-1-4471-4588-2
Funding
The first three authors received the funding (in the form of fellowship) from the Ministry of Human Resource Development (MHRD) (now, Ministry of Education), Government of India for carrying out the study.
Author information
Authors and Affiliations
Contributions
Debasish Das: Experiment, Data Collection, Machine learning-based Modeling, Paper Writing. Soumitra Dinda: Experiment, Data collection; Paper Writing. Amit Kumar Das: Modeling, Paper Writing. Dilip Kumar Pratihar: Supervision, Reviewing and Editing. Gour Gopal Roy: Supervision, Reviewing and Editing.
Corresponding authors
Ethics declarations
Ethics approval
As this experiment is not conducted on human-beings, animals, ethical approval is not required.
Consent to participate
All the authors express their consent to participate.
Consent for publication All the authors express their consent to publish this work.
Competing interests
The authors declare no competing interests.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Das, D., Dinda, S.K., Das, A.K. et al. Study of micro-porosity in electron beam butt welding. Int J Adv Manuf Technol 121, 4583–4600 (2022). https://doi.org/10.1007/s00170-022-09359-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-022-09359-x