The growing implementation of aluminum alloys in industry has focused interest on studying transformation processes such as laser welding. This process generates different kinds of signals that can be monitored and used to evaluate it and make a quality analysis of the final product. Internal defects that are difficult to detect, such as porosity, are one of the most critical irregularities in laser welding. This kind of defect may result in a critical failure of the manufactured goods, affecting the final user. In this research, a porosity prediction method using a high-speed camera monitoring system and machine learning (ML) algorithms is proposed and studied to find the most performant methodology to resolve the prediction problem. The methodology includes feature extraction by high-speed X-ray analysis, feature engineering and selection, imbalance treatment, and the evaluation of the ML algorithms by metrics such as accuracy, AUC (area under the curve), and F1. As a result, it was found that the best ML algorithm for porosity prediction in the proposed setup is Random Forest with a 0.83 AUC and 75% accuracy, 0.75 in the F1 score for no porosity, and 0.76 in the F1 score for porosity. The results of the proposed model and methodology indicate that they could be implemented in industrial applications for enhancing the final product quality for welded plates, reducing process waste and product quality analysis time, and increasing the operational performance of the process.
REFERENCES
1.
X.
Wang
, X.
Zhou
, Z.
Xia
, and X.
Gu
, “A survey of welding robot intelligent path optimization
,” J. Manuf. Process
63
, 14
–23
(2020
).2.
J.
Klæstrup Kristensen
, “Applications of laser welding in the shipbuilding industry
,” in Handbook of Laser Welding Technologies
(Woodhead Publishing Ltd, Sawston, UK, 2009), pp. 596
–612
.3.
M.
Graudenz
and M.
Baur
, “Applications of laser welding in the automotive industry
,” in Handbook of Laser Welding Technologies
(Woodhead Publishing Ltd, Sawston, UK), p. 555
–574
.4.
S.
Katayama
, “Defect formation mechanisms and preventive procedures in laser welding
,” in Handbook of Laser Welding Technologies
(Osaka University, Japan, 2013
).5.
S.
Katayama
, “Introduction: Fundamentals of laser welding
,” in Handbook of Laser Welding Technologies
(Osaka University, Japan, 2013
), Vol. 9.6.
X.
Gao
, Y.
Sun
, D.
You
, Z.
Xiao
, and X.
Chen
, “Multi-sensor information fusion for monitoring disk laser welding
,” In. J. Adv. Manuf. Technol.
85
, 1167
–1175
(2016
). 7.
S. J.
Na
and W. I.
Cho
, “Developments in modelling and simulation of laser and hybrid laser welding
,” in Handbook of Laser Welding Technologies
(KAIST, Korea, 2013
).8.
J.
Stavridis
, A.
Papacharalampopoulos
, and P.
Stavropoulos
, “Quality assessment in laser welding: A critical review
,” Int. J. Adv. Manuf. Technol.
94
, 1825
–1847
(2018
). 9.
J.
Günther
, P. M.
Pilarski
, G.
Helfrich
, H.
Shen
, and K.
Diepold
, “Intelligent laser welding through representation, prediction, and control learning: An architecture with deep neural networks and reinforcement learning
,” Mechatronics
34
, 1
–11
(2016
). 10.
P.
Stavropoulos
, K.
Sabatakakis
, A.
Papacharalampopoulos
, and D.
Mourtzis
, “Infrared (IR) quality assessment of robotized resistance spot welding based on machine learning
,” Int. J. Adv. Manuf. Technol.
119
, 1785
–1806
(2022
). 11.
R.
Lin
, H.
ping Wang
, F.
Lu
, J.
Solomon
, and B. E.
Carlson
, “Numerical study of keyhole dynamics and keyhole-induced porosity formation in remote laser welding of Al alloys
,” Int. J. Heat Mass Trans.
108
, 244
–256
(2017
). 12.
R. C. Bhagat and S. S. Patil, “
BMS
college of engineering: Department of information science and engineering, BMS college of engineering. Department of computer science and engineering, BMS college of engineering. department of computer applications, and institute of electrical and electronics engineers
,” in Souvenir of the 2015 IEEE International Advance Computing Conference (IACC)
, June 12–13, 2015
, B.M.S. College of Engineering, Bangalore, India (IEEE, Piscataway, NJ, 2015).13.
D.
Ma
, P.
Jiang
, L.
Shu
, and S.
Geng
, “Multi-sensing signals diagnosis and CNN-based detection of porosity defect during Al alloys laser welding
,” J. Manuf. Syst.
62
, 334
–346
(2022
). 14.
D.
Petković
, “Prediction of laser welding quality by computational intelligence approaches
,” Optik
140
, 597
–600
(2017
). 15.
B.
Zhang
, K. M.
Hong
, and Y. C.
Shin
, “Deep-learning-based porosity monitoring of laser welding process
,” Manuf. Lett.
23
, 62
–66
(2020
). 16.
A. Rubio-Solis and G. Panoutsos, “
Institute of electrical and electronics engineers, Friedrich-Alexander-Universität Erlangen-Nürnberg, IEEE power engineering society, IEEE industry applications society, and SüDdeutscher Verlag Veranstaltungen GmbH
,” in 2018 8th International Electric Drives Production Conference (EDPC) : Proceedings
, 4, 5 December 2018
, Schweinfurt, Germany (IEEE, Piscataway, NJ, 2018)17.
S. Q.
Moinuddin
, S. S.
Hameed
, A. K.
Dewangan
, K.
Ramesh Kumar
, and A.
Shanta Kumari
, “A study on weld defects classification in gas metal arc welding process using machine learning techniques
,” Mater. Today: Proc.
43
, 623
–628
(2020
).18.
J.
Stavridis
, A.
Papacharalampopoulos
, and P.
Stavropoulos
, “A cognitive approach for quality assessment in laser welding
,” Proc. CIRP
72
, 1542
–1547
(2018
). 19.
C. P.
Bergmann
and S.
Katayama
, see http://www.springer.com/series/11054 for “Topics in Mining, Metallurgy and Materials Engineering Series Editor Fundamentals and Details of Laser Welding.”20.
G.
Pastras
, A.
Fysikopoulos
, C.
Giannoulis
, and G.
Chryssolouris
, “A numerical approach to modeling keyhole laser welding
,” Int. J. Adv. Manuf. Technol.
78
, 723
–736
(2015
). 21.
Z.
Zhang
, B.
Li
, W.
Zhang
, R.
Lu
, S.
Wada
, and Y.
Zhang
, “Real-time penetration state monitoring using convolutional neural network for laser welding of tailor rolled blanks
,” J. Manuf. Syst.
54
, 348
–360
(2020
). 22.
J.
Chen
, T.
Wang
, X.
Gao
, and L.
Wei
, “Real-time monitoring of high-power disk laser welding based on support vector machine
,” Comput. Ind.
94
, 75
–81
(2018
). 23.
Z.
Wang
, J. P.
Oliveira
, Z.
Zeng
, X.
Bu
, B.
Peng
, and X.
Shao
, “Laser beam oscillating welding of 5A06 aluminum alloys: Microstructure, porosity and mechanical properties
,” Opt. Laser Technol.
111
, 58
–65
(2019
). 24.
K.
Hao
, G.
Li
, M.
Gao
, and X.
Zeng
, “Weld formation mechanism of fiber laser oscillating welding of austenitic stainless steel
,” J. Mater. Process. Technol.
225
, 77
–83
(2015
). 25.
P.
Horník
, H.
Šebestová
, J.
Novotný
, and L.
Mrňa
, “Visualization of laser back-reflection distribution during laser welding
,” IOP Conf. Ser. Mater. Sci. Eng.
1135
, 012015
(2021
). 26.
D.
You
, X.
Gao
, and S.
Katayama
, “Multiple-optics sensing of high-brightness disk laser welding process
,” NDT E Int.
60
, 32
–39
(2013
). 27.
L.
Li
, G.
Peng
, J.
Wang
, J.
Gong
, and S.
Meng
, “Numerical and experimental study on keyhole and melt flow dynamics during laser welding of aluminium alloys under subatmospheric pressures
,” Int. J. Heat Mass Trans.
133
, 812
–826
(2019
). 28.
L.
Li
, H.
Xia
, G.
Ma
, and G.
Peng
, “Flow dynamics during single- and dual-spot laser welding with one common keyhole of 321 stainless steel
,” J. Mater. Process. Technol.
255
, 841
–852
(2018
). 29.
Z.
Yang
, X.
Zhao
, W.
Tao
, and C.
Jin
, “Effects of keyhole status on melt flow and flow-induced porosity formation during double-sided laser welding of AA6056/AA6156 aluminium alloy T-joint
,” Opt. Laser Technol.
109
, 39
–48
(2019
). 30.
S.
Scott
and S.
Matwin
, see http://ai.iit.nrc.ca/II_public/Classification/resources.html for “Feature Engineering for Text Classification.”31.
V.
Bolón-Canedo
, N.
Sánchez-Maroño
, and A.
Alonso-Betanzos
, “Feature selection and classification in multiple class datasets: An application to KDD Cup 99 dataset
,” Expert Syst. Appl.
38
, 5947
–5957
(2011
). 32.
R. C.
Chen
, C.
Dewi
, S. W.
Huang
, and R. E.
Caraka
, “Selecting critical features for data classification based on machine learning methods
,” J Big Data
7
, 1
–26
(2020
). 33.
S.
Gopal
, K.
Patro
, and K.
Kumar Sahu
, see www.kiplinger.com for “Normalization: A Preprocessing Stage.”34.
S. Aparna, “
IEEE Electron Devices Society, Institute of Electrical and Electronics Engineers, and Vaigai College of Engineering
,” Proceeding of the 2018 International Conference on Intelligent Computing and Control Systems (ICICCS)
, 14–15 June 2018
, Madurai, India (IEEE, Piscataway, NJ, 2018).35.
D.
Ma
, L.
Shu
, Q.
Zhou
, S.
Cao
, and P.
Jiang
, “Online porosity defect detection based on convolutional neural network for Al alloy laser welding
,” J. Phys.: Conf. Ser.
1884
, 012008
(2021
). 36.
S.
Pang
, W.
Chen
, and W.
Wang
, “A quantitative model of keyhole instability induced porosity in laser welding of titanium alloy
,” Metall. Mater. Trans. A Phys. Metall. Mater. Sci.
45
, 2808
–2818
(2014
). 37.
N.
Seto
, S.
Katayama
, and A.
Matsunawa
, “High-speed simultaneous observation of plasma and keyhole behavior during high power CO2 laser welding: Effect of shielding gas on porosity formation
,” J. Laser Appl.
12
, 245
–250
(2000
). 38.
S. B.
Kotsiantis
, I. D.
Zaharakis
, and P. E.
Pintelas
, “Machine learning: A review of classification and combining techniques
,” Artif. Intell. Rev.
26
, 159
–190
(2006
). 39.
M.
Grandini
, E.
Bagli
, and G.
Visani
, “Metrics for Multi-Class Classification: An Overview,” see http://arxiv.org/abs/2008.05756 (2020
).40.
A. E.
Maxwell
, T. A.
Warner
, and F.
Fang
, “Implementation of machine-learning classification in remote sensing: An applied review
,” Int. J. Remote Sens.
39
, 2784
–2817
(2018
). 41.
R.
Sharda
, S.
Voß
, and S.
Suthaharan
, see http://www.springer.com/series/6157 for “Integrated Series in Information Systems 36 Machine Learning Models and Algorithms for Big Data Classification Thinking with Examples for Effective Learning.”. 42.
I.
Nunes
et al., “Artificial Neural Networks A Practical Course.”43.
K.
Alexopoulos
, N.
Nikolakis
, and G.
Chryssolouris
, “Digital twin-driven supervised machine learning for the development of artificial intelligence applications in manufacturing
,” Int. J. Comput. Integr. Manuf.
33
, 429
–439
(2020
). 44.
“Lecture Notes in Artificial Intelligence.”
45.
B.
Xu
, N.
Wang
, T.
Chen
, and M.
Li
, “Empirical Evaluation of Rectified Activations in Convolutional Network,” http://arxiv.org/abs/1505.00853 (2015
).46.
A.
Prinzie
and D.
van den Poel
, “Random forests for multiclass classification: Random MultiNomial logit
,” Expert Syst. Appl.
34
, 1721
–1732
(2008
). 47.
A. Bosch, A. Zisserman, and X. Munoz, “
Institute of Electrical and Electronics Engineers, IEEE International Conference on Computer Vision 11 2007.10.14-21 Rio de Janeiro, and ICCV 11 2007.10.14-21 Rio de Janeiro
,” in IEEE 11th International Conference on Computer Vision, 2007 ICCV 2007
, 14–21 October 2007
, Rio de Janeiro, Brasil (IEEE, Piscataway, NJ, 2007).48.
A. D.
Kulkarni
and B.
Lowe
, see http://hdl.handle.net/10950/341http://www.ijritcc.org for “Random Forest Algorithm for Land Cover Classification International Journal on Recent and Innovation Trends in Computing and Communication Random Forest Algorithm for Land Cover Classification,” 2016.49.
S. B.
Jabeur
, C.
Gharib
, S.
Mefteh-Wali
, and W. B.
Arfi
, “Catboost model and artificial intelligence techniques for corporate failure prediction
,” Technol. Forecast Soc. Change
166
, 120658
(2021
). 50.
A. V.
Dorogush
, V.
Ershov
, and A. G.
Yandex
, see https://github.com/Microsoft/LightGBM for “CatBoost: gradient boosting with categorical features support.”51.
M.
Ikonomakis
, S.
Kotsiantis
, and V.
Tampakas
, “Text Classification Using Machine Learning Techniques.”52.
J.
Li
et al., “Machine learning for patient-specific quality assurance of VMAT: Prediction and classification accuracy
,” Int. J. Radiat. Oncol. Biol. Phys.
105
, 893
–902
(2019
). 53.
A. M.
Carrington
et al., “Deep ROC analysis and AUC as balanced average accuracy to improve model selection, understanding and interpretation
,” IEEE Trans. Pattern Anal. Mach. Intell.
45
, 329
–341
(2021
).54.
“Lecture Notes in Artificial Intelligence Subseries of Lecture Notes in Computer Science.”
55.
D. W.
Hosmer
, Jr., S.
Lemeshow
, and R. X.
Sturdivant
, Applied Logistic Regression
(John Wiley & Sons, Amhurst, MA, 2013
), Vol. 398.56.
S.
Il Pak
and T. H.
Oh
, “Correlation and simple linear regression
,” J. Vet. Clin.
27
, 427
–434
(2010
).57.
N. J.
Gogtay
and U. M.
Thatte
, “Principles of correlation analysis
,” J. Assoc. Phys. India
65
, 78
–81
(2017
).58.
MathWorks, “Specialization Practical Data science with Matlab.”
59.
L.
Wang
, M.
Gao
, C.
Zhang
, and X.
Zeng
, “Effect of beam oscillating pattern on weld characterization of laser welding of AA6061-T6 aluminum alloy
,” Mater. Des.
108
, 707
–717
(2016
). 60.
M. B.
Kursa
and W. R.
Rudnicki
, see http://www.jstatsoft.org/ for “Feature Selection with the Boruta Package,” 2010.61.
M. B.
Kursa
, A.
Jankowski
, and W. R.
Rudnicki
, “Boruta—A system for feature selection
,” Fundam. Inform.
101
, 271
–285
(2010
). 62.
R.
Tang
and X.
Zhang
, “CART decision tree combined with Boruta feature selection for medical data classification
,” in 2020 5th IEEE International Conference on Big Data Analytics, ICBDA 2020
, May 2020, Xiamen, China (IEEE, Piscataway, NJ, 2020
), pp. 80
–84
.63.
A.
Zien
, N.
Krämer
, S.
Sonnenburg
, and G.
Rätsch
, “LNAI 5782—The Feature Importance Ranking Measure.”64.
R.
Goebel
, W.
Wahlster
, and J.
Siekmann
, see http://www.springer.com/series/1244 for “Lecture Notes in Artificial Intelligence 9851 Subseries of Lecture Notes in Computer Science LNAI Series Editors LNAI Founding Series Editor.”65.
A.
Salvadorrgarcíaa
, M. R.
Pratii
, and B.
Franciscooherrera
, “Learning from Imbalanced Data Sets.” 66.
C.
Huang
, Y.
Li
, C. C.
Loy
, and X.
Tang
, “Learning deep representation for imbalanced classification
,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
, 30 June 2016, Las Vegas, NV (IEEE, Piscataway, NJ, 2016
), Vol. 2016, pp. 5375
–5384
.67.
M.
Tripathi
, “Understanding Imbalanced Datasets and Techniques for Handling Them,” 2015.© 2023 Author(s). Published under an exclusive license by Laser Institute of America.
2023
Author(s)
You do not currently have access to this content.
