To advance quality assurance in the welding process, this study presents a deep learning (DL) model that enables the prediction of two critical welds’ key performance characteristics (KPCs): welding depth and average pore volume. In the proposed approach, a wide range of laser welding key input characteristics (KICs) is utilized, including welding beam geometries, welding feed rates, path repetitions for weld beam geometries, and bright light weld ratios for all paths, all of which were obtained from hairpin welding experiments. Two DL networks are employed with multiple hidden dense layers and linear activation functions to investigate the capabilities of deep neural networks in capturing the complex nonlinear relationships between the welding input and output variables (KPCs and KICs). Applying DL networks to the small numerical experimental hairpin welding dataset has shown promising results, achieving mean absolute error values of 0.1079 for predicting welding depth and 0.0641 for average pore volume. This, in turn, promises significant advantages in controlling welding outcomes, moving beyond the current trend of relying only on defect classification in weld monitoring to capture the correlation between the weld parameters and weld geometries.
REFERENCES
1.
See https://climate.ec.europa.eu/eu-action/european-green-deal/2030-climate-target-plan_en for “2030 Climate Target Plan.”
2.
Y.
Mao
et al, “A deep learning framework for layer-wise porosity prediction in metal powder bed fusion using thermal signatures
,” J. Intell. Manuf.
34
, 315
–329
(2023
). 3.
A.
Selema
, M. N.
Ibrahim
, and P.
Sergeant
, “Electrical machines winding technology: Latest advancements for transportation electrification
,” Machines
10
, 563
(2022
). 4.
M.
Soltani
, S.
Nuzzo
, D.
Barater
, and G.
Franceschini
, “Considerations on the preliminary sizing of electrical machines with hairpin windings
,” in 2021 IEEE Workshop on Electrical Machines Design, Control and Diagnosis (WEMDCD)
, 2021, Modena, Italy (IEEE
, Workshop on Electrical Machines Design, Control and Diagnosis (WEMDCD), 2021
).5.
A.
Mayr
, J.
Bauer
, and J.
Franke
, “A multi-view deep learning approach for quality assessment in laser welding of hairpin windings based on 2D image captures; licensed under a creative commons attribution (CC BY) license
,” Proc. CIRP
115
, 196
–201
(2022
). 6.
T.
Glaessel
, D. B.
Pinhal
, M.
Masuch
, D.
Gerling
, and J.
Franke
, “Manufacturing influences on the motor performance of traction drives with hairpin winding
,” in 2019 9th International Electric Drives Production Conference (EDPC)
(IEEE Xplore
, Esslingen, Germany, 2019), pp. 1
–8
.7.
V.
Dimatteo
, A.
Ascari
, P.
Faverzani
, L.
Poggio
, and A.
Fortunato
, “The effect of process parameters on the morphology, mechanical strength and electrical resistance of CW laser-welded pure copper hairpins
,” J. Manuf. Process.
62
, 450
–457
(2021
). 8.
P.
Berger
, H.
Hügel
, and T.
Graf
, “Understanding pore formation in laser beam welding
,” Phys. Proc.
12
, 241
–247
(2011
). 9.
B.
Acherjee
, S.
Mondal
, B.
Tudu
, and D.
Misra
, “Application of artificial neural network for predicting weld quality in laser transmission welding of thermoplastics
,” Appl. Soft Comput.
11
, 2548
–2555
(2011
). 10.
F.
Farrokhi
, B.
Endelt
, and M.
Kristiansen
, “A numerical model for full and partial penetration hybrid laser welding of thick-section steels
,” Opt. Laser Technol.
111
, 671
–686
(2019
). 11.
J. J.
Shen
, H. J.
Liu
, and F.
Cui
, “Effect of welding speed on microstructure and mechanical properties of friction stir welded copper
,” Mater. Des.
31
, 3937
–3942
(2010
). 12.
N.
Amanat
et al, “Transmission laser welding of amorphous and semi-crystalline poly-ether–ether–ketone for applications in the medical device industry
,” Mater. Des.
31
, 4823
–4830
(2010
). 13.
B.
Acherjee
, “Laser transmission welding of polymers—A review on welding parameters, quality attributes, process monitoring, and applications
,” J. Manuf. Process.
64
, 421
–443
(2021
). 14.
W.
Cai
, J.
Wang
, P.
Jiang
, L.
Cao
, G.
Mi
, and Q.
Zhou
, “Application of sensing techniques and artificial intelligence-based methods to laser welding real-time monitoring: A critical review of recent literature
,” J. Manuf. Syst.
57
, 1
–18
(2020
). 15.
D.
Wu
, P.
Zhang
, Z.
Yu
, Y.
Gao
, H.
Zhang
, H.
Chen
, S.
Chen
, and Y.
Tian
, “Progress and perspectives of in-situ optical monitoring in laser beam welding: Sensing, characterization and modeling
,” J. Manuf. Process.
75
, 767
–791
(2022
). 16.
Z.
Chen
, Y.
Huang
, F.
Han
, and D.
Tang
, “Numerical and experimental investigation on laser transmission welding of fiberglass-doped PP and ABS
,” J. Manuf. Process.
31
, 1
–8
(2018
). 17.
W.
Ge
, J. Y.
Fuh
, and S. J.
Na
, “Numerical modelling of keyhole formation in selective laser melting of Ti6Al4V
,” J. Manuf. Process.
62
, 646
–654
(2021
). 18.
M.
Jiang
, B.
Li
, X.
Chen
, C.
Tan
, Z.
Lei
, S.
Zhao
, and Y.
Chen
, “Numerical study of thermal fluid dynamics and solidification characteristics during continuous wave and pulsed wave laser welding
,” Int. J. Therm. Sci.
181
, 107778
(2022
). 19.
H.
Jia
, L.
Cao
, S.
Fu
, H.
Wen
, and G.
Ma
, “Numerical simulation and experiment for the dynamic behavior of molten pool in ultrasonic-assisted MIG welding
,” Int. J. Heat Mass Transfer
215
, 124469
(2023
). 20.
J.
Li
, P.
Jiang
, S.
Geng
, and J.
Xiong
, “Numerical and experimental study on keyhole dynamics and pore formation mechanisms during adjustable-ring-mode laser welding of medium-thick aluminum alloy
,” Int. J. Heat Mass Transfer
214
, 124443
(2023
). 21.
H.
Zhang
, Y.
Wang
, T.
Han
, L.
Bao
, Q.
Wu
, and S.
Gu
, “Numerical and experimental investigation of the formation mechanism and the distribution of the welding residual stress induced by the hybrid laser arc welding of AH36 steel in a butt joint configuration
,” J. Manuf. Process.
51
, 95
–108
(2020
). 22.
C.
Han
, P.
Jiang
, S.
Geng
, and L.
Ren
, “Multi-physics multi-scale simulation of unique equiaxed-to-columnar-to-equiaxed transition during the whole solidification process of Al-Li alloy laser welding
,” J. Mater. Sci. Technol.
171
, 235
–251
(2023
). 23.
P.
Jiang
, S.
Gao
, S.
Geng
, C.
Han
, and G.
Mi
, “Multi-physics multi-scale simulation of the solidification process in the molten pool during laser welding of aluminum alloys
,” Int. J. Heat Mass Transfer
161
, 120316
(2020
). 24.
J. S.
Rivera
, M. O.
Gagné
, S.
Tu
, N.
Barka
, F.
Nadeau
, and A. E.
Ouafi
, “Quality classification model with machine learning for porosity prediction in laser welding aluminum alloys
,” J. Laser Appl.
35
, 2
(2023
). 25.
R.
Yu
, Y.
Cao
, H.
Chen
, Q.
Ye
, and Y.
Zhang
, “Deep learning based real-time and in-situ monitoring of weld penetration: Where we are and what are needed revolutionary solutions?
,” J. Manuf. Process.
93
, 15
–46
(2023
). 26.
T.
Liu
, P.
Zheng
, and J.
Bao
, “Deep learning-based welding image recognition: A comprehensive review
,” J. Manuf. Syst.
68
, 601
–625
(2023
). 27.
E.
Mucllari
, R.
Yu
, Y.
Cao
, Q.
Ye
, and Y.
Zhang
, “Do we need a new foundation to use deep learning to monitor weld penetration?
,” IEEE Robot. Autom. Lett.
8
, 3669
–3676
(2023
). 28.
E.
Mucllari
, Y.
Cao
, Q.
Ye
, and Y.
Zhang
, “Modeling imaged welding process dynamic behaviors using generative adversarial network (GAN) for a new foundation to monitor weld penetration using deep learning
,” J. Manuf. Process.
124
, 187
–195
(2024
). 29.
D.
Kumar
, S.
Ganguly
, B.
Acherjee
, and A. S.
Kuar
, “Performance evaluation of TWIST welding using machine learning assisted evolutionary algorithms
,” Arab. J. Sci. Eng.
49
, 2411
–2441
(2024
). 30.
D.
Dhupal
, S.
Ranjan Dixit
, and S. R.
Das
, “Optimization of process parameters in laser microgrooving of alumina ceramic using genetic algorithm
,” UPB Sci. Bulle. Series D: Mech. Eng.
80
(4
), 163
–178
(2018
).31.
Y.
Li
, M.
Xiong
, Y.
He
, J.
Xiong
, X.
Tian
, and P.
Mativenga
, “Multi-objective optimization of laser welding process parameters: The trade-offs between energy consumption and welding quality
,” Opt. Laser Technol.
149
, 107861
(2022
). 32.
A.
Duggirala
, B.
Acherjee
, and S.
Mitra
, “Predicting weld pool metrics in laser welding of aluminum alloys using data-driven surrogate modeling: A FEA-DoE-GPRN hybrid approach
,” Proc. Inst. Mech. Eng. Part E
0
(0), 09544089241255927
(2024
). 33.
M.
Yusof
, M.
Ishak
, and M.
Ghazali
, “Weld depth estimation during pulse mode laser welding process by the analysis of the acquired sound using feature extraction analysis and artificial neural network
,” J. Manuf. Process.
63
, 163
–178
(2021
). 34.
B.
Liu
, W.
Jin
, A.
Lu
, C.
Wang
, and G.
Mi
, “Optimal design for dual laser beam butt welding process parameter using artificial neural networks and genetic algorithm for SUS316L austenitic stainless steel
,” Opt. Laser Technol.
125
, 106027
(2020
). 35.
M.
Luo
and Y. C.
Shin
, “Estimation of keyhole geometry and prediction of welding defects during laser welding based on a vision system and a radial basis function neural network
,” Int. J. Adv. Manuf. Technol.
81
, 263
–276
(2015
). 36.
D.
Ma
, P.
Jiang
, L.
Shu
, Z.
Gong
, Y.
Wang
, and S.
Geng
, “Online porosity prediction in laser welding of aluminum alloys based on a multi-fidelity deep learning framework
,” J. Intell. Manuf.
35
, 55
–73
(2022
). 37.
X.
Zhao
, W.
Zhang
, H.
Chen
, and Y.
Chen
, “Analysis of dynamic characteristics of vapor plume of oscillating laser welding of SUS301L-HT stainless steel
,” Opt. Laser Technol.
159
, 108947
(2023
). 38.
J.
Hartung
, A.
Jahn
, O.
Bocksrocker
, and M.
Heizmann
, “Camera-based In-process quality measurement of hairpin welding
,” Appl. Sci.
11
, 10375
(2021
). 39.
J.
Shin
, S.
Kang
, C.
Kim
, S.
Hong
, and M.
Kang
, “Identification of solidification cracking using multiple sensors and deep learning in laser overlap welded Al 6000 alloy
,” J. Laser Appl.
35
, 042019 (2023
). 40.
C.
Knaak
, M.
Kröger
, F.
Schulze
, P.
Abels
, and A.
Gillner
, “Deep learning and conventional machine learning for image-based in-situ fault detection during laser welding: A comparative study
,” Engineering
21
(12
), 4205 (2021
). 41.
M.
Omlor
, N.
Seitz
, T.
Butzmann
, T.
Petrich
, R.
Gräf
, A.-C.
Hesse
, and K.
Dilger
, “Quality characteristics and analysis of input parameters on laser beam welding of hairpin windings in electric drives
,” Weld. World
67
, 1491
–1508
(2023
). 42.
Y.
Zhang
, X.
Gao
, and S.
Katayama
, “Weld appearance prediction with BP neural network improved by genetic algorithm during disk laser welding
,” J. Manuf. Syst.
34
, 53
–59
(2015
). 43.
TRUMPF, see https://www.trumpf.com/en_IN/solutions/applications/laser-welding/low-spatter-welding-with-beam-formation-technology for “Low-Spatter Welding with Beam Formation Technology.”
44.
F.
Fetzer
, C.
Hagenlocher
, R.
Weber
, and T.
Graf
, “Geometry and stability of the capillary during deep-penetration laser welding of AlMgSi at high feed rates
,” Opt. Laser Technol.
133
, 106562
(2021
). 45.
A. K.
Sinha
, D. Y.
Kim
, and D.
Ceglarek
, “Correlation analysis of the variation of weld seam and tensile strength in laser welding of galvanized steel
,” Opt. Lasers Eng.
51
, 1143
–1152
(2013
). 46.
T.
Brežan
, P.
Franciosa
, M.
Jezeršek
, and D.
Ceglarek
, “Fusing optical coherence tomography and photodiodes for diagnosis of weld features during remote laser welding of copper-to-aluminum
,” J. Laser Appl.
35
, 012018 (2023
). © 2024 Author(s). Published under an exclusive license by Laser Institute of America.
2024
Author(s)
You do not currently have access to this content.
