Laser welding monitoring techniques based on optical diagnosis and artificial intelligence: a review

Abstract

Laser welding is an efficient and precise joining method widely used in various industries. Real-time monitoring of the welding process is important for improving the quality of the weld products. This study provides an overview of the optical diagnostics of the laser welding process. The common welding defects and their formation mechanisms are described, starting with an introduction to the principles of laser welding. Optical signal sources are divided into radiated and external active lights, and different monitoring systems are summarized and classified. Also, the applications of artificial intelligence techniques in data processing, weld defect prediction and classification, and adaptive welding control are summarized. Finally, future research and challenges in real-time laser welding monitoring technology based on optical diagnostics are discussed. This study demonstrated that optical diagnostic techniques could acquire substantial information about the laser welding process and help identify welding defects.

Keywords

Laser welding / Real-time monitoring / Welding defect / Optical diagnosis / Artificial intelligence / Engineering / Manufacturing Engineering

References

[1] AminzadehA, SattarpanahKS, MeiabadiMS, et al. . A survey of process monitoring using computer-aided inspection in laser-welded blanks of light metals based on the digital twins concept. Quantum Beam Sci, 2022, 6: 19.

[2] ChenL, YangT, ZhuangY, et al. . The multi-objective optimization modelling for properties of 301 stainless steel welding joints in ultra-narrow gap laser welding. Weld World, 2021, 65: 1333-1345.

[3] YangF. Research progress of laser welding under subatmospheric pressure. Int J Adv Manuf Technol, 2021, 116: 803-820.

[4] AmericanWS, KumarN, KumarN, et al. . A state-of-the-art review of laser welding of polymers—part I: welding parameters. Weld J, 2021, 100: 221-228.

[5] SpöttlM, MohrbacherH. Laser-based manufacturing concepts for efficient production of tailor welded sheet metals. Adv Manuf, 2014, 2: 193-202.

[6] MohrbacherH, SpoettlM, PaegleJ. Innovative manufacturing technology enabling light weighting with steel in commercial vehicles. Adv Manuf, 2015, 3: 3-18.

[7] FanX, GaoX, LiuG, et al. . Research and prospect of welding monitoring technology based on machine vision. Int J Adv Manuf Technol, 2021, 115: 3365-3391.

[8] HeB, BaiKJ. Digital twin-based sustainable intelligent manufacturing: a review. Adv Manuf, 2021, 9: 1-21.

[9] FabbroR. Melt pool and keyhole behaviour analysis for deep penetration laser welding. J Phys Appl Phys, 2010, 43: 445501.

[10] ZengH, ZhouZ, ChenY, et al. . Wavelet analysis of acoustic emission signals and quality control in laser welding. J Laser Appl, 2001, 13: 167-173.

[11] YouDY, GaoXD, KatayamaS. Review of laser welding monitoring. Sci Technol Weld Join, 2014, 19: 181-201.

[12] Cai W, Wang J, Zhou Q et al (2019) Equipment and machine learning in welding monitoring: a short review. In: Proceedings of the 5th international conference on mechatronics and robotics engineering- ICMRE’19. ACM Press, Rome

[13] LeeJ, KangM. A review on the characteristics of laser welding with filler wire according to process parameters controlling the heat input and wire feeding. J Weld Join, 2021, 39: 167-173.

[14] IonJCIonJC. Chapter 16—keyhole welding. laser processing of engineering materials, 2005OxfordButterworth-Heinemann395-495.

[15] SibillanoT, AnconaA, BerardiV, et al. . Optical detection of conduction/keyhole mode transition in laser welding. J Mater Process Technol, 2007, 191: 364-367.

[16] BahadorA, HamzahE, KondohK, et al. . Heat-conduction-type and keyhole-type laser welding of Ti-Ni shape-memory alloys processed by spark-plasma sintering. Mater Trans, 2018, 59: 835-842.

[17] CovielloD, D’AngolaA, SorgenteD. Numerical study on the influence of the plasma properties on the keyhole geometry in laser beam welding. Front Phys, 2022, 9: 754672.

[18] SvenungssonJ, ChoquetI, KaplanAFH. Laser welding process—a review of keyhole welding modelling. Phys Procedia, 2015, 78: 182-191.

[19] SibillanoT, AnconaA, BerardiV, et al. . Correlation spectroscopy as a tool for detecting losses of ligand elements in laser welding of aluminium alloys. Opt Lasers Eng, 2006, 44: 1324-1335.

[20] ChenX. Three-dimensional modelling of the laser-induced plasma plume characteristics in laser welding. J Phys Appl Phys, 2003, 36: 628.

[21] GongJ, PengG, LiL, et al. . Effect of plasma plume produced by vacuum laser welding on energy transmission. Opt Laser Technol, 2021, 136: 106744.

[22] BrockC, HohensteinR, SchmidtM. Towards fast tracking of the keyhole geometry. Phys Procedia, 2011, 12: 697-703.

[23] FengY, GaoX, ZhangY, et al. . Simulation and experiment for dynamics of laser welding keyhole and molten pool at different penetration status. Int J Adv Manuf Technol, 2021, 112: 2301-2312.

[24] Gong S, Pang S, Wang H et al (2021) Laser welding basics. In: Weld pool dynamics in deep penetration laser welding. Springer, Singapore. https://doi.org/10.1007/978-981-16-0788-2_1

[25] WoizeschkeP, RadelT, NicolayP, et al. . Laser deep penetration welding of an aluminum alloy with simultaneously applied vibrations. Lasers Manuf Mater Process, 2017, 4: 1-12.

[26] OlssonR, ErikssonI, PowellJ, et al. . Challenges to the interpretation of the electromagnetic feedback from laser welding. Opt Lasers Eng, 2011, 49: 188-194.

[27] WangT, GaoX, SeijiK, et al. . Study of dynamic features of surface plasma in high-power disk laser welding. Plasma Sci Technol, 2012, 14: 245-251.

[28] OkabeT, YasudaK, NakataK. Dynamic observations of welding phenomena and finite element analysis in high-frequency electric resistance welding. Weld Int, 2016, 30: 835-845.

[29] AuwalST, RameshS, YusofF, et al. . A review on laser beam welding of copper alloys. Int J Adv Manuf Technol, 2018, 96: 475-490.

[30] AllenTR, HuangW, TannerJR, et al. . Energy-coupling mechanisms revealed through simultaneous keyhole depth and absorptance measurements during laser-metal processing. Phys Rev Appl, 2020, 13: 064070.

[31] ParabND, ZhaoC, CunninghamR, et al. . High-speed synchrotron X-ray imaging of laser powder bed fusion process. Synchrotron Radiat News, 2019, 32: 4-8.

[32] ZhaoH, DebroyT. Pore formation during laser beam welding of die-cast magnesium alloy AM60B—mechanism and remedy. Weld J Miami Fla, 2001, 80: 204-210

[33] KatayamaSFundamentals and details of laser welding, 2020SingaporeSpringer.

[34] SheikhiM, MalekGF, AssadiH. Prediction of solidification cracking in pulsed laser welding of 2024 aluminum alloy. Acta Mater, 2015, 82: 491-502.

[35] LippoldJC. Solidification behavior and cracking susceptibility of pulsed-laser welds in austenitic stainless steels. Weld J Miami U S, 1994, 736129-139

[36] KimHT, NamSW. Solidification cracking susceptibility of high strength aluminum alloy weldment. Scr Mater, 1996, 34: 1139-1145.

[37] ZhangM, ZhangZ, TangK, et al. . Analysis of mechanisms of underfill in full penetration laser welding of thick stainless steel with a 10kW fiber laser. Opt Laser Technol, 2018, 98: 97-105.

[38] FangX, LiuH, ZhangJ. Reducing the under fill rate of pulsed laser welding of titanium alloy through the application of a transversal pre-extrusion load. J Mater Process Technol, 2015, 220: 124-134.

[39] ZhuB, ZhangG, ZouJ, et al. . Melt flow regularity and hump formation process during laser deep penetration welding. Opt Laser Technol, 2021, 139: 106950.

[40] XiaoX, LiuX, ChengM, et al. . Towards monitoring laser welding process via a coaxial pyrometer. J Mater Process Technol, 2020, 277: 116409.

[41] DoongJL, WuCS, HwangJR. Infrared temperature sensing of laser welding. Int J Mach Tools Manuf, 1991, 31: 607-616.

[42] NairAM, MuvvalaG, SarkarS, et al. . Real-time detection of cooling rate using pyrometers in tandem in laser material processing and directed energy deposition. Mater Lett, 2020, 277: 128330.

[43] StehrT, HermsdorfJ, HenningT, et al. . Closed loop control for laser micro spot welding using fast pyrometer systems. Phys Procedia, 2010, 5: 465-471.

[44] GadeR, MoeslundTB. Thermal cameras and applications: a survey. Mach Vis Appl, 2014, 25: 245-262.

[45] Al-Karawi J, Schmidt J (2004) Application of infrared thermography to the analysis of welding processes. In: Proceedings of the 2004 international conference on quantitative infrared thermography, QIRT Council, Belgium, July 5–8, H.9.1–H.9.6

[46] MathieuA, MatteïS, DeschampsA, et al. . Temperature control in laser brazing of a steel/aluminium assembly using thermographic measurements. NDT E Int, 2006, 39: 272-276.

[47] ChenZ, GaoX. Detection of weld pool width using infrared imaging during high-power fiber laser welding of type 304 austenitic stainless steel. Int J Adv Manuf Technol, 2014, 74: 1247-1254.

[48] ZhouJ, XiaG, ZhouZ, et al. . Comparison study of 6082 Al alloy laser welding using 455 nm blue laser and 1080 nm near-infrared laser. Optik, 2023, 272: 170224.

[49] YuR, GuoS, HuangY, et al. . Prediction of variable-groove weld penetration using texture features of infrared thermal images and machine learning methods. J Mater Res Technol, 2023, 23: 1039-1051.

[50] Vakili-FarahaniF, LungershausenJ, WasmerK. Wavelet analysis of light emission signals in laser beam welding. J Laser Appl, 2017, 29: 022424.

[51] SandersPG, LeongKH, KeskeJS, et al. . Real-time monitoring of laser beam welding using infrared weld emissions. J Laser Appl, 1998, 10: 205-211.

[52] GeigerM, KägelerC, SchmidtM. High-power laser welding of contaminated steel sheets. Prod Eng, 2008, 2: 235-240.

[53] ZhangY, GaoX, YouD, et al. . A low-cost welding status monitoring framework for high-power disk laser welding. IEEE Access, 2019, 7: 17365-17376.

[54] ConnollyJO, BeirneGJ, O’ConnorGM, et al. HaglundRF, WoodRF, et al. . Optical monitoring of laser generated plasma during laser welding. Laser plasma generation and diagnostics, 2000BellinghamSPIE-The International Society for Optical Engineering

[55] BrunckoJ, UherekFHrabovskyM, SenderakovaD, TomanekP. Michalka M (2003) Monitoring of laser welding processes by optical emission spectroscopy. Photonics, devices, and systems I, 2003BellinghamSPIE-The International Society for Optical Engineering

[56] SebestovaH, ChmelickovaH, NozkaL, et al. . Non-destructive real time monitoring of the laser welding process. J Mater Eng Perform, 2012, 21: 764-769.

[57] SibillanoT, RizziD, MezzapesaFP, et al. . Closed loop control of penetration depth during CO₂ laser lap welding processes. Sensors, 2012, 12: 11077-11090.

[58] SaeedG, ZhangYM. Weld pool surface depth measurement using a calibrated camera and structured light. Meas Sci Technol, 2007, 18: 2570.

[59] WangL, MohammadpourM, GaoX, et al. . Adjustable ring mode (ARM) laser welding of stainless steels. Opt Lasers Eng, 2021, 137: 106360.

[60] WangL, MohammadpourM, YangB, et al. . Monitoring of keyhole entrance and molten pool with quality analysis during adjustable ring mode laser welding. Appl Opt, 2020, 59: 1576-1584.

[61] ZhangY, GaoX. Analysis of characteristics of molten pool using cast shadow during high-power disk laser welding. Int J Adv Manuf Technol, 2014, 70: 1979-1988.

[62] WangJ, WangC, MengX, et al. . Study on the periodic oscillation of plasma/vapour induced during high power fibre laser penetration welding. Opt Laser Technol, 2012, 44: 67-70.

[63] SunD, CaiY, WangY, et al. . Effect of He-Ar ratio of side assisting gas on plasma 3D formation during CO₂ laser welding. Opt Lasers Eng, 2014, 56: 41-49.

[64] GaoX, WenQ, KatayamaS. Analysis of high-power disk laser welding stability based on classification of plume and spatter characteristics. Trans Nonferrous Met Soc China, 2013, 23: 3748-3757.

[65] TennerF, BrockC, KlämpflF, et al. . Analysis of the correlation between plasma plume and keyhole behavior in laser metal welding for the modeling of the keyhole geometry. Opt Lasers Eng, 2015, 64: 32-41.

[66] ZhangX, TangZ, WuY, et al. . Progress in in situ X-ray imaging of welding process. Rev Sci Instrum, 2022, 93: 071501.

[67] BoleyM, AbtF, WeberR, et al. . X-ray and optical videography for 3D measurement of capillary and melt pool geometry in laser welding. Phys Procedia, 2013, 41: 488-495.

[68] KaplanAFH, MizutaniM, KatayamaS, et al. , et al. MiyamotoI, KobayashiKF, SugiokaK, et al. , et al. . On the mechanism of pore formation during keyhole laser spot welding. First international symposium on high-power laser macroprocessing, 2003BellinghamSPIE-the International Society for Optics and Photonics

[69] MaiTA, SpowageAC. Characterisation of dissimilar joints in laser welding of steel-kovar, copper-steel and copper-aluminium. Mater Sci Eng A, 2004, 374: 224-233.

[70] YamadaT, ShobuT, NishimuraA, et al. . In-situ X-ray observation of molten pool depth during laser micro welding. J Laser Micro Nanoeng, 2012, 7: 244-248.

[71] HeiderA, SollingerJ, AbtF, et al. . High-speed X-ray analysis of spatter formation in laser welding of copper. Phys Procedia, 2013, 41: 112-118.

[72] ZhanX, BuX, QinT, et al. . X-ray online detection for laser welding T-joint of Al-Li alloy. Mod Phys Lett B, 2017, 31: 1750154.

[73] CunninghamR, ZhaoC, ParabN, et al. . Keyhole threshold and morphology in laser melting revealed by ultrahigh-speed X-ray imaging. Science, 2019, 3636429849-852.

[74] DupriezND, DenklA. Advances of OCT technology for laser beam processing: precision and quality during laser welding. Laser Tech J, 2017, 14: 34-38.

[75] BoleyM, FetzerF, WeberR, et al. . Statistical evaluation method to determine the laser welding depth by optical coherence tomography. Opt Lasers Eng, 2019, 119: 56-64.

[76] Lohaus L, Bautze T, Diepold K (2010) Evaluation of optical sensors for laser welding in a technical cognitive environment. In: International congress on applications of lasers & electro-optics. Laser Institute of America, Anaheim, California, USA. https://doi.org/10.2351/1.5062015

[77] SchmittR, MallmannG, DevrientM, et al. . 3D polymer weld seam characterization based on optical coherence tomography for laser transmission welding applications. Phys Procedia, 2014, 56: 1305-1314.

[78] Dorsch F, Harrer T, Haug P et al (2016) Process control using capillary depth measurement. In: International congress on applications of lasers & electro-optics. Laser Institute of America, San Diego, California, USA. https://doi.org/10.2351/1.5118550

[79] Dorsch F, Dubitzky W, Effing L et al (2017) Capillary depth measurement for process control. In: Kaierle S, Heinemann SW(eds) High-power laser materials processing: applications, diagnostics, and systems vol 10097, SPIE, San Francisco, California, United States, p 1009708

[80] SchmoellerM, StadterC, LieblS, et al. . Inline weld depth measurement for high brilliance laser beam sources using optical coherence tomography. J Laser Appl, 2019, 31: 022409.

[81] MittelstädtC, MattulatT, SeefeldT, et al. . Novel approach for weld depth determination using optical coherence tomography measurement in laser deep penetration welding of aluminum and steel. J Laser Appl, 2019, 31: 022007.

[82] AuthierN, TouzetE, LückingF, et al. KaierleS, HeinemannSW, et al. . Coupled membrane free optical microphone and optical coherence tomography keyhole measurements to setup welding laser parameters. High-power laser materials processing: applications, diagnostics, and systems, 2020San FranciscoSPIE9

[83] SokolovM, FranciosaP, SunT, et al. . Applying optical coherence tomography for weld depth monitoring in remote laser welding of automotive battery tab connectors. J Laser Appl, 2021, 33: 012028.

[84] MaD, JiangP, ShuL, et al. . DBN-based online identification of porosity regions during laser welding of aluminum alloys using coherent optical diagnosis. Opt Laser Technol, 2023, 165: 109597.

[85] GaoX, ChenY. Detection of micro gap weld using magneto-optical imaging during laser welding. Int J Adv Manuf Technol, 2014, 73: 23-33.

[86] GaoX, HuangG, YouD, et al. . Magneto-optical imaging deviation model of micro-gap weld joint. J Manuf Syst, 2017, 42: 82-92.

[87] GaoX, MoL, YouD, et al. . Tight butt joint weld detection based on optical flow and particle filtering of magneto-optical imaging. Mech Syst Signal Process, 2017, 96: 16-30.

[88] LiY, GaoX, ChenY, et al. . Modeling for tracking micro gap weld based on magneto-optical sensing and kalman filtering. IEEE Sens J, 2021, 21: 11598-11614.

[89] YouD, GaoX, KatayamaS. Data-driven based analyzing and modeling of MIMO laser welding process by integration of six advanced sensors. Int J Adv Manuf Technol, 2016, 82: 1127-1139.

[90] NormanP, EngstroemH, KaplanAFH. Theoretical analysis of photodiode monitoring of laser welding defects by imaging combined with modelling. J Phys Appl Phys, 2008, 41: 195502.

[91] LiuW, LiuS, MaJ, et al. . Real-time monitoring of the laser hot-wire welding process. Opt Laser Technol, 2014, 57: 66-76.

[92] LiS, ChenG, KatayamaS, et al. . Relationship between spatter formation and dynamic molten pool during high-power deep-penetration laser welding. Appl Surf Sci, 2014, 303: 481-488.

[93] YouD, GaoX, KatayamaS. A Novel stability quantification for disk laser welding by using frequency correlation coefficient between multiple-optics signals. IEEE/ASME Trans Mechatron, 2015, 20: 327-337.

[94] VolppJ. Keyhole stability during laser welding—part II: process pores and spatters. Prod Eng, 2017, 11: 9-18.

[95] LiuG, GaoX, YouD, et al. . Prediction of high power laser welding status based on PCA and SVM classification of multiple sensors. J Intell Manuf, 2019, 30: 821-832.

[96] von WitzendorffP, KaierleS, SuttmannO, et al. . Using pulse shaping to control temporal strain development and solidification cracking in pulsed laser welding of 6082 aluminum alloys. J Mater Process Technol, 2015, 225: 162-169.

[97] GaoX, YouD, KatayamaS. Infrared image recognition for seam tracking monitoring during fiber laser welding. Mechatronics, 2012, 22: 370-380.

[98] YouD, GaoX, KatayamaS. Monitoring of high-power laser welding using high-speed photographing and image processing. Mech Syst Signal Process, 2014, 49: 39-52.

[99] OlssonR, ErikssonI, PowellJ, et al. . Advances in pulsed laser weld monitoring by the statistical analysis of reflected light. Opt Lasers Eng, 2011, 49: 1352-1359.

[100] WuD, HuangY, ZhangP, et al. . Visual-acoustic penetration recognition in variable polarity plasma arc welding process using hybrid deep learning approach. IEEE Access, 2020, 8: 120417-120428.

[101] ParkYW, ParkH, RheeS, et al. . Real time estimation of CO₂ laser weld quality for automotive industry. Opt Laser Technol, 2002, 34: 135-142.

[102] BardinF, CoboA, Lopez-HigueraJM, et al. . Optical techniques for real-time penetration monitoring for laser welding. Appl Opt, 2005, 44: 3869-3876.

[103] MrňaL, ŠarbortM, ŘeřuchaŠ, et al. . Correlation between the keyhole depth and the frequency characteristics of light emissions in laser welding. Phys Procedia, 2013, 41: 469-477.

[104] WuD, ZhangP, YuZ, et al. . Progress and perspectives of in-situ optical monitoring in laser beam welding: sensing, characterization and modeling. J Manuf Process, 2022, 75: 767-791.

[105] Fang J, Li L, Chen Y et al (2005) Wavelet analysis of plasma optical signals at pool penetration in laser welding. In: Mu G, Yu FTS, Jutamulia S (eds) Proceedings of information optics and photonics technology, vol 5642, SPIE, Beijing, 2005

[106] SibillanoT, AnconaA, RizziD, et al. . Plasma plume oscillations monitoring during laser welding of stainless steel by discrete wavelet transform application. Sensors, 2010, 10: 3549-3561.

[107] ZhangY, YouD, GaoX, et al. . Welding defects detection based on deep learning with multiple optical sensors during disk laser welding of thick plates. J Manuf Syst, 2019, 51: 87-94.

[108] ParkH, RheeS, KimD. A fuzzy pattern recognition based system for monitoring laser weld quality. Meas Sci Technol, 2001, 12: 1318.

[109] YouDY, GaoXD, KatayamaS. Multisensor fusion system for monitoring high-power disk laser welding using support vector machine. IEEE Trans Ind Inform, 2014, 10: 1285-1295.

[110] YouD, GaoX, KatayamaS. WPD-PCA-based laser welding process monitoring and defects diagnosis by using FNN and SVM. IEEE Trans Ind Electron, 2015, 62: 628-636.

[111] CaiW, JiangP, ShuL, et al. . Real-time identification of molten pool and keyhole using a deep learning-based semantic segmentation approach in penetration status monitoring. J Manuf Process, 2022, 76: 695-707.

[112] CaoL, LiJ, ZhangL, et al. . Cross-attention-based multi-sensing signals fusion for penetration state monitoring during laser welding of aluminum alloy. Knowl Based Syst, 2023, 261: 110212.

[113] KawahitoY, KatayamaS. In-process monitoring and feedback control during laser microspot lap welding of copper sheets. J Laser Appl, 2004, 16: 121-127.

[114] KawahitoY, OhnishiT, KatayamaS. In-process monitoring and feedback control for stable production of full-penetration weld in continuous wave fibre laser welding. J Phys Appl Phys, 2009, 42: 085501.

[115] de Graaf MW, Benneker JO, Aarts RGKM et al (2005) Robust process-controller for Nd:YAG welding. In: Proceedings of 24th international congress on applications of lasers & electro-optics 2005 (ICALEO05), AIP Publishing, Miami

[116] JaureguiJM, AalderinkBJ, AartsRGKM, et al. . Design, implementation and testing of a fuzzy control scheme for laser welding. J Laser Appl, 2008, 20: 146-153.

[117] KonukAR, AartsR, VeldBH, et al. . Closed loop control of laser welding using an optical spectroscopic sensor for Nd:YAG and CO₂ lasers. Int Congr Appl Lasers Electro-Opt, 2011, 2011: 85-94

[118] GaoX, SunY, KatayamaS. Neural network of plume and spatter for monitoring high-power disk laser welding. Int J Precis Eng Manuf-Green Technol, 2014, 1: 293-298.

[119] ZhangK, LiD, GuiH, et al. . Adaptive control for laser welding with filler wire of marine high strength steel with tight butt joints for large structures. J Manuf Process, 2018, 36: 434-441.

[120] KosM, ArkoE, KoslerH, et al. . Remote-laser welding system with in-line adaptive 3D seam tracking and power control. Procedia CIRP, 2019, 81: 1189-1194.

[121] BaraniukRG. More is less: signal processing and the data deluge. Science, 2011, 3316018717-719.

[122] KouraytemN, LiX, TanW, et al. . Modeling process–structure–property relationships in metal additive manufacturing: a review on physics-driven versus data-driven approaches. J Phys Mater, 2021, 4: 032002.

Funding

National Natural Science Foundation of China(52275317)

Natural Science Foundation of Guangdong Province(2023A1515012172)

Guangzhou Municipal Special Fund Project for Scientific and Technological Innovation and Development(2023B03J1326)

RIGHTS & PERMISSIONS

Shanghai University and Periodicals Agency of Shanghai University and Springer-Verlag GmbH Germany, part of Springer Nature