Abstract
In this research, a data-driven model is developed to monitor the seam during the laser beam welding under the influence of an external magnetic field (LBW-AMF). Firstly, a visible LBW-AMF system is built for tracking the laser melting pool and keyhole. Then, the features of the laser melting pool and keyhole are extracted with image processing techniques. The approach for an ensemble of different neural networks which includes radial basis function neural network, back-propagation neural network, and generalized regression neural network is proposed to establish the correlations of the characteristics of the laser melting pool and keyhole and the welding seam. Finally, LBW-AMF experimental results are obtained to validate the performance of the proposed data-driven model. Results illustrate that the developed model can provide a reliable result for monitoring the weld bead, which could give guidance for controlling the processing parameters in real time to improve the weld quality for practical LBW-AMF.
Similar content being viewed by others
Abbreviations
- AK:
-
The area of the keyhole
- WM:
-
The width of the molten pool
- BPNN:
-
Back-propagation neural network
- ENN:
-
The ensemble of neural networks
- GRNN:
-
Generalized regression neural network
- GTAW:
-
Gas tungsten arc welding
- LK:
-
The length of the keyhole
- LBW-AMF:
-
Laser beam welding assisted by magnetic field
- MAE:
-
Maximum absolute error
- WK:
-
The width of keyhole
- MF:
-
Magnetic field
References
Zhou Q, Cao L, Zhou H, Huang X (2018) Prediction of angular distortion in the fiber laser keyhole welding process based on a variable-fidelity approximation modeling approach. J Intell Manuf 29:719–736
Huang L, Hua X, Wu D, Ye Y (2019) Role of welding speed on keyhole-induced porosity formation based on experimental and numerical study in fiber laser welding of Al alloy. Int J Adv Manuf Technol 103:913–925
Li S, Chen G, Zhou C (2015) Effects of welding parameters on weld geometry during high-power laser welding of thick plate. Int J Adv Manuf Technol 79:177–182
Stavridis J, Papacharalampopoulos A, Stavropoulos P (2017) Quality assessment in laser welding: a critical review. Int J Adv Manuf Technol 94:1825–1847
You D, Gao X, Katayama S (2015) WPD-PCA-based laser welding process monitoring and defects diagnosis by using FNN and SVM. IEEE Trans Ind Electron 62:628–636
Chen J, Zhang Y, Wu C, Padhy GK (2019) Suppression of undercut defects in high-speed GMAW through a compound magnetic field. J Mater Process Technol 274:1–11
Fritzsche A, Avilov V, Gumenyuk A, Hilgenberg K, Rethmeier M (2016) High power laser beam welding of thick-walled ferromagnetic steels with electromagnetic weld pool support. Phys Procedia 83:362–372
Gatzen M, Tang Z, Vollertsen F, Mizutani M, Katayama S (2011) X-ray investigation of melt flow behavior under magnetic stirring regime in laser beam welding of aluminum. J Laser Appl 23:032002
Tang Z, Gatzen M (2010) Influence on the dilution by laser welding of aluminum with magnetic stirring. Phys Procedia 5:125–137
Bachmann M, Avilov V, Gumenyuk A, Rethmeier M (2011) CFD simulation of the liquid metal flow in high power laser welding of aluminum with electromagnetic weld pool support. In Proc. 2nd Int. Conf.: 179–184
Zhou J, Tsai H-L (2007) Effects of electromagnetic force on melt flow and porosity prevention in pulsed laser keyhole welding. Int J Heat Mass Transf 50:2217–2235
Chen J, Wei Y, Zhan X, Gao Q, Zhang D, Gao X (2018) Influence of magnetic field orientation on molten pool dynamics during magnet-assisted laser butt welding of thick aluminum alloy plates. Opt Laser Technol 104:148–158
Chen J, Wei Y, Zhan X, Gu C, Zhao X (2018) Thermoelectric currents and thermoelectric-magnetic effects in full-penetration laser beam welding of aluminum alloy with magnetic field support. Int J Heat Mass Transf 127:332–344
Chen X, Luo M, Hu R, Li R, Liang L, Pang S (2019) Thermo-electromagnetic effect on weld microstructure in magnetically assisted laser welding of austenite steel. J Manuf Process 41:111–118
Torabi A, Kolahan F (2018) Optimizing pulsed Nd:YAG laser beam welding process parameters to attain maximum ultimate tensile strength for thin AISI316L sheet using response surface methodology and simulated annealing algorithm. Opt Laser Technol 103:300–310
Gao JQ, Qin GL, Yang JL, He JG, Zhang T, Wu CS (2011) Image processing of weld pool and keyhole in Nd:YAG laser welding of stainless steel based on visual sensing. T Nonfree Metal Soc 21:423–428
Jin Z, Li H, Jia G, Gao H (2016) Dynamic nonlinear modeling of 3D weld pool surface in GTAW. Robot Comput Integr Manuf 39:1–8
Zhang Y, Gao X, Katayama S (2015) Weld appearance prediction with BP neural network improved by genetic algorithm during disk laser welding. J Manuf Syst 34:53–59
Liu YK, Zhang YM (2014) Model-based predictive control of weld penetration in gas tungsten arc welding. IEEE Trans Control Syst Technol 22:955–966
Gao X, Zhong X, You D, Katayama S (2013) Kalman filtering compensated by radial basis function neural network for seam tracking of laser welding. IEEE Trans Contr Sys Techn 21:1916–1923
Chen J, Wang T, Gao X, Wei L (2018) Real-time monitoring of high-power disk laser welding based on support vector machine. Comput Ind 94:75–81
You DY, Gao XD, Katayama S (2013) Review of laser welding monitoring. Sci Technol Weld Join 19:181–201
Leng H, Li X, Zhu J, Tang H, Zhang Z, Ghadimi N (2018) A new wind power prediction method based on ridgelet transforms, hybrid feature selection and closed-loop forecasting. Adv Eng Inform 36:20–30
Zeghlache S, Mekki H, Bouguerra A, Djerioui A (2018) Actuator fault tolerant control using adaptive RBFNN fuzzy sliding mode controller for coaxial octorotor UAV. ISA Trans 80:267–278
Addeh J, Ebrahimzadeh A, Azarbad M, Ranaee V (2014) Statistical process control using optimized neural networks: a case study. ISA Trans 53:1489–1499
Liu Y, Yang D, Zhang C (2018) Relaxed conditions for convergence analysis of online back-propagation algorithm with L 2 regularizer for Sigma-Pi-Sigma neural network. Neurocomputing 272:163–169
Zeng X, Zhen Z, He J, Han L (2018) A feature selection approach based on sensitivity of RBFNNs. Neurocomputing 275:2200–2208
Li H-z, Guo S, Li C-j, Sun J-q (2013) A hybrid annual power load forecasting model based on generalized regression neural network with fruit fly optimization algorithm. Knowl-Based Syst 37:378–387
Xie Y, Li C, Lv Y, Yu C (2019) Predicting lightning outages of transmission lines using generalized regression neural network. Appl Soft Comput 78:438–446
Wang X, You M, Mao Z, Yuan P (2016) Tree-structure ensemble general regression neural networks applied to predict the molten steel temperature in ladle furnace. Adv Eng Inform 30:368–375
Pani AK, Mohanta HK (2015) Online monitoring and control of particle size in the grinding process using least square support vector regression and resilient back propagation neural network. ISA Trans 56:206–221
Song X, Lv L, Li J, Sun W, Zhang J (2018) An advanced and robust ensemble surrogate model: extended adaptive hybrid functions. J Mech Des 140:041402
Zhou, Q., Wang, Y., Choi, S. K., Cao, L., & Gao, Z. (2018). Robust optimization for reducing welding-induced angular distortion in fiber laser keyhole welding under process parameter uncertainty. Applied Thermal Engineering, 129, 893–906.
Qian, J., Yi, J., Cheng, Y., Liu, J., & Zhou, Q. (2019). A sequential constraints updating approach for Kriging surrogate model-assisted engineering optimization design problem. Engineering with Computers, 1–17.
Zhou, Q., Wu, J., Xue, T., & Jin, P. (2019). A two-stage adaptive multi-fidelity surrogate model-assisted multi-objective genetic algorithm for computationally expensive problems. Engineering with Computers, 1–17.
Acknowledgments
This research has been supported by the National Natural Science Foundation of China (NSFC) under Grant No. 51805179, and the National Defense Innovation Program under Grant No. 18-163-00-TS-004-033-01.
Author information
Authors and Affiliations
Corresponding author
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
Cao, L., Zhang, L. & Wu, Y. A data-driven model for weld bead monitoring during the laser welding assisted by magnetic field. Int J Adv Manuf Technol 107, 475–487 (2020). https://doi.org/10.1007/s00170-020-05028-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-020-05028-z