Real-time monitoring of high-power disk laser welding statuses based on deep learning framework

  • Yanxi Zhang
  • Deyong You
  • Xiangdong GaoEmail author
  • Congyi Wang
  • Yangjin Li
  • Perry P. Gao


The laser welding quality is determined by its welding statuses, and online welding statuses are depicted by the real-time signals captured from the welding process. A multiple-sensor system is designed to obtain information as comprehensive as possible for welding statuses monitoring. The multiple-sensor system includes an auxiliary illumination visual sensor system, an ultraviolet and visible band visual sensor system, a spectrometer and two photodiodes. The signals captured by different sensors are analyzed via signal or digital image processing algorithms, and distinct features are extracted from these signals to depict the online welding statuses. A deep learning framework based on stacked sparse autoencoder (SSAE) is established to model the relationship between the multi-sensor features and their corresponding welding statuses, and Genetic algorithm (GA) is applied to optimize the parameters of the SSAE framework (SSAE-GA). The proposed framework achieves higher accuracy and stronger robustness in monitoring welding status by comparing with the backpropagation neural network, support vector machine and random forest. Three new experiments with different welding parameters are implemented to validate the effectiveness and generalization of our proposed method. This study provides a novel and accurate method for high-power disk laser welding status monitoring.


Features fusion Deep learning Genetic algorithm Stacked sparse autoencoder Multiple-sensor signals 



This work was partly supported by the National Natural Science Foundation of China (Grant Numbers 51675104, 61703110), Innovation Team Project, Department of Education of Guangdong Province, China (2017KCXTD010), the Guangdong Provincial Natural Science Foundation of China (Grant Numbers 2017A030310494, 2016A030310347) and Youth Science Foundation of Guangdong University of Technology (Grant Number 16ZK0010). Many thanks are given to Katayama Laboratory of Osaka University for their assistance of laser welding experiments.


  1. Alvear-Sandoval, R. F., & Figueiras-Vidal, A. R. (2018). On building ensembles of stacked denoising auto-encoding classifiers and their further improvement. Information Fusion, 39, 41–52.CrossRefGoogle Scholar
  2. Atabaki, M. M., Yazdian, N., Ma, J., & Kovacevic, R. (2016). High power laser welding of thick steel plates in a horizontal butt joint configuration. Optics & Laser Technology, 83, 1–12.CrossRefGoogle Scholar
  3. Charte, D., Charte, F., García, S., Jesus, M. J., & Herrera, F. (2018). A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines. Information Fusion, 44, 78–96.CrossRefGoogle Scholar
  4. Cho, J. H., & Na, S. J. (2007). Theoretical analysis of keyhole dynamics in polarized laser drilling. Journal of Physics D: Applied Physics, 40, 7638–7647.CrossRefGoogle Scholar
  5. Dos Santos, E. M., Sabourin, R., & Maupin, P. (2009). Overfitting cautious selection of classifier ensembles with genetic algorithms. Information Fusion, 10, 150–162.CrossRefGoogle Scholar
  6. Gao, X. D., & Wen, Q. (2013). Monitoring of high-power fiber laser welding based on principal component analysis of a molten pool configuration. Laser Physics, 23, 126001.CrossRefGoogle Scholar
  7. Gao, X., You, D., & Katayama, S. (2012). Infrared image recognition for seam tracking monitoring during fiber laser welding. Mechatronics, 22, 370–380.CrossRefGoogle Scholar
  8. Garcia-Allende, P. B., Mirapeix, J., Conde, O. M., Cobo, A., & Lopez-Higuera, J. M. (2009). Spectral processing technique based on feature selection and artificial neural networks for arc-welding quality monitoring. NDT & E International, 42, 56–63.CrossRefGoogle Scholar
  9. Greses, J., Hilton, P. A., Barlow, P. A., & Steen, W. M. (2004). Plume attenuation under high power Nd: yttritium–aluminum–garnet laser welding. Journal of Laser Applications, 16, 9–15.CrossRefGoogle Scholar
  10. Jha, M. N., Pratihar, D. K., Bapat, A. V., Dey, V., Ali, M., & Bagchi, A. C. (2014). Knowledge-based systems using neural networks for electron beam welding process of reactive material (Zircaloy-4). Journal of Intelligent Manufacturing, 25, 1315–1333.CrossRefGoogle Scholar
  11. Jia, F., Lei, Y., Lin, J., Zhou, X., & Lu, N. (2016). Deep neural networks: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data. Mechanical Systems and Signal Processing, 72–73, 303–315.CrossRefGoogle Scholar
  12. Kong, F., Ma, J., Carlson, B., & Kovacevic, R. (2012). Real-time monitoring of laser welding of galvanized high strength steel in lap joint configuration. Optics & Laser Technology, 44(7), 2186–2196.CrossRefGoogle Scholar
  13. Kuo, C. F. J., Tung, C. P., & Weng, W. H. (2019). Applying the support vector machine with optimal parameter design into an automatic inspection system for classifying micro-defects on surfaces of light-emitting diode chips. Journal of Intelligent Manufacturing, 30, 727–741.CrossRefGoogle Scholar
  14. Liu, C. Q., Li, Y. G., Zhou, G. Y., & Shen, W. M. (2018). A sensor fusion and support vector machine based approach for recognition of complex machining conditions. Journal of Intelligent Manufacturing, 29, 1739–1752.CrossRefGoogle Scholar
  15. Liu, Y., Zhou, S., & Chen, Q. (2011). Discriminative deep belief networks for visual data classification. Pattern Recognition, 44(10–11), 2287–2296.CrossRefGoogle Scholar
  16. Mirapeix, J., García-Allende, P. B., Cobo, A., Conde, O. M., & López-Higuera, J. M. (2007). Real-time arc-welding defect detection and classification with principal component analysis and artificial neural networks. NDT & E International, 40, 315–323.CrossRefGoogle Scholar
  17. Molino, A., Martina, M., Vacca, F., Masera, G., Terreno, A., Pasquettaz, G., et al. (2009). FPGA implementation of time–frequency analysis algorithms for laser welding monitoring. Microprocessors and Microsystems, 33, 179–190.CrossRefGoogle Scholar
  18. Paleocrassas, A. G., & Tu, J. F. (2010). Inherent instability investigation for low speed laser welding of aluminum using a single-mode fiber laser. Journal of Materials Processing Technology, 210(10), 1411–1418.CrossRefGoogle Scholar
  19. Pang, S., Chen, X., Shao, X., Gong, S., & Xiao, J. (2016). Dynamics of vapor plume in transient keyhole during laser welding of stainless steel: Local evaporation, plume swing and gas entrapment into porosity. Optics and Lasers in Engineering, 82, 28–40.CrossRefGoogle Scholar
  20. Pang, S., Chen, X., Zhou, J., Shao, X., & Wang, C. (2015). 3D transient multiphase model for keyhole, vapor plume, and weld pool dynamics in laser welding including the ambient pressure effect. Optics and Lasers in Engineering, 74, 47–58.CrossRefGoogle Scholar
  21. Pimenov, D. Y., Bustillo, A., & Mikolajczyk, T. (2018). Artificial intelligence for automatic prediction of required surface roughness by monitoring wear on face mill teeth. Journal of Intelligent Manufacturing, 29, 1045–1061.CrossRefGoogle Scholar
  22. Rodil, S. S., Gómez, R. A., Bernárdez, J. M., Rodríguez, F., Miguel, L. J., & Perán, J. R. (2010). Laser welding defects detection in automotive industry based on radiation and spectroscopical measurements. International Journal of Advanced Manufacturing Technology, 49(1), 133–145.CrossRefGoogle Scholar
  23. Ronao, C. A., & Cho, S. B. (2016). Human activity recognition with smartphone sensors using deep learning neural networks. Expert Systems with Applications, 59, 235–244.CrossRefGoogle Scholar
  24. Sforza, P., & Blasiis, D. (2002). Online optical monitoring system for arc welding. NDT & E International, 35, 37–43.CrossRefGoogle Scholar
  25. Shao, H., Jiang, H., Wang, F., & Zhao, H. (2017). An enhancement deep feature fusion method for rotating machinery fault diagnosis. Knowledge-Based Systems, 119, 200–220.CrossRefGoogle Scholar
  26. Sibillano, T., Ancona, A., Berardi, V., & Lugara, P. M. A. (2009). Real-time spectroscopic sensor for monitoring laser welding processes. Sensors, 9(5), 3376–3385.CrossRefGoogle Scholar
  27. Srinivasa Murthy, Y. V., & Koolagudi, S. G. (2018). Classification of vocal and non-vocal segments in audio clips using genetic algorithm based feature selection (GAFS). Expert Systems with Applications, 106, 77–91.CrossRefGoogle Scholar
  28. Tamilselvan, P., & Wang, P. (2013). Failure diagnosis using deep belief learning based health state classification. Reliability Engineering & System Safety, 115, 124–135.CrossRefGoogle Scholar
  29. Tan, W., Bailey, N. S., & Shin, Y. C. (2013). Investigation of keyhole plume and molten pool based on a three-dimensional dynamic model with sharp interface formulation. Journal of Physics D: Applied Physics, 46, 055501.CrossRefGoogle Scholar
  30. Wang, L., Gao, X., & Chen, Z. (2018). Status analysis of keyhole bottom in laser-MAG hybrid welding process. Optics Express, 26, 347–355.CrossRefGoogle Scholar
  31. Zhang, Y. X., & Gao, X. D. (2013). Analysis of characteristics of molten pool using cast shadow during high-power disk laser welding. The International Journal of Advanced Manufacturing Technology, 70, 1979–1988.CrossRefGoogle Scholar
  32. Zhang, Y. X., Gao, X. D., & Katayama, S. (2015). Weld appearance prediction with BP neural network improved by genetic algorithm during disk laser welding. Journal of Manufacturing Systems, 34, 53–59.CrossRefGoogle Scholar
  33. Zhang, Y., Li, F. Z., Liang, Z. C., Ying, Y. Y., Lin, Q. D., & Wei, H. Y. (2018). Correlation analysis of penetration based on keyhole and plasma plume in laser welding. Journal of Materials Processing Technology, 256, 1–12.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  • Yanxi Zhang
    • 1
  • Deyong You
    • 1
  • Xiangdong Gao
    • 1
    Email author
  • Congyi Wang
    • 1
  • Yangjin Li
    • 1
  • Perry P. Gao
    • 2
  1. 1.Guangdong Provincial Welding Engineering Technology Research CenterGuangdong University of TechnologyGuangzhouChina
  2. 2.US-China Youth Education Solutions FoundationNew YorkUSA

Personalised recommendations