Real-Time Control of Laser Beam Welding Processes: Reality

  • Leonardo Nicolosi
  • Andreas Blug
  • Felix Abt
  • Ronald Tetzlaff
  • Heinrich Höfler
  • Daniel Carl
Chapter

Abstract

Cellular neural networks (CNN) are more and more attractive for closed-loop control systems based on image processing because they allow for the combination of high computational power and short feedback times. This combination enables new applications, which are not feasible for conventional image processing systems. Laser beam welding (LBW), which has been largely adopted in the industrial scenario, is an example for such processes. Concerning the latter, monitoring systems using conventional cameras are quite common, but they do a statistical postprocess evaluation of certain image features for quality control purposes. Earlier attempts to build closed-loop control systems failed due to the lack of computational power. In order to increase controlling rates and decrease false detections by a more robust evaluation of the image feature, strategies based on CNN operations have been implemented in a cellular architecture called Q-Eye. They allow enabling the first robust closed-loop control system adapting the laser power by observing the full penetration hole (FPH) in the melt. In this paper, the algorithms adopted for the FPH detection in process images are described and compared. Furthermore, experimental results obtained in real-time applications are also discussed.

Keywords

Welding Assure Smoke 

Notes

Acknowledgements

This work was financed by the Baden-Württemberg Stiftung gGmbH within the project “Analoge Bildverarbeitung mit zellularen neuronalen Netzen (CNN) zur Regelung laserbasierter Schweißprozesse (ACES).”

References

  1. 1.
    Schmidt, M., Albert, F., Frick, T., Grimm, A., Kägeler, C., Rank, M., Tangermann-Gerk, K.: Process control in laser manufacturing – Dream or reality. Laser Materials Processing Conference. In Proc. of ICALEO 2007, pp. 1087–1096Google Scholar
  2. 2.
    Fortunato, A., Ascari, A.: Tecnologie di giunzione mediante saldatura, procedimenti non convenzionali e allo stato solido, vol. 2 (Societá editrice Esculapio S.R.L., 2008)Google Scholar
  3. 3.
    Dawes, C.: Laser welding, a practical guide (Abington Publishing, 1992), isbn: 1-85573-034-0Google Scholar
  4. 4.
    Blug, A., Abt, F., Nicolosi, L., Carl, D., Dausinger, F., Höfler, H., Tetzlaff, R., Weber, R.: Closed loop control of laser welding processes using cellular neural network cameras: Measurement technology. In Proc. of the 28th International Congress on Applications of Lasers and Electro Optics, ICALEO, November 2–5 2009, OrlandoGoogle Scholar
  5. 5.
    Bicknell, A., Smith, J.S., Lucas, J.: Infrared sensor for top face monitoring of weld pools. Meas. Sci. Technol. 5 (1994), pp. 371–378CrossRefGoogle Scholar
  6. 6.
    Li, L., Brookfield, D.J., Steen, W.M.: Plasma charge sensor for in-process, non-contact monitoring of the laser welding process. Meas. Sci. Technol. 7 (1996), pp. 615–626CrossRefGoogle Scholar
  7. 7.
    Zhang, X., Chen, W., Jiang, P., Liu, C., Guo, J.: Double closed-loop control of the focal point position in laser beam welding. Meas. Sci. Technol. 14 (2003), pp. 1938–1943CrossRefGoogle Scholar
  8. 8.
    Park, H., Rhee, S., Kim, D.: A fuzzy pattern recognition based system for monitoring laser weld quality. Meas. Sci. Technol. 12 (2001), pp. 1318–1324CrossRefGoogle Scholar
  9. 9.
    Haran, F.M., Hand, D.P., Ebrahim, S.M., Peters, C., Jones, J.D.C.: Optical signal oscillations in laser keyhole welding and potential application to lap welding. Meas. Sci. Technol. 8 (1997), pp. 627–633CrossRefGoogle Scholar
  10. 10.
    Sibillano, T., Ancona, A., Berardi, V., Lugará, P.M.: A real-time spectroscopic sensor for monitoring laser welding processes. Sensors 9 (2009), pp. 3376–3385, doi: 10.3390/s90503376CrossRefGoogle Scholar
  11. 11.
    Otto, A., Hohenstein, R., Dietrich, S.: Diagnostik und Regelung beim Laserstrahlschweißen. Presented at the 5th Laser-Anwenderforum, 2006, BremenGoogle Scholar
  12. 12.
    Beersiek, J.: New aspects of monitoring with a CMOS camera for laser materials processing. In Proc. of the 21st International Congress on Applications of Lasers and Electro-Optics, ICALEO, 2002Google Scholar
  13. 13.
    Chen, W., Zhang, X., Jia, L.: Penetration monitoring and control of CO2 laser welding with coaxial visual sensing system. Lasers in Material Processing and Manufacturing II. Edited by Deng, ShuShen; Matsunawa, Akira; Yao, Y. Lawrence; Zhong, Minlin. In Proc. of the SPIE, vol. 5629 (2005), pp. 129–140Google Scholar
  14. 14.
    Müller-Borhanian, J., Deininger, C., Dausinger, F.H., Hügel, H.: Spatially resolved on-line monitoring during laser beam welding of steel and aluminium. In Proc. of the 23rd International Congress on Applications of Lasers and Electro-Optics, ICALEO, 2004Google Scholar
  15. 15.
    Bardin, F., Cobo, A., Lopez-Higuera, J.M., Collin, O., Aubry, P., Dubois, T., Högström, M., Nylen, O., Jonsson, P., Jones, J.D.C., Hand, D.P.: Optical techniques for real-time penetration monitoring for laser welding. Appl. Optic. 44(19) (2005), pp. 3869–3876CrossRefGoogle Scholar
  16. 16.
    De Graaf, M.W., Olde Benneker, J., Aarts, R.G.K.M., Meijer, J., Jonker, J.B.: Robust process-controller for Nd:Yag welding. In Proc. of the International Conference on Applications of Lasers and Electro-optics, ICALEO, October 31–November 3 2005, Miami, FL, USAGoogle Scholar
  17. 17.
    Chua, L.O., Roska, T.: Cellular neural networks and visual computing. Foundations and applications. Cambridge University Press, 2004, first published in printed format 2002Google Scholar
  18. 18.
    Nicolosi, L., Tetzlaff, R., Abt, F., Blug, A., Höfler, H., Carl, D.: New CNN based algorithms for the full penetration hole extraction in laser welding processes. In Proc. of the IEEE International Symposium on Circuits and Systems, ISCAS, pp. 2713–2716, May 24–27 2009, Taipei, TaiwanGoogle Scholar
  19. 19.
    Nicolosi, L., Tetzlaff, R., Abt, F., Blug, A., Carl, D., Höfler, H.: New CNN based algorithms for the full penetration hole extraction in laser welding processes: Experimental results. In Proc. of the IEEE International Joint Conference on Neural Networks, IJCNN, pp. 2256–2263, June 14–19 2009, Atlanta, GA, USAGoogle Scholar
  20. 20.
    Nicolosi, L., Tetzlaff, R., Abt, F., Blug, A., Höfler, H., Carl, D.: Omnidirectional algorithm for the full penetration hole extraction in laser welding processes. In Proc. of the European Conference on Circuit Theory and Design, ECCTD, pp. 177–180, August 23–27 2009, Antalya, TurkeyGoogle Scholar
  21. 21.
    Nicolosi, L., Tetzlaff, R., Abt, F., Blug, A., Höfler, H.: Cellular neural network (CNN) based control algorithms for omnidirectional laser welding processes: Experimental results. In Proc. of the 12th International Workshop on Cellular Nanoscale Networks and Applications, CNNA, February 2–5 2010, Berkeley, CA, USAGoogle Scholar
  22. 22.
    Chua, L.O., Yang, L.: Cellular neural networks: Theory. IEEE Trans. Circ. Syst. 35(10) (1988), pp. 1257–1272MathSciNetMATHCrossRefGoogle Scholar
  23. 23.
    Corinto, F., Gilli, M., Civalleri, P.P.: On stability of full range and polynomial type CNNs. In Proc. of the 7th IEEE International Workshop on Cellular Neural Networks and their Applications, CNNA, pp. 33–40, July 22–24 2002Google Scholar
  24. 24.
    Linan, G., Dominguez-Castro, R., Espejo, S., Rodriguez-Vazquez, A.: Design of Large-Complexity Analog I/O CNNUC. Presented at the Design Automation Day on Cellular Visual Microprocessor, ECCTD, pp. 42–57, 1999, Stresa, ItalyGoogle Scholar
  25. 25.
    Chua, L.O., Yang, L.: Cellular neural networks: Applications. IEEE Trans. Circ. Syst. pp. 1273–1290Google Scholar
  26. 26.
    Yalcin, M., Suykens, J., Vandewalle, J.: Cellular Neural Networks, Multi-Scroll Chaos And Synchronization. World scientific series on nonlinear science, series A, vol. 50, 2005, isbn: 978-981-256-161-9Google Scholar
  27. 27.
    Yokosawa, K., Tanji, Y., Tanaka, M.: CNN with multi-level hysteresis quantization output. In Proc. of the 6th IEEE International Workshop on Cellular Neural Networks and Their Applications, CNNA, 2000Google Scholar
  28. 28.
    Gilli, M., Roska, T., Chua, L., Civalleri, P.P.: CNN Dynamics Represents a Broader Range Class than PDEs. Int. J. Bifurcat. Chaos 12(10) (2002), pp. 2051–2068MathSciNetMATHCrossRefGoogle Scholar
  29. 29.
    Adamatzky, A., Costello, B., Asai, T.: Reaction-Diffusion Computers. Elsevier Science and Technology, 2005, isbn: 978-0-444-52042-5Google Scholar
  30. 30.
    Bardin, F., Cobo, A., Lopez-Higuera, J.M., Collin, O., Aubry, P., Dubois, T., Högström, M., Nylen, O., Jonsson, P., Jones, J.D.C., Hand, D.P.: Closed-loop power and focus control of laser welding for full-penetration monitoring. Appl. Optic. 44(1) (2005)Google Scholar
  31. 31.
    Nicolosi, L., Tetzlaff, R.: Real Time Control of Curved Laser Welding Processes by Cellular Neural Networks (CNN): First Results. Presented at the Kleinheubacher Tagung, U.R.S.I. Landesausschuss in der Bundesrepublik Deutschland e.V., September 28–October 1 2009, Miltenberg, Germany. Adv. Radio Sci., 8, 117–122, 2010,www.adv-radio-sci.net/8/117/2010/,doi: 10.5194/ars-8-117-2010
  32. 32.
    Abt, F., Blug, A., Nicolosi, L., Dausinger, F., Weber, R., Tetzlaff, R., Carl, D., Höfler, H.: Closed loop control of laser welding processes using cellular neural network cameras – experimental results. In Proc. of the 28th International Congress on Applications of Lasers and Electro Optics, ICALEO, November 2–5 2009, OrlandoGoogle Scholar
  33. 33.
    Abt, F., Blug, A., Nicolosi, L., Dausinger, F., Höfler, H., Tetzlaff, R., Weber, R.: Real time closed loop control of full penetration keyhole welding with cellular neural network cameras. In Proc. of the 5th International Congress on Laser Advanced Materials Processing, LAMP, June 29–July 2 2009, KobeGoogle Scholar
  34. 34.
    Blug, A., Jetter, V., Strohm, P., Carl, D., Höfler, H.: High power LED lighting for CNN based image processing at frame rates of 10 kHz. Presented at the 12th IEEE International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2010, February 3–5 2010, Berkeley, CA, USAGoogle Scholar
  35. 35.
    Strohm, P., Blug, A., Carl, D., Höfler, H.: Using Cellular neural network to control highly dynamic laser processes. Presented at Laser Optics Berlin, LOB, 2010Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Leonardo Nicolosi
    • 1
  • Andreas Blug
  • Felix Abt
  • Ronald Tetzlaff
  • Heinrich Höfler
  • Daniel Carl
  1. 1.Technische Universität DresdenDresdenGermany

Personalised recommendations