Advertisement

Sensing of Arc Length and Wire Extension Using Neural Network in Robotic Welding

  • Kazuhiko Eguchi
  • Satoshi Yamane
  • Hideo Sugi
  • Kenji Oshima
Conference paper
  • 581 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1424)

Abstract

It is important to design intelligent welding robots to obtain a good quality of the welding. It is required to detect bead height and deviation from center of gap and to control arc length and back bead by adjusting welding conditions such as welding speed, power source voltage and wire feed rate. Authors propose arc sensor using neural networks to detect arc length and wire extension. By using them and by means of geometric method, the bead height is detected. Moreover, authors propose switch back welding method to get stable back bead. That is, welding torch is not only woven in the groove, but also moved backward and forward.

Keywords

Base Metal Weld Pool Welding Speed Wire Feed Rate Welding Torch 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    P. Drews, G. Starke, “Welding in the Century of Information Technology”, Int. Conf. on Advanced Techniques and Low Cost Automation, pp.3–22(1994)Google Scholar
  2. 2.
    K. Ohshima, et. al., “Digital Control of Torch Position and Weld Pool in MIG-Welding Using Image Processing Device”, Trans. of IEEE IAS, Vol.28,No.3, pp.607–612(1992)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Kazuhiko Eguchi
    • 1
  • Satoshi Yamane
    • 2
  • Hideo Sugi
    • 2
  • Kenji Oshima
    • 2
  1. 1.Semiconductor & IC Division Hitachi, Ltd.Kodairashi TokyoJapan
  2. 2.Department of Environmental Science & Human EngineeringSaitama UniversityUrawaJapan

Personalised recommendations