Signal Processing using Fuzzy Logic and Neural Network for Welding Gap Detection

  • Kim, Gwan-Hyung (Dept. of Electronic & Communication Eng., Korea Maritime University) ;
  • Kim, Il (Dept. of Multimedia Eng., Dong-Pusan Collage) ;
  • Lee, Sang-Bae (Dept. of Electronic & Communication Eng., Korea Maritime University)
  • Published : 2001.04.01

Abstract

Welding is essential for the manufacture of a range of engineering components which may vary from very large structures such as ships and bridges to very complex structures such as aircraft engines, or miniature components for microelectronic applications. Especially, a domestic situation of the welding automation is still depend on the arc sensing system in comparison to the vision sensing system. Specially, the gap-detecting of workpiece using conventional arc sensor is proposed in this study. As a same principle, a welding current varies with the size of a welding gap. This study introduce to the fuzzy membership filter to cancel a high frequency noise of welding current, and ART2 which has the competitive learning network classifies the signal patterns the filtered welding signal. A welding current possesses a specific pattern according to the existence or the size of a welding gap. These specific patterns result in different classification in comparison with an occasion for no welding gap. The patterns in each case of 1mm, 2mm, 3mm and no welding gap are identified by the artificial neural network.

Keywords

References

  1. Welding Journal Robotic are welding under adaptive control-A survey of current technology J. Hanright
  2. IEEE Transactions on Industrial Electronics v.IE-30 Robotic are welding:Research in sensory feedback control Cook, G. E.
  3. Transactions of the Japan Welding Society v.18 no.2 Automatic real-time bead height control with arc sensor Nomura H.;Sugitani Y.;Tamaoki, N.
  4. Transactions of the Japan Welding Society v.18 no.1 Joint tracking control sensor of GMAW Fujimura, H.;Ide, E.;Inoue, H.
  5. IIW Doc. v.XII GMA welding of filler passes with a new type of arc controlled seam tracking system Eichhorn, F.;Blasig, K.;Platz, J.
  6. IIW Doc. v.XII Arc sensor for welding line tracking applied to welding robot Nakajima, J.;Araya, T.;Tsuji, M.;Sarugaki, S.
  7. Neural Networks v.10 no.4 A comparative study of self-organizing clustering algorithms dignet and ART2 Chin-Der Wann;Stelios C. A. Thomopoulos
  8. IEEE Comput. v.21 no.3 The ART of adptive pattern recognition by a self-organizing neural network Carpenter, G.A.;Grossberg S.
  9. Applied Optics v.26 no.23 ART2: Self-organization of stable category recognition codes for analog input patterns Carpenter, G.A.;Grossberg S.