Transactions on Control, Automation and Systems Engineering

Institute of Control, Robotics and Systems (제어로봇시스템학회)
권호 표지

A Neural Network- Based Classification Method for Inspection of Bead Shape in High Frequency Electric Resistance Weld

  • Published : 2000.09.01
Download PDF
⟨ Previous Next ⟩

Abstract

High-frequency electric resistance welding (HERW) technique is one of the most productive manufacturing method currently available for pipe and tube production because of its high welding speed. In this process, a heat input is controlled by skilled operators observing color and shape of bead but such a manual control can not provide reliability and stability required for manufacturing pipes of high grade quality because of a variety of bead shapes and noisy environment. In this paper, in an effort to provide reliable quality inspection, we propose a neural network-based method for classification of bead shape. The proposed method utilizes the structure of Kohonen network and is designed to learn the skill of the expert operators and to provide a good solution to classify bead shapes according to their welding conditions. This proposed method is implemented on the real pipe manufacturing process, and a series of experiments are performed to show its effectiveness.

Keywords

References

  1. Nippon Steel technical report no. 14 Welding mechanisms in high-frequency electric resistance welding H. Gondo;H. Haga;K. Aoki;T. Sato
  2. Transaction ISIJ. v.25 High-frequency ERW phenomena and weld defect ratio under high-speed and large v-convergence angle condition H. Haga;N. Mizuhashi
  3. Transaction ISIJ. v.24 Relation between current voltage and power in oscillator and load circuit during HFERW H. Saito;A. Siga;T. Enami;M. Itatani;H. Kasahara
  4. Nippon Steel Technical report no. 20 Welding technology in manufacture of large-diameter line pipe S. Sugimura;H. Matsuda
  5. Nippon steel Technical report Welding phenomena and welding mechanisms in high frequency electric resistance welding - 1st Report H. Haga;K. Aoki;T.Sato
  6. Nippon Steel Technical report An automatic power input control system in high frequency electric resistance welding N. Watanable;M. Funaki;S. Sanmiya;N. Kosuge;H. Haga;N. Mizuhashi
  7. Nippon Steel Technical report no. 30 High frequency induction welded high-strength steel pipe N. Tanaka;T. Iwasaki;N. Watanabe;Y. Tamura
  8. Transaction ISII v.26 A new automatic heat input control for producton of electric resistance welded pipe Y. Mihara
  9. Nippon Kokan Technical report Newly developed heat input control & monitoring system for ERW tube production S. Ishiro;Y. Enomoto;Ikuo Takahashi;Isamu Komine;Yutaka Mihara;Koji Suzuki
  10. The Sumitomo search no.49 Recent progress in automatic welding control system for ERW tube mill O. Sugiyama;C. Takamadate;T. Hikita
  11. Sumitomo Technical report Automatic welding control system for electric-resistance weld tube mill T. Kyogoku(et al.)
  12. Research Report, Dept. of Mechanical Engineering Development of heat input control System for high frequency resistance welding machine H. S. Cho;J. H. Kim;K. W. Ko
  13. World Automation Congress'98 A bead shape classification method using neural network in high fequency electric resistance weld K.W.Ko;H.S.Cho;J.H.Kim
  14. IEEE Transactions on Pattern Analysis and Machine Intelligence v.10 no.3 Real-time part position sensing S. J. Gordon
  15. Computer vision, Graphics, and Image processing v.48 Modeling sensors: toward automatic generation of object recognition program K. Ikeuchi;T. Kanade
  16. Machine Vision and Application v.2 Active, optical range image sensors J.Paul
  17. Digital image processing (3rd ed.) R Conzalez;R. E. Woods
  18. Computer and robot vision v.1 H. Shapiro
  19. Computer Vision (4th ed.) D. H. Ballard;C.M. Brown
  20. Introduction to the theory of neural computation (6th ed.) J. Hertz;A. Krogh;R.G. Palmer
  21. Adaptive pattern recognition and neural networks (5th ed.) Y. Pao
  22. Introduction to artificial neural sytems (3rd ed.) J. M. Zurada