Journal of Welding and Joining

The Korean Welding and Joining Society (대한용접접합학회)
권호 표지

Development of Algorithm for Prediction of Bead Height on GMA Welding

GMA 용접의 최적 비드 높이 예측 알고리즘 개발

  • 김인수 (목포대학교 공과대학 기계공학과 대학원) ;
  • 박창언 (목포대학교 공과대학 기계공학과) ;
  • 김일수 (목포대학교 공과대학 기계공학과) ;
  • 손준식 (목포대학교 공과대학 기계공학과 대학원) ;
  • 안영호 (목포기능대학) ;
  • 김동규 (목포기능대학) ;
  • 오영생 (목포기능대학)
  • Published : 1999.10.01
Download PDF
⟨ Previous Next ⟩

Abstract

The sensors employed in the robotic are welding system must detect the changes in weld characteristics and produce the output that is in some way related to the change being detected. Such adaptive systems, which synchronise the robot arm and eyes using a primitive brain will form the basis for the development of robotic GMA(Gas Metal Arc) welding which increasingly higher levels of artificial intelligence. The objective of this paper is to realize the mapping characteristics of bead height through learning. After learning, the neural estimation can estimate the bead height desired from the learning mapping characteristic. The design parameters of the neural network estimator(the number of hidden layers and the number of nodes in a layer) are chosen from an estimation error analysis. A series of bead of bead-on-plate GMA welding experiments was carried out in order to verify the performance of the neural network estimator. The experimental results show that the proposed neural network estimator can predict the bead height with reasonable accuracy and guarantee the uniform weld quality.

Keywords

References

  1. International Series in Materials Science and Technology v.33 Analysis of Welded Structure K. Masubuchi
  2. Metallurty of Welding (Third Edition) J. F. Lancaster
  3. Engineering Fracture Mechanics v.36 no.6 Effects of Welding Residual Stresses on Fatigue Crack Growth Behaviour in Butt Welds of a Pipeline Steel Y. W. Shi;B. Y. Chen
  4. Engineering Fracture Mechanics v.38 no.6 Residual Stress Analysis in Weldments V. Ramamurti;S. Suresh
  5. Welding Journal v.63 no.3 Coaxial weld pool viewing for process monitoring and control R. W. Richardson;A. Gutow;R. A. Anderson;D. F. Farson
  6. Advances in Welding Science and Technology Effect of welding parameters and grove angle on the soundness of root beads depodited by the SAW process R. S. Chandel;S. R. Bala
  7. 3rd Int. Con. on Treds in welding Research Recent actives in sensing and adaptive control of arc welding T. Araya;S. Saikawa
  8. IEEE Spectrum v.25 no.3 Neurocomputing : Picking the human brain R. Hecht-Nielsen
  9. IEEE Trans. on. Systems. Man, and Cybernetics v.15 no.1 Fuzzy identification of system and its applications to modeling and control T. Tkagi;M. Sugeno
  10. The Welding Institute Report 4/1972/PE An examination of the influence of process parameters in submerged arc welding P. A. Drayton
  11. Proceedings of the Forth International Conference on Medeling of Casting and Welding Processes Mathenatical modeling of gas metal arc weld features R. S. Chandel
  12. Proc. IMechE v.205 A study on Prediction of Welding Current in Gas Metal Arc Welding part1: Modeling of Welding Current in Response to Change of Tip-to-Workpoece Distance J. W. Kim;S. J. Na
  13. Proc. IMechE v.295 A study on Prediction of Welding Current in Gas Metal Arc Welding part2: Experimental Modelling of Relationship between Welding Current and Tip-to-Work-piece Distance and Its Application to Weld1 Seam Tracking System J. W. Kim;S. J. Na
  14. Recent Trends in Welding Science and Technology : TWR'89 : Proceeding of the 2nd International Conference on Trends in Welding research Keynote address : Fddeback and adaptive control in welding G. E. Cook;K. Andersen;R. J. Barrett