Transactions of the Korean Society of Machine Tool Engineers (한국공작기계학회논문집)

The Korean Society of Manufacturing Technology Engineers (한국생산제조학회)
권호 표지

Back-bead Prediction and Weldability Estimation Using An Artificial Neural Network

인공신경망을 이용한 이면비드 예측 및 용접성 평가

  • 이정익 (인하공업전문대학 기계시스템학부 기계설계과) ;
  • 고병갑 (인하공업전문대학 기계시스템학부 기계과)
  • Published : 2007.08.15
Download PDF
⟨ Previous Next ⟩

Abstract

The shape of excessive penetration mainly depends on welding conditions(welding current and welding voltage), and welding process(groove gap and welding speed). These conditions are the major affecting factors to width and height of back bead. In this paper, back-bead prediction and weldability estimation using artificial neural network were investigated. Results are as follows. 1) If groove gap, welding current, welding voltage and welding speed will be previously determined as a welding condition, width and height of back bead can be predicted by artificial neural network system without experimental measurement. 2) From the result applied to three weld quality levels(ISO 5817), both experimented measurement using vision sensor and predicted mean values by artificial neural network showed good agreement. 3) The width and height of back bead are proportional to groove gap, welding current and welding voltage, but welding speed. is not.

Keywords

References

  1. Lee, J. B., Bang, Y. W., Oh, S. W. and Chan, H. S., 1997, 'Control of Bead Geometry in GMAW,' Journal of the Korean Welding Society, Vol. 15, No. 6, pp. 116-123
  2. Kim, W. H. and Na, S. J., 1997, 'Numerical Analysis of Weldment by Considering the Convection of Welding Arc and Weld Pool,' Journal of the Korean Welding Society, Vol. 15, No. 1, pp. 26-35
  3. Ahn, J. H. and Kim, J. W., 'A study on the Back Bead Control by Using Short Circuit Frequency in GMA Welding of Sheet Metal,' Journal of the Korean Welding Society, Vol. 13, No. 4, pp. 75-84
  4. Kim, I. S., Kwon, W. H. and Park, C. E., 1996, 'The Effects of Welding Process Parameters on Weld Bead Width in GMAW Processes,' Journal of the Korean Welding Society, Vol. 14, No. 2, pp. 33-42
  5. Kim, I. S., 1997, 'A Development of Mathematical Models for Prediction of Optimal Weld Bead Geometry for GMA Welding,' Journal of the Korean Welding Society, Vol. 15, No. 3, pp. 118-127
  6. Lim, T. G., Cho, H. S. and Boo, K. S., 1994, 'Control of Weld Pool Size in GMA Welding Process using Neural Network,' Journal of the Korean Welding Society, Vol. 12, No. 1, pp. 59-72
  7. Kenji, O., Masaki, M., Tatsuya, I., Yasuyoshi, K. and Satoshi, Y., 1995, 'Application of Multi-Layered Fuzzy Inference to Weld Pool Model and Control,' The Japanese Welding Society, The Textbook of Research Group for Welding Method, June, pp. II-48-II-52
  8. Kenji, O., Akihisa, T., Takefumi, K. and Satoshi, Y., 1995, 'Modeling and Controlling of Weld Pool Using Neuro Network,' The Textbook of Research Group for Welding Method, June, pp. II-53-II-56
  9. Lee, B. Y., 1997, 'Defects, examples and prevention of welded structures,' Welding Summer School Textbook, pp. 249-295
  10. Kim, H. S., 1994, Image Recognition-Image Processing, Computer Vision, Pattern Recognition, Neural Network, Press Seong Neung, pp. 229-259
  11. Jain, R., Kasturi, R. and Schunck, B. G., 1995, Machine Vision, McGraw-Hill, pp. 186-233
  12. Lee, D. H., Park, S. H. and Park, S. K., The Handbook of Special Welding, Press Iljin, pp. 155-170
  13. Yoo, Y. T., Kim, J. Y., Ro, K. B., Yang, D. J., Oh, Y. S., Im, K. G. and Kim, J. H., 2003, 'Estimation of Laser Welding Behavior of SM 45C Steels by Plume Monitoring,' Transactions of the Korean Society of Machine and Tool Engineers, Vol. 12, No. 6, pp. 14-21
  14. Yoon, S. U., Kim, J. Y., Song, K. S. and Cha, Y. H., 2006, 'The Development of Automatic Inspection System for Flaw Detection in Welding Pipe,' Transactions of the Korean Society of Machine