DOI QR코드

DOI QR Code

A Development of the Inference Algorithm for Bead Geometry in the GMA Welding Using Neuro-fuzzy Algorithm

Neuro-Fuzzy 기법을 이용한 GMA 용접의 비드 형상에 대한 기하학적 추론 알고리듬 개발

  • 김면희 (경북대학교 대학원 기계공학과) ;
  • 배준영 (경북대학교 대학원 기계공학과) ;
  • 이상룡 (경북대학교 기계공학부)
  • Published : 2003.02.01

Abstract

One of the significant subject in the automatic arc welding is to establish control system of the welding parameters for controlling bead geometry as a criterion to evaluate the quality of arc welding. This paper proposes an inference algorithm for bead geometry in CMA Welding using Neuro-Fuzzy algorithm. The characteristic welding parameters are measured by the circuit composed of hall sensor, voltage divider tachometer, etc. and then the bead geometry of each weld pool is calculated and detected by an image processing with CCD camera and a measuring with microscope. The relationships between the characteristic welding parameters and the bead geometry have been arranged empirically. From the result of experiments, membership functions and fuzzy rules are tuned and determined by the learning of neural network, and then the relationship between actual bead geometry and inferred bead geometry are concluded by fuzzy logic controller. In the applied inference system of bead geometry using Neuro-Fuzzy algorithm, the inference error percent is within -5%∼+4% in case of bead width, -10%∼+10% in bead height, -5%∼+6% in bead area, -10%∼+10% in penetration. Use of the Neuro-Fuzzy algorithm allows the CMA Welding system to evaluate the quality in bead geometry in real time as the welding parameters change.

Keywords

GMAW;Inference Algorithm;Fuzzy-Logic;Neural Network

References

  1. Shing J. and Jang R., 1993, 'Adaptive-Network-Based Fuzzy Inference System', IEEE Transactions on Sys., Man., and Cyber., Vol. 23, No. 3, May/June https://doi.org/10.1109/21.256541
  2. Kim, I.S., Park, C.E., Jeong, Y.J., Kim, I.J., Son, J.S. and Lee, J.P., 1998, 'A Study on Development of System for Prediction of the Optimal Bead Width on Robotic GMA Welding,' Journal of the Korean Society of Machine Tool Engineers, Vol. 7, No. 6, pp. 57-63
  3. Kim, I.J., Park, C.E., Kim, I.S., Son, J.S., An, Y.H., Kim, D.K. and Oh, Y.S., 1999, 'Development of Algorithm for Prediction of Bead Height on GMA Welding,' Journal of KWS, Vol. 17, No. 5, pp. 304-310
  4. Tsoukalas, L.H., 1997, 'Fuzzy and Neural Approaches in Engineering,' John Willy & Sons, Inc
  5. Takagi T., and Sugeno M., 1985, 'Fuzzy Identification of Systems and Its Applications to Modeling and Control,' IEEE Trans. on SMC, 15-1, pp. 116-132
  6. Kim, J.S., Lee, J.I. and Lee, S.R., 1998, 'Quality Assurance Algorithm Using Fuzzy Reasoning for Resistance Spot Weldings.,' Transactions of the KSME A, Vol. 22, No. 3, pp. 644-653
  7. Kang, M.J., Rhee, S.H. and Woo, J.J., 2000, 'Development of Estimation Model for Arc Stability Considering Arc Extinction with Multiple Regression Analysis in $CO_2$ Arc Welding,' Transaction of the KSME A, Vol. 24, No. 8, pp. 1885-1898
  8. Kim, I.S., Kwon, W.H. and Park, C.E., 1996, 'The Effect of Welding Process Parameters on Weld Bead Width in GMAW Processes,' Journal of the Korean Welding Society, Vol. 14, No. 4, pp. 33-42
  9. Na, S.J., Shin, J.S. and Kim, J.W., 1992, 'A study on seam Tracking and Arc Data Monitoring for sheet Metal Weldign,' Int. Conf. on Computerization of Welding information IV. November 3-6, Orando, Florida, pp. 240-250
  10. Lim, T.G., Cho, H.S. and Boo, K.S., 'Control of Weld Pool Size in GMA Welding Process Using Neural Network,' Journal of the Korean Welding Society, Vol. 12, No. 2, pp. 59-72
  11. Kim, I.S. and Chon, K.S, 1999, 'A Study on Prediction of Optimized Penetration Using the Neural Network and Empirical models,' Journal of the Korean Society of Machine Tool Engineers, Vol. 8, No. 5, pp. 70-75