Solder Joint Inspection Using a Neural Network and Fuzzy Rule-Based Classification Method

신경회로망과 퍼지 규칙을 이용한 인쇄회로 기판상의 납땜 형상검사

  • 고국원 (한국과학기술원 기계공학과) ;
  • 조형석 (한국과학기술원 기계공학과) ;
  • 김종형 (삼성전자 생산기술센터) ;
  • 김성권 (삼성전자 생산기술센터)
  • Published : 2000.08.01

Abstract

In this paper we described an approach to automation of visual inspection of solder joint defects of SMC(Surface Mounted Components) on PCBs(Printed Circuit Board) by using neural network and fuzzy rule-based classification method. Inherently the surface of the solder joints is curved tiny and specular reflective it induces difficulty of taking good image of the solder joints. And the shape of the solder joints tends to greatly vary with the soldering condition and the shapes are not identical to each other even though the solder joints belong to a set of the same soldering quality. This problem makes it difficult to classify the solder joints according to their qualities. Neural network and fuzzy rule-based classification method is proposed to effi-ciently make human-like classification criteria of the solder joint shapes. The performance of the proposed approach is tested on numerous samples of commercial computer PCB boards and compared with the results of the human inspector performance and the conventional Kohonen network.

Keywords

References

  1. P. J. Bartlett, C. L. Besl, R. Cole, D. Jain, Mukherjee, and K. D. Skifstad, 'Automated solder joint inspection,' IEEE trans. PAMI, vol. 10, no. 1, pp. 31-43, 1988 https://doi.org/10.1109/34.3865
  2. Capson and S. L. Eng, 'A tiered color illumination approach for machine inspection of solder joint,' IEEE Trans. PAMI, vol. 10, no. 3, pp. 387-393, 1988 https://doi.org/10.1109/34.3902
  3. S. Takagi and W. B. Hata, 'Visual inspection machine for solder joints using tiered illumination,' Proc. SPIE, vol. 1386, pp. 21-29, 1990 https://doi.org/10.1117/12.25375
  4. J-S Park and J. T. Tou, 'A solder joint inspection system for automated printed circuit board manufacturing,' Pro. IEEC Conf. Robotics and Automation, vol. 2, pp. 1290-1295, 1999 https://doi.org/10.1109/ROBOT.1990.126177
  5. J. H. Kim and H. S. Cho, 'Neural network-based inspection of solder joints using a circular illumination,' Image and Vision Computing, 1995 https://doi.org/10.1016/0262-8856(95)94381-9
  6. H. J. Zimmermann, 'Fuzzy set theory and its appl-ications,' Kluwer-Nijhoff Publishing, pp. 205-212
  7. 이광형, 오길록, '퍼지 이론 및 응용,' 홍릉과학출판사, vol. 2, chap 7
  8. A. C. Nayer, L. E. Sanderson, Weiss, and Simon D. D., 'Specular surface inspection using structured highlight and Gaussian Images,' IEEE Trans. Robotics Automation, vol. 6, no. 2, pp. 108-218, 1999 https://doi.org/10.1109/70.54736
  9. J. H. Kim and H. S. Cho, 'Neural network-based inspection of solder joints using a circular illumination,' Image and Vision computing, vol. 13, pp. 479-490, 1995 https://doi.org/10.1016/0262-8856(95)94381-9
  10. J. C. Bezdeck, 'Pattern recognition with fuzzy objective function algorithm,' Plenum Press, 1991
  11. J. S. Park and J. T. Tou, 'A solder joint inspection system for automated printed circuit board manufacturing,' Proc. of Int. Conf. on Robotics and automation, pp. 1290-1295, 1990 https://doi.org/10.1109/ROBOT.1990.126177
  12. H. S. Cho, J. S. Kim, J. H. Kim, 'Development of visual inspection machine for solder joint,' KAIST LCA Tech. Report, 1993
  13. H. S. Cho, K. W. Ko, I. S. Joung, 'Development of advanced solder joint inspection system for SMC,' KAIST LCA Tech. Report, 1996
  14. K. W. Ko, J. H. Kim, and H. S. Cho, 'Solder joints inspection using a circular illumination & fuzzy pattern matching,' ICARCV'96, pp. 1044-1048, 1996
  15. J. H. Kim and H. S. Cho, 'Pattern Classification of solder joint images using vector correlation neural network,' J. Engineering Application of Artificial Intelligent, vol. 9, no. 6, pp. 655-669, 1996 https://doi.org/10.1016/S0952-1976(96)00046-2
  16. Y. K. Ryu and H. S. Cho, 'New optical measuring system for solder joint insepecton,' Optics and Lasers in Engineering, vol. 26, no. 6, pp. 487-514, 1997 https://doi.org/10.1016/0143-8166(95)00118-2
  17. K. W. Ko, H. S. Cho, J. H. Kim, J. S. Kim, S. K. Kim, 'Solder joints inspection using neural Network and fuzzy rule-based classification,' IROS 98, 1998 https://doi.org/10.1109/IROS.1998.724821
  18. Jacek M. Zurada, 'Introduction to artificial neural systems,' West publishing company, 1992
  19. Yoh-Han Pao, 'Adaptive pattern recognition and neural networks,' Addision-Wesley Publishing Company, 1989
  20. Kuk Won Ko and Hyung Suck Cho, 'Solder joints inspection using a neural network and Fuzzy Rule-Based Classification Method,' IEEE CPMT(to appear) https://doi.org/10.1109/6104.846932