Advertisement

SMT defect classification by feature extraction region optimization and machine learning

  • Ji-Deok Song
  • Young-Gyu Kim
  • Tae-Hyoung ParkEmail author
ORIGINAL ARTICLE
  • 42 Downloads

Abstract

In this paper, we propose a solder joint defect type classification method for automatic optical inspection machines in the manufacturing system of printed circuit boards. The inspection procedure for the solder joint defect type classification consists of an offline stage, which sets the optimal feature extraction region, and an online stage which classifies a defect type. In the offline stage, we use an optimization technique, namely, the genetic algorithm, to optimize the feature extraction region. In this stage, the optimal feature extraction region for defect type classification is constructed automatically. In the online stage, feature extraction regions are used to segment the solder joint image after component image acquirement. We then extract various color features from the segmented feature extraction regions. Next, we use support vector machine, which is one of the machine learning model’s method to classify the solder joint defect type. To evaluate the performance of the proposed method, ten types of solder joint defects were used in an experiment. The experimental results verified the effectiveness of the method in terms of the recognition rate, and its convenience.

Keywords

Automated optical inspection Classification Genetic algorithm Optimization Printed circuit board Solder joint Support vector machine 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Notes

Acknowledgements

This work was supported by Institute for Information & communications Technology Promotion(IITP) grant funded by the Korea government(MSIT) (No. R7117-16-0164, Development of eight wide area driving environment awareness and cooperative driving technology, which are based on V2X wireless communication)

References

  1. 1.
    Kong F (2008) A new method of inspection based on shape from shading. Int Congress on Image and Signal Process, pp. 291–294Google Scholar
  2. 2.
    Jiang J, Cheng J, Tao D (2012) Color biological features based solder paste defects detection and classification on printed circuit boards. IEEE Trans Compon Packag Manuf Technol 2(9):1536–1544CrossRefGoogle Scholar
  3. 3.
    Cai N, Lin J, Wang H, Weng S, Ling BW-K, Ye Q, New A (2016) IC solder joint inspection method for an automatic optical inspection system based on an improved visual background extraction algorithm. IEEE Trans Compon Packag Manuf Technol 6(1):161–172CrossRefGoogle Scholar
  4. 4.
    N. Cai, Q. Ye, G. Liu, H. Wang, and Z. Yang, IC solder joint inspection based on the Gaussian mixture model. International Journal of Soldering and Surface Mount Technology 28(4):207–214 (2016)Google Scholar
  5. 5.
    Cai N, Zhou Y, Ye Q, Liu G, Wang H, Chen X (2017) IC solder joint inspection via robust principle component analysis. IEEE Trans Compon Packag Manuf Technol 7(2):300–309Google Scholar
  6. 6.
    Xie HW, Zhang XM, Kuang YC, Ouyang GF (2011) Solder joint inspection method for chip component using improved AdaBoost and decision tree. IEEE Trans Compon Packag Manuf Technol 1(12):2018–2027CrossRefGoogle Scholar
  7. 7.
    Wu H, Zhang X, Xie H, Kuang Y, Ouyang G (2013) Classification of solder joint using feature selection based on Bayes and support vector machine. IEEE Trans Compon Packag Manuf Technol 3(3):516–522CrossRefGoogle Scholar
  8. 8.
    Hao W, Xianmin Z, Yongcong K, Gaofei O, Hongwei X (2013) Solder joint inspection based on neural network combined with genetic algorithm. Int J Light and Electron Optics 124(20):4110–4116CrossRefGoogle Scholar
  9. 9.
    Sim KJ, Yun TS, Kim HJ (2000) Solder joint inspection system using support vector machine and circular illumination. Proceed KIISE Spring Conference (in Korean) 27(1B):607–609Google Scholar
  10. 10.
    Xie H, Kuang Y, and Zhang X (2009) A high speed AOI algorithm for chip component based on image difference. IEEE Int Conf Inform Autom, pp. 969–974Google Scholar
  11. 11.
    Wu F, Zhang X (2011) Feature-extraction based inspection algorithm for IC solder joints. IEEE Trans Compon Packag Manuf Technol 1(5):689–694CrossRefGoogle Scholar
  12. 12.
    Wu F, Zhang X, Kuan Y, and He Z (2008) An AOI algorithm for PCB based on feature extraction inspection. Int Conf Intellig Control and Autom, pp. 240–247Google Scholar
  13. 13.
    Wu F, Zhang X (2014) Inspection and classification method for chip solder joints using color grads and Boolean rules. Int J Robotics Comp-Integr Manuf 30(5):517–526CrossRefGoogle Scholar
  14. 14.
    Song JD, Kim YG, Park TH (2017) Defect classification method of PCB solder joint by color features and region segmentation. J Instit Control Robotics and Systems (in Korean) 23(12):1086–1091CrossRefGoogle Scholar
  15. 15.
    Lee JS, Park TH (2015) Defect classification of components for SMT inspection machines. J Instit Control Robotics and Systems (in Korean) 21(10):982–987CrossRefGoogle Scholar
  16. 16.
    Youn SG, Lee YA, Park TH (2015) Automatic classification of SMD packages using neural network. J Instit Control Robotics and Systems (in Korean) 21(3):276–282CrossRefGoogle Scholar
  17. 17.
    Youn SG, Kim YG, Park TH (2017) Wavelet transform based defect detection for PCB inspection machines. Trans Korean Instit Electric Eng 66(10):849–857Google Scholar
  18. 18.
    Li X, Tso SK, Guan X, Huang Q (2006) Improving automatic detection of defects in castings by applying wavelet technique. IEEE Trans Ind Electron 53(1):849–857Google Scholar
  19. 19.
    Shenouda A (2006) A quantitative comparison of different MLP activation functions in classification. Int Symp Neural Networks, pp. 849–857Google Scholar
  20. 20.
    Vedaldi A, Zisserman A (2011) Efficient additive kernels via explicit feature maps. IEEE Trans Pattern Anal Mach Intell 34(3):480–492CrossRefGoogle Scholar
  21. 21.
    Platt JC (1999) Fast training of support vector machines using sequential minimal optimization. Advances in Kernel Methods-Support Vector. Learning, pp. 185–208Google Scholar
  22. 22.
    Fan R, Chen P, Lin C (2005) Working set selection using second order information for training support vector machines. Int J Mach Learn Res 6:1889–1918MathSciNetzbMATHGoogle Scholar
  23. 23.
    Mika S, Ratsch G, Weston J, Scholkopf B, and Mullers R (1999) Fisher discriminant analysis with kernels. Proceed 1999 IEEE Signal Process Soc Workshop, pp. 41–48Google Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Control & Robot Eng.Chungbuk National UniversityCheongjuSouth Korea

Personalised recommendations