Data Mining for High Quality and Quick Response Manufacturing

  • Jang-Hee Lee
  • Sang-Chan Park
Part of the Massive Computing book series (MACO, volume 3)


As the manufacturing industry becomes more and more competitive, both intelligent process control and fast manufacturing cycle time are more crucial than ever. Recently, semiconductor manufacturing has become increasingly complex due to device size reduction and consequently, those objectives become necessities in the survival and can be achieved through optimal sampling strategy utilizing inspection resources effectively without incurring a loss in quality or output. We propose a new and better application of data mining in developing an optimal measurement sampling method for process parameter monitoring in a wafer fab and illustrate the effectiveness of proposed sampling method using actual fab data. The results indicate that if the sampling chip locations and their size are chosen rationally by data mining, that sampling can provide a good sensitivity of 100% wafer coverage and defect detection for high quality and quick response manufacturing in spite of smaller sampling size.


Similarity Criterion Semiconductor Manufacturing Winning Neuron High Similarity Score Chip Location 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Albin S. L., and Friedman D. J., “The Impact of Clustered Defect Distribution in IC Fabrication, Management Science,” 35, 1066–1078, 1989CrossRefGoogle Scholar
  2. Caudill M., “Neural networks primer, part I,” AI Expert, December, pp. 46–52, 1987Google Scholar
  3. Cunningham J. A., “The Use and Evaluation of Yield Models in Integrated Circuit Manufacturing,” IEEE Trans. Semiconduct. Manufact., 3, 60–71, 1990CrossRefGoogle Scholar
  4. Duncan A. J., “The economic design of X-bar charts used to maintain current control of a Process, ” J. Amer. Statistical Assoc., 51, 228–242, 1956MATHGoogle Scholar
  5. Fayyad U., and Piatetssky -Shapiro G., et al.,Advances in Knowledge Discovery and Data Mining, AAA Press/ MIT Press, California, 1996Google Scholar
  6. Friedman D. J., and Hansen H., et al.,A Method for Characterizing Defects in Integrated Circuits, U.S. Patent 5,240,866, 1993Google Scholar
  7. Kaski S., Data Exploration Using Self- Organizing Maps, PhD thesis, Helsinki University of Technology, 1997MATHGoogle Scholar
  8. Lorenzen T. J. and Vance L. C., “The Economic Design of Control Charts: A Unified Approach,” Technometrics, 28, 3–10, 1986MathSciNetCrossRefMATHGoogle Scholar
  9. Mallory C. L., and Perloff D. S., et al.,“Spatial Yield Analysis in Integrated Circuit Manufacture”, Solid State Technology, 26, 121–127, 1983Google Scholar
  10. Montgomery D. C., Introduction to Statistical Quality Control: New York: Wiley, 1991MATHGoogle Scholar
  11. Kohonen T., “Self-organized formation of topologically correct feature maps,” Biological Cybernetics, vol. 43, pp. 59–69, 1982MathSciNetCrossRefMATHGoogle Scholar
  12. Kohonen T., and Oja E., et al.,“Engineering applications of the self-organizing map,” Proceedings of the IEEE, 1984Google Scholar
  13. Raman K., Ram Akella, and Andrzej J. Stroj was, “In-Line Defect Sampling Methodology in Yield Management: An Integrated Framework,” IEEE Trans. Semiconduct. Manufact., 9, 506517, 1996Google Scholar
  14. Shewart W. A., Economic Control of Quality of Manufactured Product. New York: Van Nostrand, 1931Google Scholar
  15. Stalk G. and Hout T. M., Competing Against Time. New York: Free Press, 1990.Google Scholar
  16. Telfeyan R., and Moyne J., et al., “A Multilevel Approach To The Control Of A Chemical-Mechanical Planarization Process”, J. Vac. Sci. Tech. A, Vol. 14, No 3, 1907–1913, 1996Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2001

Authors and Affiliations

  • Jang-Hee Lee
    • 1
  • Sang-Chan Park
    • 1
  1. 1.Department of Industrial EngineeringKorea Advanced Institute of Science and Technology (KAIST)TaejonRepublic of Korea

Personalised recommendations