Journal of KIISE:Computing Practices and Letters (한국정보과학회논문지:컴퓨팅의 실제 및 레터)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지

Application of Symbolic Representation Method for Fault Detection and Clustering in Semiconductor Fabrication Processes

반도체공정 이상탐지 및 클러스터링을 위한 심볼릭 표현법의 적용

  • 노웅기 (성결대학교 멀티미디어학부) ;
  • 홍상진 (명지대학교 전자공학과)
  • Published : 2009.11.15
Download PDF
⟨ Previous Next ⟩

Abstract

Since the invention of the integrated circuit (IC) in 1950s, semiconductor technology has undergone dramatic development up to these days. A complete semiconductor is manufactured through a diversity of processes. For better semiconductor productivity, fault detection and classification (FDC) has been rigorously studied for finding faults even before the processes are completed. For FDC, various kinds of sensors are attached in many semiconductor manufacturing devices, and sensor values are collected in a periodic manner. The collection of sensor values consists of sequences of real numbers, and hence is regarded as a kind of time-series data. In this paper, we propose an algorithm for detecting and clustering faults in semiconductor processes. The proposed algorithm is a modification of the existing anomaly detection algorithm dealing with symbolically-represented time-series. The contributions of this paper are: (1) showing that a modification of the existing anomaly detection algorithm dealing with general time-series could be used for semiconductor process data and (2) presenting experimental results for improving correctness of fault detection and clustering. As a result of our experiment, the proposed algorithm caused neither false positive nor false negative.

반도체(semiconductor) 기술은 1950년대에 집적 회로(integrated circuit, IC)가 발명된 이후 오늘날까지 급속한 발전을 거듭하고 있다. 하나의 완전한 반도체를 제조하기 위해서는 매우 다양하고 긴 공정을 거쳐야 한다. 반도체 제조 생산성을 높이기 위하여 공정들이 종료되기 전에 미리 이상(fault)을 발견하기 위한 이상탐지 및 분류(fault detection and classification, FDC)에 대한 많은 연구가 진행되고 있다. 이를 위하여 다양한 반도체 장비에 갖가지 종류의 센서를 부착하여 일정한 시간 간격으로 원하는 값을 측정한다. 이러한 측정 값은 실수 값들의 연속이므로 시계열(time-series) 데이터의 일종이다. 본 논문에서는 반도체 공정에서의 이상탐지 및 클러스터링을 수행하는 알고리즘을 제안한다. 제안된 알고리즘은 시계열 데이터를 심볼릭 표현법(symbolic representation)으로 변환하여 이상을 탐지하는 기존의 알고리즘을 수정한 것이다. 본 논문의 공헌은 일반적인 시계열 데이터에 대한 기존의 이상탐지 알고리즘을 수정하여 반도체 공정 데이터에 대해서도 활용할 수 있음을 보일 뿐만 아니라, 이상탐지 및 클러스터링의 정확성을 높이는 실험 결과를 제시하는 것이다. 실험 결과, 본 논문에서 제안한 알고리즘은 긍정 오류(false positive) 및 부정 오류(false negative)를 모두 발생하지 않았다.

Keywords

References

  1. S. J. Hong, G. S. May, J. Yamartino, and A. Skumanich, “Automated Fault Detection and Classification of Etch Systems Using Modular Neural Networks,” In Proc. of the SPIE, vol.5378, pp.134-141, Feb. 2004 https://doi.org/10.1117/12.536870
  2. D. C. Montgomery, Introduction to Statistical Quality Control, 6th Edition, Wiley, May 2008
  3. G. G. Barna, "APC in the semiconductor industry, history and near term prognosis," In Proc. of the Advanced Semiconductor Manufacturing Confer-ence and Workshop (ASMC), IEEE/SEMI, pp.364-369, Nov. 1996 https://doi.org/10.1109/ASMC.1996.558084
  4. E. Keogh, J. Lin, and A. Fu, “HOT SAX: Effi-ciently Finding the Most Unusual Time Series Subsequence,” In Proc. of the IEEE Int'l Conf. on Data Mining (ICDM), Houston, Texas, pp. 226-233, Nov. 2005 https://doi.org/10.1109/ICDM.2005.79
  5. H. Ding, G. Trajcevski, P. Scheuermann, X. Wang, and E. Keogh, "Querying and Mining of Time Series Data: Experimental Comparison of Representations and Distance Measures," In Proc. of the VLDB Endowment (PVLDB), vol.1, no.1, pp.1542-1552, Aug. 2008 https://doi.org/10.1145/1454159.1454226
  6. J. Lin, E. Keogh, S. Lonardi, and B. Chiu, "A Symbolic Representation of Time Series, with Implications for Streaming Algorithms," In Proc. of the ACM SIGMOD Workshop on Research Issues in Data Mining and Knowledge Discovery (DMKD), San Diego, California, pp.2-11, June 2003 https://doi.org/10.1145/882082.882086
  7. SEMI, Silicon Run I, 2nd Edition, Training Video, Silicon Run Productions, 1996
  8. H. J. Hwang, Semiconductor Process Technology, Saeng-Reung Publishers, July 2000 (in Korean)
  9. B. A. Rashap et al., “Control of Semiconductor Manufacturing Equipment: Real-Time Feedback Control of a Reactive Ion Etcher,” IEEE Trans. on Semiconductor Manufacturing, vol.8, no.3, pp.286-297, Aug. 1995 https://doi.org/10.1109/66.401003
  10. S.-Y. Lin and S.-C. Hong, "A Classification-Based Fault Detection and Isolation Scheme for the Ion Implanter," IEEE Trans. on Semiconductor Manufacturing, vol.19, no.4, pp.411-424, Nov. 2006 https://doi.org/10.1109/TSM.2006.883594
  11. J. Han and M. Kamber, Data Mining: Concepts and Techiques, Morgan Kaufmann, Second Edition, Nov. 2005
  12. O. A. S. Youssef, “An optimised fault classifica-tion technique based on Support-Vector-Machines,” In Proc. Power Systems Conference and Exposi-tion (PES), pp.1-8, Mar. 2009
  13. V. Anandarajah et al., “Precise Time Synchroni-zation in Semiconductor Manufacturing,” In Proc. of IEEE Int'l Symposium on Precision Clock Synchronization for Measurement, Control and Communication (ISPCS), Vienna, Austria, pp.78-84, Oct. 2007 https://doi.org/10.1109/ISPCS.2007.4383777
  14. J. R. Moyne, H. Hajj, K. Beatty, and R. Lewandowski, "SEMI E133-The Process Control System Standard: Deriving a Software Intero-perability Standard for Advanced Process Control in Semiconductor Manufacturing," IEEE Trans. on Semiconductor Manufacturing, vol.20, no.4, pp.408-420, Nov. 2007 https://doi.org/10.1109/TSM.2007.907617
  15. K. Chan and A. W. Fu, “Efficient Time Series Matching by Wavetets,” In Proc. of the IEEE Int'l Conf. on Data Engineering (ICDE), Sydney, Australia, pp,126-133, Mar. 1999 https://doi.org/10.1109/ICDE.1999.754915
  16. C. Faloutsos, M. Ranganathan, and Y. Manolo-poulos, "Fast Subsequence Matching in Time-Series Databases," In Proc. of the ACM SIGMOD Int'l Conf. on Management of Data, Minneapolis, Minnesota, pp.419-429, May 1991 https://doi.org/10.1145/191843.191925
  17. P. Geurts, “Pattern Extraction for Time Series Classification,” In Proc. of the European Conf. on Principles of Data Mining and Knowedge Discovery, Freiburg, Germany, pp.115-127, Sep. 2001 https://doi.org/10.1007/3-540-44794-6_10
  18. E. Keogh, K. Chakrabarti, M. Pazzani, and S. Mehrotxa, "Locally Adaptive Dimensionaiity Reduc-tion for Indexing Large Time Series Databases," In Proc. of ACM SIGMOD Conf. on Management of Data, Santa Barbara, California, pp.151-162, May 2001
  19. J. Lin, E. Keogh, L. Wei, and S. Lonardi, “Experiencing SAX: a Novel Symbolic Represen-tation of Time Series,” Data Mining and Know-ledge Discovery (DMKD), vol.15, no.1, pp.107-144, Aug. 2007 https://doi.org/10.1007/s10618-007-0064-z
  20. L. Wei, N. Kumar, V. N. Lolla, E. Keogh, S. Lonardi, and C. A. Ratanamahatana, "Assump-tion-Free Anomaly Detection in Time Series," In Proc. of the Int'l Scientific and Statistical Data-base Management of Conf. (SSDBM), Santa Barbara, California, pp.237-240, June 2005
  21. B. Chiu, E. Keogh, and S. Lonardi, "Probabilistic Discovery of Time Series Motifs," In Proc. of the ACM SIGKDD Int'l Conf. on Knowledge Disco-very and Data Mining, Washington DC, USA, pp.493-498, Aug. 2003 https://doi.org/10.1145/956750.956808
  22. P. Patel, E. Keogh, J. Lin, and S. Lonardi, “Mining Motifs in Massive Time Series Data-bases,” In Proc. of the IEEE Int'l Conf. on Data Mining (ICDM), Maebashi City, Japan, pp. 370- 377, Dec. 2002 https://doi.org/10.1109/ICDM.2002.1183925
  23. E. Keogh, S. Lonardi, and C. Ratanamnahatana, “Towards Parameter-Free Data Mining,” In Proc. of the ACM SIGKDD Int'l Conf. on Knowledge Discovery and Datn Mining, Seattle, Washington, pp.206-215, Aug. 2004 https://doi.org/10.1145/1014052.1014077
  24. J. Shieh and E. Keogh, "iSAX: Indexing and Mining Terabyte Sized Time Series," In Proc. oj the ACM SIGKDD Int'l Conf. on Knowledge Discovery and Data Mining, Las Vegas, Nevada, pp.623-632, Aug. 2008 https://doi.org/10.1145/1401890.1401966
  25. W. L. Martinez and A. R. Martinez, Exploratory Data Analysis with MATLAB, Chapman & Hall, Nov. 2004