DOI QR코드

DOI QR Code

데이터 마이닝과 지능 모델링에 기반한 에칭공정의 공정관리시스템 설계

Design of Process Management System based on Data Mining and Artificial Modelling for the Etching Process

  • Bae, Hyeon (School of Electrical and Computer Engineering, Pusan National University) ;
  • Kim, Sung-shin (School of Electrical and Computer Engineering, Pusan National University) ;
  • Woo, Kwang-Bang (Automation Technology Research Institute, Yonsei University)
  • 발행 : 2004.07.01

초록

반도체 공정은 많은 단위 공정으로 이루어진 복잡하고 동적인 공정이다. 그 중 에칭공정은 반도체 생산에서 중요한 공정중 하나이다. 본 논문에서는 데이터 마이닝과 지식 획득을 통한 의사지원시스템으로 생산성과 수율을 높일 수 있는 시스템을 구성하고자 하였다. 제안된 방법은 퍼지 논리와 신경망으로 구성되는데, 신경망으로 에칭공정의 품질을 나타내는 품질에 대한 결과를 예측하고, 예측된 결과를 퍼지 추론 시스템으로 분류하는 과정으로 수행된다. 퍼지 논리에 사용된 규칙은 전문가의 지식에 기반 하여 도출되거나 데이터로부터 도출된다. 본 시스템을 통해 공정의 최적 조건을 찾아 효율을 높이는 것이 본 연구의 주요 목표이다.

A semiconductor manufacturing process is the complicate and dynamic process, and consists of many sub-processes. An etching process is the most important process in the semiconductor fabrication. In this paper, the decision support system based upon data mining and knowledge discovery is an important factor to improve the productivity and yield. The proposed decision support system consists of a neural network model and an inference system based on fuzzy logic Firstly, the product results are predicted by the neural network model constructed by the product patterns that represent the quality of the etching process. And the product patters are classified by expert's knowledge. Finally, the product conditions are estimated by the fuzzy inference system using the rules extracted from the classified patterns. Prediction of product qualities can be linked to each input and process variables. We employ data mining and intelligent techniques to find the best condition of the etching process. The proposed decision support system is efficient and easy to be implemented for the process management based upon expert's knowledge.

키워드

참고문헌

  1. Jay Liebowitz: Knowledge Management Handbook. CRC Press, 1999.
  2. Michael J. A. Berry: Data Mining Techniques. John Wiley & Sons Inc., New York, 1997.
  3. Nadine Tschichold-Gurman: The neural network model RuleNet and its application to mobile robot navigation. Fuzzy Sets and Systems 85, 1997, p. 287-303. https://doi.org/10.1016/0165-0114(95)00351-7
  4. Ken Nozaki, Hisao Ishibuchi, Hideo Tanaka: A simple but powerful heuristic method for generating fuzzy rules from numerical data. Fuzzy Sets and Systems 86, 1997, p. 251-270. https://doi.org/10.1016/0165-0114(95)00413-0
  5. C. T. Lin: Neural Fuzzy Control Systems with Structure and Parameter Learning. World Scientific Pub Co., 1994.
  6. Sigeru Omatu, Marzuki Khalid, Rubiyah Yusof: Neuro-Control and its Applications. Springer, 1995.
  7. Yan Shi, Masaharu Mizumoto:An improvement of neuro-fuzzy learning algorithm for tuning fuzzy rules. Fuzzy Sets and Systems 118, 2001, p. 339-350. https://doi.org/10.1016/S0165-0114(98)00440-0
  8. X. Z. Wang, Y. D. Wang, X. F. Xu, W. D. Ling, D. S. Yeung: A new approach to fuzzy rule generation-fuzzy extension matrix. Fuzzy Sets and Systems 123, 2001, p. 291-306. https://doi.org/10.1016/S0165-0114(01)00002-1
  9. S. Abe, Ming-Shong Lan: A Function Approximator Using Fuzzy Rules Extracted Directly From Numerical Data. Proceedings of 1993 International Joint Conference on Neural Networks. Vol. 2, 1993, p. 1887-1892.
  10. N. R. Pal, S. Chakraborty: Fuzzy rule extraction from ID3-type decision trees for real data. IEEE Transactions on Systems, Man and Cybernetics, Part B. Vol. 31, No. 5, 2001, p. 745-754 https://doi.org/10.1109/3477.956036
  11. Lefteri H. Tsoukalas, Robert E. Uhrig: Fuzzy and Neural Approaches in Engineering. John Wiley & Sons Inc., New York, 1997.
  12. L. X. Wang: A Course in Fuzzy Systems and Control. Prentice-Hall, NZ, 1997.