응용통계연구 (The Korean Journal of Applied Statistics)

  • 제29권2호
  • /
  • Pages.369-379
  • /
  • 2016
  • /
  • 1225-066X(pISSN)
  • /
  • 2383-5818(eISSN)
한국통계학회 (The Korean Statistical Society)
권호 표지
DOI QR코드

DOI QR Code

R&D 분야의 목표 시그마 수준 설정과 설계 공차의 강건 한계 결정에 대한 연구

A study on target Sigma Level at R&D stage and robust limits for design margins

  • 고승곤 (가천대학교 응용통계학과)
  • Ko, Seoung-gon (Department of Applied Statistics, Gachon University)
  • 투고 : 2016.01.18
  • 심사 : 2016.01.21
  • 발행 : 2016.02.29
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

시그마 수준(sigma level)이란 미국 모토롤라사에 의해 소개된 프로세스 능력 지수로서 1970년대 이후 널리 활용되고 있는 다양한 지수들 중의 하나이다. 이는 다른 지수들과 비교할 때 모 프로세스의 확률 분포에 기초한다는 장점을 갖지만 양산 단계를 가정한 것으로 R&D 분야의 시제품 그리고/또는 초도 양산품 단계에 직접 적용하는 것은 적절하지 못할 수 있다. 이에 본 논문은 시그마 수준을 계산할 때 가정하는 치우침에 대한 통계적 고찰을 통하여 양산단계에서 6 시그마 품질 수준을 달성하기 위한 개발 단계의 시제품 그리고/또는 초도 양산품의 목표 시그마 수준 설정 방법을 소개한다. 그리고 이를 기초로 개발과 양산 단계에서 경제성을 달성할 수 있는 설계 공차의 강건 한계 도출 방법을 제시해 보고자 한다.

The Sigma Level, proposed by Motorola Inc., is one of the many Process Capability Index (PCI)'s that have been presented since the 1970's. It is used to evaluate process capability and unlike other PCI's, it has an advantage in that it uses population probability distribution. However, it is originally designed for mass production and is inadequate to evaluate prototypes or early products in the R&D stages. For use in such cases, we propose an R&D target Sigma Level, derived by considering 1.5 sigma shifts in traditional sigma level from a statistical point of view. We also explain the way to find robust limits for design tolerance because the sigma level or defect probability is useful to establish economical tolerance limits at the R&D stage and mass production.

키워드

참고문헌

  1. Bender, A. (1962). Benderizing tolerances-a simple practical probability method of handling tolerances for limit-stack-ups, Graphic Science, 17.
  2. Bissell, A. F. (1990). How reliable is your capability index?, Applied Statistics, 39, 331-340. https://doi.org/10.2307/2347383
  3. Bothe, D. R. (2002). Statistical reason for the 1.5 sigma shift, Quality Engineering, 14, 479-487. https://doi.org/10.1081/QEN-120001884
  4. Denniston, B. (2006). Capability indices and conformance to specification: the motivation for using Cpm, Quality Engineering, 18, 79-88. https://doi.org/10.1080/08982110500406469
  5. Donaldson, P. D. (2004). 100 years of Juran, Quality Progress, 37, 25-37.
  6. El-Haik, B. (2005). Axiomatic Quality: Integrating Axiomatic Design with Six-Sigma, Reliability, and Quality Engineering, John Wiley & Sons.
  7. Evans, D. H. (1975). Statistical tolerancing: the state of the art, part III, methods for estimating moments, Journal of Quality Technology, 7, 1-12.
  8. Gilson, J. (1951). A New Approach to Engineering Tolerances, Machinery Publishing Co, London.
  9. Harry, M. J. (1994). The Vision of Six Sigma: Tools and Methods for Breakthrough, Sigma Academy, Phoenix, AZ.
  10. Harry, M. J. and Lawson, J. R. (1992). Six Sigma Producibility Analysis and Process Characterization, Addison-Wesley, MA, 2-3.
  11. Kane, V. E. (1986). Process capability indices, Journal of Quality Technology, 18, 41-52. https://doi.org/10.1080/00224065.1986.11978984
  12. Kotz, S. and Johnson, N. L. (1993). Process Capability Indices, CRC Press.
  13. Mathew, T., Sebastian, G., and Kurian, K. M. (2007). Generalized confidence intervals for process capability indices, Quality and Reliability Engineering International, 23, 471-481. https://doi.org/10.1002/qre.828
  14. Munro, R. A. (2000). Linking six sigma with QS-9000, Quality Progress, 33, 47.
  15. Shewhart, W. A. (1931). Economic Control of Quality of Manufactured Product, ASQ Quality Press.
  16. Sleeper, A. (2005). Design for Six Sigma Statistics: 59 Tools for Diagnosing and Solving Problems in DFFS Initiatives: 59 Tools for Diagnosing and Solving Problems in DFFS Initiatives, McGraw Hill Professional.