DOI QR코드

DOI QR Code

혼합물 실험에서의 EVOP법

EVOP in Experiments with Mixtures

  • 임용빈 (이화여자대학교 자연과학대학 통계학과) ;
  • 조호 (이화여자대학교 자연과학대학 통계학과) ;
  • 김영일 (중앙대학교 정보시스템학과)
  • Lim, Yong-Bin (Department of Statistics, Ewha Womans University) ;
  • Cho, Ho (Department of Statistics, Ewha Womans University) ;
  • Kim, Yoing-Il (Department of Information System, ChoongAng University)
  • 투고 : 2011.09.26
  • 심사 : 2011.11.07
  • 발행 : 2011.12.31

초록

Evolutionary operation (EVOP) proposed by Box(1957) is a method for continuous monitoring and improvement of a full-scale manufacturing process with the objective of moving the current operating conditions toward the better ones. EVOP in experiments with mixtures consists of screening vital few components and making small changes in the current operating condition by making small increments in the proportion of the screened component. In this paper, how to determine operating conditions in EVOP in experiments with mixtures around the current operating condition is proposed. The proposed methods are illustrated with the simulated data based on the well known flare experimental data described by McLean and Anderson(1966).

키워드

참고문헌

  1. Box, G.E,P.(1957). "Evolutionary operations: a method for increasing industrial productivity", Applied Statistics, Vol.6, 81-101. https://doi.org/10.2307/2985505
  2. Cornell, J.(2002). Experiments with Mixtures, 3rd ed., New York: Wiley
  3. Lim, Yong B. and Park, S.H.(2007). "Number of cycles in evolutionary operation", J. of Korean Statistical Society, Vol. 36, 201-208
  4. Mclean, R.A. and Anderson, V.L.(1966). "Extreme vertices design of mixture experiments", Technometrics, Vol. 8, 447-454. https://doi.org/10.1080/00401706.1966.10490377
  5. Myers, R.H. and Montgomery, D.C.(2009). Response Surface Methodology, 3rd ed., New York: Wiley