The 62% Problems of SN Ratio and New Conference Matrix for Optimization: To Reduce Experiment Numbers and to Increase Reliability for Optimization

Conference paper
Part of the ICSA Book Series in Statistics book series (ICSABSS)

Abstract

Robust design has been widely adopted during product design to reduce variation and improve quality. However, based on our survey of 171 published case studies using the L\(_{18}\) orthogonal array in Japan, 62% of the signal-to-noise ratios (SN) of the optimal design cases concluded from the main effects plots were worse than the best combinations of the existing 18 runs of the L\(_{18}\) orthogonal array. This means that current robust design based on SN ratios and the L\(_{18}\) cannot predict the optimal conditions accurately and needs further work to improve the analytical prediction accuracy and optimization efficiency. We will show the six causes of 62% problems. Now, we have understood to face the serious problems like global warming, food amounts for increasing population. We need faster and more precise methodology for researching them, and it will be able to reduce experiment numbers and to increase reliability using conference matrix.

References

  1. Japan Quality Engineering association, Proceeding (2003–2012).Google Scholar
  2. Jeff Wu, C. F., & Hamada, M. S. (2009). Experiments: Planning, analysis, and optimization., Wiley series in probability and statistics New York: Wiley.Google Scholar
  3. Mori, T. (1992). Methods for new product and new technology development, trend book.Google Scholar
  4. Mori, T. (2009). Taguchi methods- pocket guide book, trend book.Google Scholar
  5. Mori, T. (2011). Taguchi methods: ASME.Google Scholar
  6. Mori, T. (2012). QES2012, the 20th Annual Proceeding, Paper No. 63 (Quality Engineering Symposium).Google Scholar
  7. Mori, T. (2013). QES2013, the 21th Annual Proceeding, Paper No. 23 (Quality Engineering Symposium).Google Scholar
  8. Mori, T. (2014). Technical report, Toyota Bousyoku, vol. 08, pp. 8–19.Google Scholar
  9. Mori, T. (2015). Mathematic and application of near orthogonal array, Mori Office, Chap. 23.Google Scholar
  10. Taguchi, G. (1984). Parameter design for new product development. Japan: Japan Standards Association.Google Scholar
  11. Tanabe, S. (2016). QES2016 The 24 Proceeding (Quality Engineering Symposium) No. 87.Google Scholar
  12. Tanaka, K. (2016). Quality (JSQC) 46(1), 51–54.Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.The Mori Consulting OfficeFujiedaJapan

Personalised recommendations