Fusion Method for True Value Estimation of Manufacturing Quality under Condition of Poor Information (Part I: Theory)

Abstract:

Poor information means incomplete and insufficient information, such as small sample and unknown distribution. For point estimation under the condition of poor information, the statistical methods relied on large samples and known distributions may become ineffective. For this end, a fusion method is proposed. The fusion method develops five methods, three concepts, and one rule. The five methods include the rolling mean method, the membership function method, the maximum membership grade method, the moving bootstrap method, and the arithmetic mean method. The three concepts comprise the solution set on the estimated true value, the fusion series, and the final estimated true value. The rule is the range rule. The method proposed can supply a foundation for the true value estimation of manufacturing quality under the condition of poor information.

• Periodical: Applied Mechanics and Materials (Volumes 34-35)
• Pages: 157-161
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.34-35.157
• Online since: October 2010
• Authors: Xin Tao Xia, Lei Lei Gao, Jian Feng Chen
• Keywords: Data Series, Evaluation, Information Fusion, Manufacturing Quality, Point Estimation, Small Sample

References

[1] Z.L. Du, H.N. Wang and H. He: Advances in Space Research, Vol. 42 (2008), p.1457.

[2] Carlos Zuppa: Applied Numerical Mathematics, Vol. 47(2003), p.575.

[3] X. T Xia, X.Y. Chen and Y.Z. Zhang: Measurement, Vol. 41(2008), p.687.

[4] S.L. Wu: Information Processing & Management, Vol. 45(2009), p.413.

[5] X.T. Xia and Z.Y. Wang: Measurement Science & Technology, Vol. 11 (2000), p.430.