Advertisement

Journal of Mechanical Science and Technology

, Volume 31, Issue 6, pp 2901–2910 | Cite as

A new method to determine the number of experimental data using statistical modeling methods

  • Jung-Ho Jung
  • Young-Jin Kang
  • O.-Kaung Lim
  • Yoojeong NohEmail author
Article

Abstract

For analyzing the statistical performance of physical systems, statistical characteristics of physical parameters such as material properties need to be estimated by collecting experimental data. For accurate statistical modeling, many such experiments may be required, but data are usually quite limited owing to the cost and time constraints of experiments. In this study, a new method for determining a reasonable number of experimental data is proposed using an area metric, after obtaining statistical models using the information on the underlying distribution, the Sequential statistical modeling (SSM) approach, and the Kernel density estimation (KDE) approach. The area metric is used as a convergence criterion to determine the necessary and sufficient number of experimental data to be acquired. The proposed method is validated in simulations, using different statistical modeling methods, different true models, and different convergence criteria. An example data set with 29 data describing the fatigue strength coefficient of SAE 950X is used for demonstrating the performance of the obtained statistical models that use a pre-determined number of experimental data in predicting the probability of failure for a target fatigue life.

Keywords

Number of experimental data Statistical modeling Sequential statistical modeling Kernel density estimation Area metric 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    P. Hess, D. Bruchman, I. Asskkaf and B. M. Ayyub, Uncertainties in material strength, geometric, and load variables, Naval Engineers Journal, 114 (2) (2002) 139–166.CrossRefGoogle Scholar
  2. [2]
    Y. J. Kang, O. K. Lim and Y. Noh, Sequential statistical modeling method for distribution type identification, Structural and Multidisciplinary Optimization, 54 (6) (2016) 1587–1607.CrossRefGoogle Scholar
  3. [3]
    Y. Noh, K. K. Choi and I. Lee, Identification of marginal and joint CDFs using Bayesian method for RBDO, Structural and Multidisciplinary Optimization, 40 (1) (2010) 35–51.MathSciNetCrossRefzbMATHGoogle Scholar
  4. [4]
    A. K. Verma, S. Ajit and D. R. Karaki, Reliability and safety engineering, Springer, London (2010).CrossRefGoogle Scholar
  5. [5]
    W. Zhang and C. Cho, A method for epistemic uncertainty quantification and application to uniaxial tension modeling of polymers, Journal of Mechanical Science and Technology, 29 (3) (2015) 1199–1206.CrossRefGoogle Scholar
  6. [6]
    Y. Noh, K. K. Choi, I. Lee, D. Gorsich and D. Lamb, Reliability-based design optimization with confidence level under model uncertainty due to limited test data, Structural and Multidisciplinary Optimization, 43 (4) (2011) 443–458.MathSciNetCrossRefzbMATHGoogle Scholar
  7. [7]
    C. Y. Park, N. H. Kim and R. T. Haftka, How coupon and element tests reduce conservativeness in element failure prediction, Reliability Engineering and System Safety, 123 (2014) 123–136.CrossRefGoogle Scholar
  8. [8]
    L. H. Miller, Table of percentage points of Kolmogorov statistics, Journal of the American Statistical Association, 51 (273) (1956) 111–121.MathSciNetCrossRefzbMATHGoogle Scholar
  9. [9]
    B. M. Ayyub and R. H. McCuen, Probability, statistics, and reliability for engineers and scientists, CRC Press, Florida, USA (2012).zbMATHGoogle Scholar
  10. [10]
    D. F. Findley, Counterexamples to parsimony and BIC, Annals of the Institute of Statistical Mathematics, 43 (3) (1991) 505–514.MathSciNetCrossRefzbMATHGoogle Scholar
  11. [11]
    M. P. Wand and M. C. Jones, Kernel smoothing, Chapman and Hall, CRC press, London (1994).Google Scholar
  12. [12]
    B. W. Silverman, Density estimation for statistics and data analysis, CRC press, London, 26 (1986).CrossRefzbMATHGoogle Scholar
  13. [13]
    S. G. Krantz, Real analysis and foundations, Chapman and Hall, CRC Press, London (1991).zbMATHGoogle Scholar
  14. [14]
    J. Choi, S. Hong, S. Chi, H. Lee, C. Park, H. Kim, T. Yeu and T. H. Le, Probability distribution for the shear strength of seafloor sediment in the KR5 area for the development of manganese nodule miner, Ocean Engineering, 39 (2011) 2033–2041.CrossRefGoogle Scholar
  15. [15]
    S. Kim, S. Jun, H. Kang, Y. Park and D. Lee, Reliability based optimal design of a helicopter considering annual variation of atmospheric temperature, Journal of Mechanical Science and Technology, 25 (2011) 1095–1104.CrossRefGoogle Scholar
  16. [16]
    D. D. Socie, Probabilistic statistical simulations technical background. eFatigue LLC, https://www.efatigue.com/probabilistic/background/statsim.html#Cor (2014).Google Scholar
  17. [17]
    R. G. Budynas and J. K. Nisbett, Shingley’s mechanical engineering design, 9th edition, McGraw-Hill, New York, USA (2010).Google Scholar
  18. [18]
    Retried from MatWeb, www.matweb.com, Feb. 2 (2016).Google Scholar

Copyright information

© The Korean Society of Mechanical Engineers and Springer-Verlag GmbH Germany 2017

Authors and Affiliations

  • Jung-Ho Jung
    • 1
  • Young-Jin Kang
    • 1
  • O.-Kaung Lim
    • 1
  • Yoojeong Noh
    • 1
    Email author
  1. 1.School of Mechanical EngineeringPusan National UniversityBusanKorea

Personalised recommendations