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.
Number of experimental data Statistical modeling Sequential statistical modeling Kernel density estimation Area metric
This is a preview of subscription content, log in to check access.
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
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
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
A. K. Verma, S. Ajit and D. R. Karaki, Reliability and safety engineering, Springer, London (2010).CrossRefGoogle Scholar
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
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
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
S. G. Krantz, Real analysis and foundations, Chapman and Hall, CRC Press, London (1991).zbMATHGoogle Scholar
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
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
D. D. Socie, Probabilistic statistical simulations technical background. eFatigue LLC, https://www.efatigue.com/probabilistic/background/statsim.html#Cor (2014).Google Scholar
R. G. Budynas and J. K. Nisbett, Shingley’s mechanical engineering design, 9th edition, McGraw-Hill, New York, USA (2010).Google Scholar