G., 'Porbabilistic Analysis of Time-dependent Deflections of RC Flexural Members,' Computers & Structures, Vol.79, Issue. E., 'Reliability Analysis of Creep and Shrinkage Effects,' Journal of Structural Engineering, ASCE, Vol.118, No.5, 1992, pp.1532~1548 O., and Rackwitz, R., 'On the Variability of the Creep Coefficient of Structural Concrete,' Materials and Structures, Vol.17, No.100, 1983, pp.321~328 P., 'Uncertainty Analysis of Creep and Shrinkage Effects in Concrete Structures,' ACI Journal, Vol.80, March-April, 1983, pp.116~127ĭiamantidis, D., Madsen, H. The comparison uses results from a model for. H., 'Variability of Creep and Shrinkage of Concrete,' Proceedings of symposium on fundamental on creep and shrinkage of concrete, M.Nijhoff, The Hague, 1982, pp.75~94 Uncertainty and sensitivity analysis results obtained with random and Latin hypercube sampling are compared. In respect to sensitivity analysis, the global methods were preferred over the deterministic or local methods. and Panula, L., 'Creep and Shrinkage Characterization for Analyzing Prestressed Concrete Structures,' PCI Journal, Vol.25, No.3, 1980, pp.86~122 Simple Monte Carlo sampling and the Latin Hypercube sampling were the sampling approaches selected to make uncertainty analysis. T., Probability and Statistics for Engineers, 2nd Ed., Duxbury Press, Boston, 1986īazant, Z. To facilitate the uncertainty analysis of a finite element multiphase multi-component transport model MOFAT, this paper provides guidance on latin hypercube sampling Monte Carlo (LHS-MC) sample. P., Statistical Inference Based on Ranks, John Wiley & Sons, New York, 1984 Olsson, A., Sandberg, G., and Dahlblom, O., 'On Latin Hypercube Sampling for Structural Reliability Analysis,' Structural Safety, 25, 2003, pp.47~68 Novak, D., Teply, B., and Kersner, Z., 'The Role of Latin Hypercube Sampling Method in Reliability Engineering,' Proceedings of ICOSSAR-97, Kyoto, Japan, 1997, pp.403~409 E., 'An Approach to Sensitivity Analysis of Computer Models, Part-Ranking of Input Variables, Response Surface Validation, Distribution Effect and Technique Synopsis,' Journal of Quality Technology, Vol.13, No.4, Oct., 1981, pp.232~240 E., 'An Approach to Sensitivity Analysis of Computer Models, Part I Introduction, Input Variable Selection and Preliminary Variable Assessment,' Journal of Quality Technology, Vol.13, No.3, July, 1981, pp.l74~183 J., 'Small Sample Sensitivity Analysis Techniques for Computer Models with an Application to Risk Assessment,' Communications in Statistics, A9, 1980, pp.1749~1842 Latin Hypercube Sampling) to the deterministic CDF based upon a response surface constructed with only two sampling points. Worley Engineering Physics and Mathematics Oak Ridge National Laboratory Oak Ridge, Tennessee 37831-6364. Novak, D., Teply, B., and Shiraishi, N., 'Sensitivity Analysis of Structures : a review,' Proceedings of CIVIL COMP 93, Edinburgh, Scotland, 1993, pp.201~207 DETERMINISTIC UNCERTAINTY ANALYSIS CONF-87110130 Brian A. C., Methods of Structural Safety, Prentice Hall, Englewood Cliffs, New Jersey, 1986 E., 'Probabilistic Creep Analysis of Underground Structures in Salt,' Journal of Engineering Mechanics, ASCE, Vol.122, No.3, 1996, pp.209~217 H., 'Sensitivity Analysis of Time-Dependent Behavior in PSC Box Girder Bridges,' Journal of Structural Engineering, ASCE, Vol.126, No.2, 2000, pp.171~179įossum, A. Our results indicate that PLHS leads to improved efficiency, convergence, and robustness of sampling-based analyses.Oh, B. The performance of PLHS is compared with benchmark sampling strategies across multiple case studies for Monte Carlo simulation, sensitivity and uncertainty analysis.
LATIN HYPERCUBE SAMPLING UNCERTAINTY ANALYSIS SERIES
Unlike Latin hypercube sampling, PLHS generates a series of smaller sub-sets (slices) such that (1) the first slice is Latin hypercube, (2) the progressive union of slices remains Latin hypercube and achieves maximum stratification in any one-dimensional projection, and as such (3) the entire sample set is Latin hypercube. In this study, we propose a new strategy, called Progressive Latin Hypercube Sampling (PLHS), which sequentially generates sample points while progressively preserving the distributional properties of interest (Latin hypercube properties, space-filling, etc.), as the sample size grows. Efficient sampling strategies that scale with the size of the problem, computational budget, and users’ needs are essential for various sampling-based analyses, such as sensitivity and uncertainty analysis.