Influence of statistical sample size on evaluation of overall strength of cement-treated soil column

Abstract

The quality of cement-treated soil columns is normally assured based on the unconfined compressive strength qu of core samples. qu of core samples varies spatially and the statistical parameters of qu (i.e., mean µqu, variance [Formula: see text], and autocorrelation distance θqu) are adopted in quality assurance procedures. The statistical parameters of qu evaluated from the core sample strengths have a statistical uncertainty depending on the statistical sample size. The present study investigates the influence of the statistical sample size on the evaluation of overall strength of a cement-treated soil column. A probabilistic framework in which a Bayesian inference analysis and a finite element method analysis are incorporated is used to calculate the overall strength while simultaneously considering the statistical uncertainty and spatial variability of core strength. The probabilistic framework is briefly described, and a parametric analysis is performed to investigate the influence of the statistical sample size on the evaluation of the overall strength of a full-scale column. The numerical results show that the sample size and spatial correlation influence the variability of the overall strength, and the influence can be reasonably described using an equivalent number of independent data.