随机加权法辅助小样本岩土参数分布拟合  

PROBABILITY DISTRIBUTION OF SMALL SAMPLES OF GEOTECHNICAL PARAMETERS USING STOCHASTIC WEIGHTED METHOD

作　　者：周金龙[1,2] 赵春风[1,2] 钱涛[1,2] 

机构地区：[1]同济大学岩土及地下工程教育部重点实验室,上海200092 [2]同济大学地下建筑与工程系,上海200092

出　　处：《低温建筑技术》2009年第10期59-61,共3页Low Temperature Architecture Technology

摘　　要：提出小样本条件下基于随机加权法的多项式拟合方法,对岩土参数总体分布密度函数进行推断。应用随机加权法重采样技术对小样本数据信息进行提取,估计总体各阶原点矩。采用勒让德正交多项式拟合推断分布密度函数并采用精度较高的K-S检验法进行检验,确认本方法具有较高的精度。本方法直接根据样本数据进行推断,大大降低了对已有数据及经典分布概型的依赖性,具有明确的数学物理意义,能够满足岩土工程可靠性分析的需要。Polynomial approximation based on stochastic weighted method is proposed to generate probability density functions of geotechnical parameters with small samples. Stochastic weighted method is used to resample from the present samples so as to get the origin moment of the total. Legendre polynomial approximation is presented to determine the probability distribution and Kolmogorov-Smimov test is used to verify the availability of this method. Direct assessment from the samples greatly reduces the reliance on the existing testing data and probability distribution. It shows that the presented method is accurate and can be used in stochastic reliability analysis of geotechnical parameters.

关 键 词：岩土参数 小样本 随机加权 概率分布 

分 类 号：TU431[建筑科学—岩土工程]