摘要
对于土性随深度线性变化的情况 ,指出通常所用的回归方法没有考虑土性随机分量之间的自相关性 ,并讨论了考虑这种自相关性的概率统计模型 .建立了一种准确预估给定深度处土性参数的方法 ,并用非线性最小方差法进行求解 .最后以不排水剪切强度 cu
Points out that the ordinary regression method can't take the auto\|correlation into account, and the probability model which can consider this kind of auto\|correlation is discussed. An accurate method is recommended which can estimate the value of soil property at a given depth, and non\|linear least square method is used to do the calculation. The regression variance of this method is lower than others among the literature can be seen. At the end of the paper, the data of undrained shear strength are used to do the estimation.
基金
国家自然科学基金资助项目! (5 96 790 16 )
关键词
空间变异性
不排水剪强度
统计模拟
土工试验
spatial variability
regression
nonlinear least squares
undrained shear strengt
