【24h】

Insensitivity regions for deformation measurement on a dam

机译:大坝变形测量的不敏感区

获取原文

摘要

Deformation measurement during the filling a dam can be modelled by a multivariate model. Multivariate models usually involve unknown parameters not only in the mean value of the observation matrix but also in the covariance matrix (variance components). The variance components must be estimated and plug-in estimators for the mean value parameters can be used. To find statistical properties of plug-in estimators is rather difficult. In some cases the sensitivity approach can be used. If we know that the true value of the variance components is with sufficiently high probability in so-called insensitivity region, then the plug-in estimator is almost the best linear unbiased estimator. The aim of the paper is to investigate this insensitivity regions, i.e. the region around the true value of variance components, where small changes of them are only of negligible influence on the mean value parameter estimators. The obtained results are applied on the problem of deformation measurement during the filling a dam.
机译:填充坝期间的变形测量​​可以由多变量模型建模。多变量模型通常涉及不仅在观察矩阵的平均值中的未知参数,而且涉及在协方差矩阵(方差分量)中。必须估计方差分量,并且可以使用用于平均值参数的插入式估计器。找到插件估计器的统计属性相当困难。在某些情况下,可以使用灵敏度方法。如果我们知道方差分量的真实值在所谓的不敏感区域中具有足够高的概率,则插入式估计器几乎是最佳的线性无偏的估计器。本文的目的是研究这种不敏感的区域,即围绕方差分量的真实值的区域,其中它们的小变化对平均值参数估计的影响众多。所得结果应用于填充坝期间变形测量的问题。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号