原型观测数据离群点的检验

Detection on outlier of prototype observation data

在水工建筑物的原型观测数据处理工作中,经常会遇到一些异常值(离群点)。本文通过深入分析,判断离群点产生的性质和原因,从数量上揭示数据的变化规律,以动态的角度表现某一工况条件下,各变量之间的内在关系,从而达到认识水工建筑物运行状态的目的。

During the prototype observation of hydraulic structures, some abnormal values （outlier） often occurs in the treatment of the observed data. The causation and character of the occurrence of the outlier are judged herein through a detailed analysis ; in which the variable law of the data is quantitatively revealed and the inherent relationship among all the variables under a certain operation condition is dynamically presented as well, so as to acquaint the operation condition of the hydraulic structures concemed.