基于广义Pareto分布的大坝预警指标拟定方法
发布时间:2019-02-21 17:33
【摘要】:将极值理论中的广义Pareto分布模型用于大坝预警指标拟定中是一个行之有效的方法,该方法通过设定某一阈值,以监测序列超过该阈值的实测值为分析样本,并认为该样本服从广义Pareto分布。由于阈值的选取关系到广义Pareto分布参数估计的精度,而用超限期望图法确定的阈值具有较大的主观性误差,因此,从定义出发,通过数学推导,建立了自动选取阈值的方法。通过实例分析表明,采用自动选取法确定阈值的广义Pareto分布拟定的大坝预警指标更加合理。
[Abstract]:It is an effective method to apply the generalized Pareto distribution model in extreme value theory to the determination of dam warning index. By setting a certain threshold value, the measured value of monitoring sequence exceeding that threshold is taken as the analysis sample. It is considered that the sample is based on the generalized Pareto distribution. Because the selection of threshold value is related to the accuracy of parameter estimation of generalized Pareto distribution, and the threshold value determined by the method of over-limit expectation graph has great subjective error, a method of automatically selecting threshold value is established from the definition and mathematical derivation. The analysis of examples shows that the dam warning index based on the generalized Pareto distribution with automatic selection method is more reasonable.
【作者单位】: 西京学院土木工程学院;
【基金】:陕西省教育厅科学研究项目(15JK2171)
【分类号】:TV698.1
[Abstract]:It is an effective method to apply the generalized Pareto distribution model in extreme value theory to the determination of dam warning index. By setting a certain threshold value, the measured value of monitoring sequence exceeding that threshold is taken as the analysis sample. It is considered that the sample is based on the generalized Pareto distribution. Because the selection of threshold value is related to the accuracy of parameter estimation of generalized Pareto distribution, and the threshold value determined by the method of over-limit expectation graph has great subjective error, a method of automatically selecting threshold value is established from the definition and mathematical derivation. The analysis of examples shows that the dam warning index based on the generalized Pareto distribution with automatic selection method is more reasonable.
【作者单位】: 西京学院土木工程学院;
【基金】:陕西省教育厅科学研究项目(15JK2171)
【分类号】:TV698.1
【相似文献】
相关期刊论文 前6条
1 王剑峰;宋松柏;;广义Pareto分布在超定量洪水序列频率分析中的应用[J];西北农林科技大学学报(自然科学版);2010年02期
2 陈子q,
本文编号:2427725
本文链接:https://www.wllwen.com/kejilunwen/shuiwenshuili/2427725.html