摘要
安全监测是研究和防治滑坡的重要手段之一,而位移监测又是滑坡监测中一种最常用的监测手段。滑坡位移监测数据的分析一般基于平面文件进行,而本研究则基于数据仓库的概念,深入分析滑坡位移监测时间序列数据,使用建模工具Power Designer建立了滑坡位移监测多维模型,在多维数据集的基础上进行数据挖掘分析。以长江三峡库区白水河滑坡位移监测数据为例,设计了滑坡监测数据多维数据集的维、概念层次和度量等,并在SQL Server 2005 Analysis Services软件中使用Microsoft时序算法实现数据挖掘,对滑坡位移进行预测分析,得到的预测数据与实测数据误差很小,表明Microsoft时序算法可用于滑坡监测数据的短期预测。
Security monitoring is one of the most important ways to investigate and control landslides and displacement monitoring is the most common way to monitor landslides. The analysis of landslide displacement monitoring data is generally based on flat files. A different approach based on data warehouse is proposed,which analyzes in depth the time series data from landslide displacement monitoring and build a multidimensional model of landslide displacement monitoring using CASE tool Power Designer. By the approach,a multidimensional model is designed and applied in Baishuihe landslide in the Three Gorges Reservoir area. Data mining process is then implemented using the algorithm of Microsoft Time Series in SQL Server 2005 Analysis Services. Results show that the predicted value is approximately in accordance with the measured value and the algorithm is applicable in short-term prediction.
出处
《水土保持通报》
CSCD
北大核心
2010年第4期121-124,共4页
Bulletin of Soil and Water Conservation
基金
三峡库区地质灾害防治工作指挥部"三峡库区地质灾害预警指挥系统(GHPACS)数据仓库及管理系统建设"(SXJC-3ZH1B1)
关键词
时间序列
滑坡监测
数据仓库
多维建模
数据挖掘
time series
landslide monitoring
data warehouse
multidimensional modeling
data mining
