指数平滑法在基坑深层位移预测中的应用  

Application of Exponential Smoothing to Prediction of Deep Displacement in Foundation Pit

作　　者：熊莎[1] 贺跃光[1] 姬方[1] 戴潇蕾[1] 

机构地区：[1]长沙理工大学交通运输工程学院,湖南长沙410076

出　　处：《矿冶工程》2013年第2期5-7,共3页Mining and Metallurgical Engineering

基　　金：湖南省重点学科建设项目资助

摘　　要：将指数平滑法应用于基坑深层位移预测中,并利用累计方差和最小准则选取平滑系数α。运用指数平滑法对某基坑工程3#测斜孔20 m深处监测数据进行预测分析,得到最大绝对误差为0.41 mm,远小于规定值,表明预测效果良好。通过比较3#测斜孔15 m深处与20 m深处的同期预测数据的平均绝对误差与均方差,得出15 m深处预测误差较20 m深处大,表明20 m处预报较准确。Exponential smoothing was adopted for the predication of deep displacement in foundation pit. The smoothing coefficient a was selected based on the minimum value of cumulative sum of variance. The monitoring data obtained from 3# hole with clinometer at the depth of 20 m was predicted and analyzed by using exponential smoothing. The maximum error obtained is 0.41 far less than specified value, showing a good prediction effect. Based on the comparison between the mean absolute error and mean square error for the predicted results obtained at the depth of 15 m and 20 m of 3# hole, it is found that the prediction for the depth of 15 m has a bigger error than the depth of 20 m, so the prediction for the depth of 20 m is more precise.

关 键 词：基坑 深层位移 指数平滑 预报 

分 类 号：TU457[建筑科学—岩土工程]