施工技术 2016年10月上 110 CONSTRUCTION TECHNOLOGY 第45卷第19期 D01:10.7672/sjs2016190110 基于趋势项分离的隧道变形组合预测研究 陈飞飞，杨振兴，马还援，李忠艳 (青海省水文地质及地热地质重点实验室（青海省水文地质工程地质环境地质调查院），青海西宁810008) [摘要]以小波变换分离隧道变形数据的趋势项和误差项，采用回归模型对趋势项进行单项预测，并进一步对其进 行组合预测：同时，利用BP神经网络对误差项及原始数据项进行预测，最后对比本文组合预测与传统BP神经网络 的预测结果.结果表明：ym5小波函数对本文监测数据的分离效果最好，而非线性组合预测的精度要优于线性组 合预测的精度，且综合对比本文组合预测和P神经网络的结果，得出本文的组合预测很大程度上提高了预测精 度，为隧道的变形预测提供了一种新的思路. [关键词]隧道工程；小波变换；回归模型；组合预测；BP神经网络 [中图分类号]U456.31 [文献标识码]A [文章编号]1002-8498(2016)19-0115-06 Prediction Combination of Tunnel Deformation Based on Trend Term Separation Chen Feifei Yang Zhenxing Ma Huanyuan Li Zhongyan Hydrogeological and Geothermal Geological Key Laboratory of Qinghai Province Hydro Geology and Engineering Geology and Enwironmental Geology Surtey Institute of Qinghai Province) Xining Qinghai 810008 China) Abstract:In this paper the trend and the error terms of the deformation data of the tunnel are separated by wavelet transform the authors use the regression model to forecast the trend and then make a bination forecast.At the same time the authors use BP neural network to predict the error term and the original data and then pare the forecasting results between bination forecast and the traditional BP neural network.The results show that sym5 wavelet function is the best for the separation of the monitoring data in this paper.The accuracy of nonlinear bination forecasting is better than that of linear bination forecasting through prehensive parison of the resu...
基于趋势项分离的隧道变形组合预测研究.pdf
