| 基于集合经验模态分解和自回归滑动平均的某碾压混凝土重力坝变形预测模型及应用 |
| |
| 引用本文： | 梁嘉琛,赵二峰,张秀山,孔庆梅,兰石发.基于集合经验模态分解和自回归滑动平均的某碾压混凝土重力坝变形预测模型及应用[J].水电能源科学,2015,33(3):68-70. |
| |
| 作者姓名： | 梁嘉琛 赵二峰 张秀山 孔庆梅 兰石发 |
| |
| 作者单位： | 1. 河海大学 a. 水利水电学院； b. 水文水资源与水利工程科学国家重点实验室； c. 水资源高效利用与 工程安全国家工程研究中心， 江苏 南京 210098； 2. 青海黄河水电公司 大坝管理中心， 青海 西宁 810008； 3. 古田溪水力发电厂， 福建 宁德 352200 |
| |
| 基金项目： | 国家自然科学基金重点项目（41323001，51139001）；水利部公益性行业科研专项经费项目(201201038，201301061)；江苏高校优势学科建设工程资助项目（水利工程）(YS11001) |
| |
| 摘 要： | 为更精确地预测大坝变形数据,针对大坝变形监测序列的非线性和非平稳性问题,提出了一种结合集合经验模态分解和自回归滑动平均模型的大坝变形预测模型。首先利用集合经验模态分解法将非平稳的大坝变形监测数据分解为具有不同特征尺度的本征模态函数,然后分析各分量特征并分别建立自回归滑动平均模型,选择各自适合的最优模型参数,最后叠加各分量的预测结果作为最终的变形预测结果。分析结果表明,相较单一预测模型,结合集合经验模态分解和自回归滑动平均模型的组合预测模型的预测精度更高。
|
| 关 键 词： | 大坝 变形 预测 集合经验模态分解 自回归滑动平均 |
Deformation Forecasting Model of RCC Gravity Dam and Its Application Based on Ensemble Empirical Mode Decomposition and Auto-Regressive Moving Average Model |
| |
| LIANG Jia-chen;ZHAO Er-feng;ZHANG Xiu-shan;KONG Qing-mei;LAN Shi-fa.Deformation Forecasting Model of RCC Gravity Dam and Its Application Based on Ensemble Empirical Mode Decomposition and Auto-Regressive Moving Average Model[J].International Journal Hydroelectric Energy,2015,33(3):68-70. |
| |
| Authors: | LIANG Jia-chen;ZHAO Er-feng;ZHANG Xiu-shan;KONG Qing-mei;LAN Shi-fa |
| |
| Affiliation: | LIANG Jia-chen;ZHAO Er-feng;ZHANG Xiu-shan;KONG Qing-mei;LAN Shi-fa;College of Water Conservancy and Hydropower Engineering,Hohai University;State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering,Hohai University;National Engineering Research Center of Water Resources Efficient Utilization and Engineering Safety,Hohai University;Dam Management Center,Yellow River Upstream Hydropower Development Co.,Ltd.;Gutianxi Hydroelectric Power Plant; |
| |
| Abstract: | In order to better predict the dam deformation data and to overcome the deficiencies in monitoring and predicting non-stationary dam deformation series, a hybrid model of dam deformation forecasting based on ensemble empirical mode decomposition (EEMD) and auto-regressive moving average (ARMA) is proposed. Firstly, the dam deformation series is decomposed into a set of intrinsic mode function (IMF) with different characteristic scales by using EEMD. And then the ARMA forecasting model of each IMF is established with the optimal model parameters. Finally, the final forecasting result is obtained by superimposing the forecasting results of each component. Compared to single forecasting model, the simulation results demonstrate that the hybrid EEMD-ARMA model has higher prediction accuracy. |
| |
| Keywords: | dam deformation forecasting EEMD ARMA |
| 本文献已被 CNKI 等数据库收录！ |
