院报 ›› 2020, Vol. 37 ›› Issue (11): 70-73.DOI: 10.11988/ckyyb.20190892

• 工程安全与灾害防治 • 上一篇    下一篇

基于EEMD-ELM的大坝变形预测模型

鄢涛1,2,3, 陈波1,2,3, 曹恩华1,2,3, 刘永涛1,2,3   

  1. 1.河海大学 水文水资源与水利工程科学国家重点实验室,南京 210098;
    2.河海大学 水资源高效利用与工程安全国家工程研究中心,南京 210098;
    3.河海大学 水利水电学院,南京 210098
  • 收稿日期:2019-07-24 修回日期:2019-10-28 出版日期:2020-11-01 发布日期:2020-12-02
  • 通讯作者: 陈 波(1986-),男,浙江绍兴人,副教授,博士,研究方向为水工结构安全监控。E-mail:chenbo@hhu.edu.cn
  • 作者简介:鄢 涛(1996-),男,江西南昌人,硕士研究生,研究方向为水工结构安全监控。E-mail: yantao@hhu.edu.cn
  • 基金资助:
    国家重点研发计划项目(2018YFC0407104);国家自然科学基金青年项目(51609074);江苏省基础研究计划青年项目(BK20160872)

Prediction of Dam Deformation Using EEMD-ELM Model

YAN Tao1,2,3, CHEN Bo1,2,3, CAO En-hua1,2,3, LIU Yong-tao1,2,3   

  1. 1. State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering, Hohai University, Nanjing210098, China;
    2. National Engineering Research Center of Water Resources Efficient Utilization and EngineeringSafety, Hohai University, Nanjing 210098, China;
    3. College of Water Conservancy and HydropowerEngineering, Hohai University, Nanjing 210098, China
  • Received:2019-07-24 Revised:2019-10-28 Online:2020-11-01 Published:2020-12-02

PDF

1207

摘要： 建立合理可信的大坝变形监控模型对科学有效地分析大坝变形监测数据和准确可靠地评估大坝工作运行状况意义重大。通过EEMD算法分解大坝变形量,得到代表不同特征尺度的本征模函数(IMF)分量,针对不同IMF分量选择不同影响因素,将各IMF分量作为极限学习机(ELM)的训练样本对大坝变形分量进行分析、拟合、预测,最后累加各IMF分量的预测结果得到大坝变形预测值。以某碾压混凝土重力坝为例,利用EEMD-ELM模型对大坝变形量进行预测,同时与BPNN模型和ELM模型的预测结果进行对比分析,其中EEMD-ELM模型的平均相对误差为0.566,较BPNN模型、ELM模型分别降低54%和14.8%,表明EEMD-ELM模型预测精度更高,具备一定的应用价值。

关键词: 大坝变形, 预测模型, 集合经验模态分解(EEMD), 极限学习机(ELM), 本征模函数(IMF)

Abstract: A reasonable and credible dam deformation monitoring model is of great significance for scientific and effective analysis of dam deformation monitoring data and accurate and reliable evaluation of dam's working and operating conditions. The EEMD (Ensemble Empirical Mode Decomposition) model is adopted to decompose the dam deformation monitoring data, and the IMF (Intrinsic Mode Function) components representing different feature scales are obtained. With different influence factors for different components, the IMF components are used as the training samples of ELM (Extreme Learning Machine) to analyze, fit and predict the monitoring data. The predicted values of dam deformation are obtained by adding the values of each component. With a RCC (Roller Compacted Concrete) gravity dam as an example, the prediction result of EEMD-ELM model is compared with those of BPNN (Back Propagation Neural Network) model and ELM model. The comparison result reveal that the prediction accuracy of EEMD-ELM model is higher than that of BPNN model and ELM model, with the mean relative error merely 0.566, 54% and 14.8% lower than those of BPNN and ELM, respectively.

Key words: dam deformation, prediction model, EEMD, ELM, IMF

中图分类号: 

*严禁使用本系统存储、处理、传输涉密信息*
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持：support@magtech.com.cn
Baidu
map