张健飞,衡琰

• 1:河海大学力学与材料学院

摘要(Abstract)：

为了进一步提高混凝土坝变形预测精度，基于“先分解再重构”的思想，将变分模态分解(VMD)、排列熵(PE)与卷积神经网络(CNN)相结合，提出了一种混凝土坝变形预测模型。通过VMD和计算模态分解余量的PE将原始实测变形时间序列数据自适应地分解为一系列具有不同频域尺度特征的模态分量，然后将每个模态分量作为单独的子序列，采用CNN直接对各子序列进行时域建模并预测，最后将各个子序列的预测值叠加重构得到最终的大坝变形预测值。实测数据计算结果表明：采用计算模态分解余量PE的方法可以得到最优的模态分量个数，实现实测数据的最优分解；较之于CNN和LSTM模型，VMD-PE-CNN模型在测试数据上的均方根误差分别降低了61.8%和65.5%,显示出更强的预测能力。

关键词(KeyWords)： 变分模态分解;卷积神经网络;排列熵;变形预测;深度学习

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(12072105)

作者(Author): 张健飞,衡琰

DOI: 10.13928/j.cnki.wrahe.2022.11.010

参考文献(References)：

• [1] 周仁练，苏怀智，韩彰，等.混凝土坝变形的长期预测模型与应用[J].水力发电学报，2021,40(9):122-131.ZHOU Renlian,SU Huaizhi,HAN Zhang,et al.Long-term deformation prediction model of concrete dams and its application[J].Journal of Hydroelectric Engineering,2021,40(9):122-131.
• [2] 吴中如，陈波.大坝变形监控模型发展回眸[J].现代测绘，2016,39(5):1-3.WU Zhongru,CHEN Bo.A review on development of dam safety monitoring models[J].Modern Surveying and Mapping,2016,39(5):1-3.
• [3] 闫滨.大坝安全监控及评价的智能神经网络模型研究[D].大连：大连理工大学，2006.YAN Bin.Study of intelligent neural network model for dam safety monitoring and safety evaluation[D].Dalian:Dalian University of Technology,2006.
• [4] 张帆，胡伍生.神经网络融合模型在大坝安全监控中的应用[J].测绘工程，2015,24(1):53-56.ZHANG Fan,HU Wusheng.Application of neural network merging model to dam safety monitoring[J].Engineering of Surveying and Mapping,2015,24(1):53-56.
• [5] 魏道红，王博，张明.基于CNN的混凝土坝变形预测深度学习模型研究[J].水利水电技术，2021,52(6):52-57.WEI Daohong,WANG Bo,ZHANG Ming.A deep learning model for concrete dam deformation prediction based on CNN[J].Water Resources and Hydropower Engineering,2021,52(6):52-57.
• [6] 胡安玉，包腾飞，杨晨蕾，等.基于LSTM-Arima的大坝变形组合预测模型及其应用[J],长江科学院院报，2020,37(10):64-68.HU Anyu,BAO Tengfei,YANG Chenlei,et al.LSTM-ARIMA-based prediction of dam deformation:model and Its application[J].Journal of Yangtze River Scientific Research Institute,2020,37(10):64-68.
• [7] QU Xudong,YANG Jie,CHANG Meng.A deep learning model for concrete dam deformation prediction based on RS-LSTM[J].Journal of Sensors,2019:4581672.
• [8] YANG Dashan,GU Chongshi,ZHU Yantao,et al.A concrete dam deformation prediction method based on LSTM with attention mechanism[J].IEEE Access,2020,8:185177-185186.
• [9] REN Qiubing,LI Mingchao,LI Heng,et al.A novel deep learning prediction model for concrete dam displacements using interpretable mixed attention[J].Advanced Engineering Informatics,2021,50:101407.
• [10] LI Mingchao,LI Minghao,REN Qiubing,et al.DRLSTM:A dual-stage deep learning approach driven by raw monitoring data for dam displacement prediction[J].Advanced Engineering Informatics,2022,51:101510.
• [11] 周兰庭，柳志坤，徐长华.基于WA-LSTM-ARIMA的混凝土坝变形组合预测模型[J].人民黄河，2022,44(1):124-128.ZHOU Lanting,LIU Zhikun,XU Changhua.Concrete dam deformation combination prediction based on WA-LSTM-ARIMA[J].Yellow River,2022,44(1):124-128.
• [12] 马佳佳，苏怀智，王颖慧.基于EEMD-LSTM-MLR的大坝变形组合预测模型[J].长江科学院院报，2021,38(5):47-54.MA Jiajia,SU Huaizhi,WANG Yinhui.Combinatorial precondition model for dam deformation based on EEMD-LSTM-MLR[J].Journal of Yangtze River Scientific Research Institute,2021,38(5):47-54.
• [13] 宋洋，杨杰，宋锦焘，等.基于CEEMDAN-PE-LSTM的混凝土坝变形预测[J].水利水运工程学报，2021(3):41-49.SONG Yang,YANG Jie,SONG Jintao,et al.Concrete dam deformation prediction based on CEEMDAN-PE-LSTM model[J].Hydro-Science and Engineering,2021(3):41-49.
• [14] 侯回位，郑东健，刘永涛，等.基于 EEMD-SE-LSTM 的混凝土坝变形监测模型[J].水利水电科技进展，2022,42(1):61-66.HOU Huiwei,ZHENG Dongjian,LIU Yongtao,et al.Deformation monitoring model of concrete dams based on EEMD-SE-LSTM[J].Advances in Science and Technology of Water Resources,2022,42(1):61-66.
• [15] 罗亦泳，黄城，张静影.基于变分模态分解的变形监测数据去噪方法[J].武汉大学学报(信息科学版),2020,45(5):784-790.LUO Yiyong,HUANG Cheng,ZHANG Jingying.Denoising method of deformation monitoring data based on variational mode decomposition[J].Geomatics and Information Science of Wuhan University,2020,45(5):784-790.
• [16] 陈竹安，熊鑫，游宇垠.变分模态分解与长短时神经网络的大坝变形预测[J].测绘科学，2021,46(9):34-42.CHEN Zhuan,XIONG Xin,YOU Yuyin.Variational mode deconposition and long short time neural network for dam deformation prediction[J].Science of Surveying and Mapping,2021,46(9):34-42.
• [17] DRAGOMIRETSKIY K,ZOSSO D.Variational Mode Decomposition.IEEE Transactions on Signal Processing,2014,62(3):531-544.
• [18] 罗亦泳，黄城，张静影.基于改进 IVMD 的工程结构状态特征分析研究[J].应用基础与工程科学学报，2021,29(4):873-888.LUO Yiyong,HUANG Cheng,ZHANG Jingying.Structural state feature analysis based on improved variational mode decomposition[J].Journal of Basic Science and Engineering,2021,29(4):873-888.
• [19] 杨云，张昊宇.薛元贺，等.基于VMD和排列熵的滚动轴承故障诊断研究[J].组合机床与自动化加工技术，2021(6):90-93.YANG Yun,ZHANG Haoyu,XUE Yuanhe,et al.Research on fault diagnosis of rolling bearing based on VMD and permutation entropy[J].Modular Machine Tool & Automatic Manufacturing Technique,2021(6):90-93.
• [20] 周飞燕，金林鹏，董军.卷积神经网络研究综述[J].计算机学报，2017,40(7):1-23.ZHOU Feiyan,JIN Linpeng,DONG Jun.Review of convolutional network[J].Chinese Journal of Computers,2017,40(7):1-23.