|本期目录/Table of Contents|

[1]王世杰,肖萌,华国威,等.基于CNN-GRU的混凝土大坝扬压力预测模型研究*[J].中国安全生产科学技术,2023,19(7):99-105.[doi:10.11731/j.issn.1673-193x.2023.07.015]
　WANG Shijie,XIAO Meng,HUA Guowei,et al.Research on uplift pressure prediction of concrete dam based on CNN-GRU[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2023,19(7):99-105.[doi:10.11731/j.issn.1673-193x.2023.07.015]
点击复制

基于CNN-GRU的混凝土大坝扬压力预测模型研究*
分享到：

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
19
期数:
2023年7期
页码:
99-105
栏目:
职业安全卫生管理与技术
出版日期:
2023-07-31

文章信息/Info

Title:
Research on uplift pressure prediction of concrete dam based on CNN-GRU
文章编号:
1673-193X(2023)-07-0099-07
作者:
王世杰; 肖萌; 华国威; 胡少华; 刘泽
（武汉理工大学 安全科学与应急管理学院，湖北 武汉 430070)
Author(s):
WANG Shijie;  XIAO Meng;  HUA Guowei;  HU Shaohua;  LIU Ze
(School of Safety Science and Emergency Management,Wuhan University of Technology,Wuhan Hubei 430070,China)
关键词:
CNN-GRU; 扬压力; 时间序列; 预测精度
Keywords:
CNN-GRU;  uplift pressure;  time series;  prediction accuracy
分类号:
X947
DOI:
10.11731/j.issn.1673-193x.2023.07.015
文献标志码:
A
摘要:
为准确预测混凝土大坝扬压力的变化趋势，基于扬压力历史监测数据，通过卷积神经网络（CNN）自动获取大坝历史监测数据在高维空间的联系，建立大坝环境量与扬压力的映射关系，结合门控循环单元（GRU）处理长时序监测数据的优越性，构建CNN-GRU扬压力预测模型，并以某大坝为例进行模型性能验证。研究结果表明：本文提出的模型在4个测点的MAE分别为0.155 4，0.039 76，0.230 6，0.182 7 m，RMSE分别为0.027 2，0.054 85，0.291 6，0.212 8 m，能够高精度地演绎扬压力整体及局部拐点上的变化趋势，其预测性能明显优于PSO-BP、BBO-SVM、GRU、LSTM模型。研究结果可为大坝安全监测提供支撑。
Abstract:
To accurately predict the change trend of uplift pressure of the concrete dams,the linkage of historical monitoring data of dam in high-dimensional space was obtained automatically by convolutional neural network (CNN) based on the historical monitoring data of uplift pressure,and the mapping relationship between dam environmental volume and uplift pressure was established.A CNN-GRU uplift pressure prediction model was constructed through combining the superiority of gated recurrent unit (GRU) in processing the long time series monitoring data,and the model performance was verified with a dam as an example.The results show that the MAE of the model proposed in this paper at four measurement points are 0.155 4,0.039 76,0.230 6,0.182 7 m respectively,and the RMSE are 0.027 2,0.054 85,0.291 6 and 0.212 8 m respectively,which can deduce the change trend of lift pressure at the overall and local inflection points with high accuracy,and can also effectively predict the change trend of lift pressure.The prediction performance is significantly better than those of PSO-BP,BBO-SVM,GRU,and LSTM models.The results can provide support for the safety monitoring of dams.

参考文献/References:

［1］MA C H,ZHAO T H,LI G C,et al.Intelligent anomaly identification of uplift pressure monitoring data and structural diagnosis of concrete dam［J］.Applied Sciences,2022,12(2):612-621.
［2］PEREIRA R,BATISTA A L,NEVES L C,et al.A priori uplift pressure model for concrete dam foundations based on piezometric monitoring data［J］.Structure and Infrastructure Engineering,2021,17(11):1523-1534.
［3］BELMOKRE A,MIHOUBI M K,SANTILLAN D.Seepage and dam deformation analyses with statistical models:support vector regression machine and random forest［J］.Procedia Structural Integrity,2019,17:698-703.
［4］RANKOVIC＇ V,GRUJOVIC＇ N,DIVAC D,et al.Development of support vector regression identification model for prediction of dam structural behaviour［J］.Structural Safety,2014,48:33-39.
［5］SU H,LI X,YANG B,et al.Wavelet support vector machine-based prediction model of dam deformation［J］.Mechanical Systems and Signal Processing,2018,110:412-427.
［6］袁志明,李沛鸿,刘小生.顾及邻点变形因素的改进PSO-SVM模型大坝变形预测［J］.江西理工大学学报,2020,41(3):16-23. YUAN Zhiming,LI Peihong,LIU Xiaosheng.Improved deformation prediction of PSO-SVM model dam taking into account adjacent deformation factors［J］.The Jiangxi University of Science and Technology Journal,2020,41(3):16-23.
［7］ZHANG J,TANG H,TANNANT D D,et al.Combined forecasting model with CEEMD-LCSS reconstruction and the ABC-SVR method for landslide displacement prediction［J］.Journal of Cleaner Production,2021,293:126205.
［8］华国威,娄彦彬,王世杰,等.基于PCA-BBO-SVM的尾矿坝变形预测模型与性能验证研究［J］.中国安全生产科学技术,2022,18(9):20-26. HUA Guowei,LOU Yanbin,WANG Shijie,et al.Research on deformation prediction model and performance verification of tailings dam based on PCA-BBO-SV［J］.Journal of Safety Science and Technology,2022,18(9):20-26.
［9］LIU Y H,XIAO F.Prediction of dam horizontal displacement based on CNN-LSTM and attention mechanism［J］.Academic Journal of Architecture and Geotechnical Engineering,2021,3(1):47-53.
［10］ZHU Y,GAO Y J,WANG Z H,et al.A tailings dam long-term deformation prediction method based on empirical mode decomposition and LSTM model combined with attention mechanism［J］.Water,2022,14(8):1229-1234.
［11］YANG B B,XIAO T,WANG L Q,et al.Using complementary ensemble empirical mode decomposition and gated recurrent unit to predict landslide displacements in dam reservoir［J］.Sensors,2022,22(4):1320-1327.
［12］LI X,SU H Z,HU J.The prediction model of dam uplift pressure based on random forest［J］.IOP Conference Series:Materials Science and Engineering,2017,229(1):371-380.
［13］刘超,雷晨,李树刚,等.基于CNN-GRU的瓦斯浓度预测模型及应用［J］.中国安全生产科学技术,2022,18(9):62-68. LIU Chao,LEI Chen,LI Shugang,et al.Gas concentration prediction model and application based on CNN-GRU［J］.Journal of Safety Science and Technology,2022,18(9):62-68.
［14］韩莹,王乐豪,魏平慧，等.水库水位的VMD-CNN-GRU混合预测模型［J］.南京信息工程大学学报,2022,12(2):1-11. HAN Ying,WANG Lehao,WEI Pinghui,et al.VMD-CNN-GRU hybrid prediction model for reservoir water level［J］.Journal of Nanjing University of Information Science & Technology,2022,12(2):1-11.
［15］卢武,郑人杰,赵文彬,等.基于EMD-GRU的短期电力负荷预测方法［J］.电气传动,2022,52(21):74-80. LU Wu,ZHENG Renjie,ZHAO Wenbin,et al.Short-term power load forecasting method based on EMD-GRU［J］.Electric Drive,2022,52(21):74-80.
［16］郝天轩,陈国印,赵立桢,等.基于Adam优化深度神经网络快速确定瓦斯抽采半径［J］.中国安全生产科学技术,2022,18(6):52-57. HAO Tianxuan,CHEN Guoyin,ZHAO Lizhen,et al.Rapid determination of gas extraction radius based on Adam optimization deep neural network［J］.Journal of Safety Science and Technology,2022,18(6):52-57.
［17］武小梅,张琦,田明正.基于VMD-SE和优化支持向量机的光伏预测方法［J］.电力科学与工程,2017,33(9):29-36. WU Xiaomei,ZHANG Qi,TIAN Mingzheng.Photovoltaic prediction method based on VMD-SE and optimized support vector machine［J］.Electric Power Science and Engineering,2017,33(9):29-36.
［18］GAO S,HUANG Y F,ZHANG S,et al.Short-term runoff prediction with GRU and LSTM networks without requiring time step optimization during sample generation［J］.Journal of Hydrology,2020,589:125188.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期： 2022-12-10
* 基金项目： 国家自然科学基金项目（42271026）
作者简介： 王世杰，博士，研究员，主要研究方向为突发事件应急管理、公共安全管理。
通信作者： 华国威，硕士，主要研究方向为工程安全及应急管理。
更新日期/Last Update: 2023-08-07