Improved wavelet thresholding combined with optimized BiLSTM for dam deformation prediction

石佳晨; 岳春芳; 朱明远; 皮李浪

doi:10.11660/slfdxb.20240709

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Improved wavelet thresholding combined with optimized BiLSTM for dam deformation prediction

更新时间：2026-06-30

- Improved wavelet thresholding combined with optimized BiLSTM for dam deformation prediction
- Journal of Hydroelectric Engineering Vol. 43, Issue 7, (2024)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.11660/slfdxb.20240709
  CLC：
- Online First：25 July 2024，
  
  Published：2024
- 稿件说明：
移动端阅览
石佳晨, 岳春芳, 朱明远, et al. Improved wavelet thresholding combined with optimized BiLSTM for dam deformation prediction[J]. Journal of Hydroelectric Engineering, 2024, 43(7).
DOI：

石佳晨, 岳春芳, 朱明远, et al. Improved wavelet thresholding combined with optimized BiLSTM for dam deformation prediction[J]. Journal of Hydroelectric Engineering, 2024, 43(7). DOI： 10.11660/slfdxb.20240709.

摘要

变形是反映大坝结构状态变化的重要指标。由于变形数据的非线性特点和其背后复杂的机理，提升变形的预测精度对大坝安全及结构控制具有重要意义。为此，基于融合建模理念提出了一种组合的大坝变形预测方法，该方法结合了改进小波阈值去噪与鹈鹕优化算法（POA）优化的双向长短期神经网络（BiLSTM）。首先，采用改进小波阈值去噪法对变形实测数据序列进行处理；其次，通过POA搜索最优超参数组合用于优化BiLSTM模型；最后，基于最优超参数下的BiLSTM模型进行大坝变形预测。工程实例表明，改进小波阈值法具有更好的去噪效果，POA-BiLSTM能够准确预测大坝变形。在最终测试集上平均MAE、MAPE、RMSE、R2分别为0.244、0.041、0.301、0.906。相较于其他方法，表现出更高的预测准确性和稳健性，可为大坝变形监测提供参考。

Abstract

Deformation serves as a crucial indicator of the structural changes of dams. Enhancing the prediction accuracy of dam deformation is of paramount significance for the safety and structural control of dams

due to the nonlinear characteristics of deformation data and the underlying intricate mechanism. This paper develops a combined approach for dam deformation prediction based on the integrated modeling concept

integrating an improved wavelet threshold denoising and a Pelican Optimization Algorithm (POA) optimized Bidirectional Long Short-Term Memory (BiLSTM) network. First

the deformation measurement data sequence is processed using an improved wavelet threshold denoising method; then

POA is used to search for the optimal hyperparameter combination to optimize the BiLSTM model; finally

dam deformation prediction is conducted based on the BiLSTM with the optimal hyperparameters. Engineering case studies demonstrate that this improved wavelet threshold method produces superior denoising effects

and POA-BiLSTM gives a satisfactory accuracy for dam deformation prediction. And on the ultimate test set

it has achieved the average MAE

MAPE

RMSE

and R2 of 0.244

0.041

0.301

and 0.906

respectively. Compared to other methods

it exhibits higher predictive accuracy and robustness

offering valuable insight for dam deformation monitoring.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

MPM-DEM hierarchical multiscale method for macroscopic and microscopic analysis of deformation in rockfill dams

Prediction of aqueduct deformation based on time series decomposition and machine learning

Long-term deformation prediction model of concrete dams and its application

Intelligent deformation predicting methods for underground chambers of Longtan hydropower station

Deformation prediction of high embankment dams by combining time series decomposition and deep learning

Related Author

马刚

王頔

李易奥

周伟

安妮

马钰明

王仁超

赵鹏远

Related Institution

State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering, Hohai University

College of Water Conservancy and Hydropower Engineering, Hohai University

Research Institute of Geotechnical Engineering,Hohai University

Key Laboratory of Ministry of Education for Geomechanics and Embankment Engineering, Hohai University

State Key Laboratory for Geomechanics and Deep Underground Engineering,China University of Mining and Technology

AI问答

⁰