| 注册
首页|期刊导航|水利学报|机理-数据融合与残差修正的土石坝渗压预测模型研究

机理-数据融合与残差修正的土石坝渗压预测模型研究

黄昊冉 谷艳昌 陈斯煜 王士军 黄海兵

水利学报2025,Vol.56Issue(3):398-410,13.
水利学报2025,Vol.56Issue(3):398-410,13.DOI:10.13243/j.cnki.slxb.20240302

机理-数据融合与残差修正的土石坝渗压预测模型研究

Study on the seepage prediction model of earth-rock dams based on mechanism-data fusion and residual correction

黄昊冉 1谷艳昌 2陈斯煜 3王士军 3黄海兵3

作者信息

  • 1. 南京水利科学研究院大坝安全与管理研究所,江苏南京 210029
  • 2. 南京水利科学研究院大坝安全与管理研究所,江苏南京 210029||水利部大坝安全管理中心,江苏南京 210029||水利部水旱灾害防御重点实验室,江苏南京 210029
  • 3. 南京水利科学研究院大坝安全与管理研究所,江苏南京 210029||水利部大坝安全管理中心,江苏南京 210029
  • 折叠

摘要

Abstract

The mechanistic models can predict and evaluate the seepage safety state of earth-rock dams,which of-fer clear physical meaning and good interpretations,but their prediction accuracy fluctuates greatly.To enhance this accuracy,a fusion model that incorporates a data-driven deep learning approach was introduce in this study,and the Sparrow Search Algorithm(SSA)and Radial Basis Function(RBF)were employed to invert the permea-bility coefficient.This process constructs an SSA-RBF surrogate model for predicting seepage pressure,yielding both the model's predictive values and a residual sequence.Then,the residual sequence was decomposed by u-sing Variational Mode Decomposition(VMD),training a Long Short-Term Memory(LSTM)neural network to ob-tain a model for correcting the residual sequence.By overlaying the mechanistic model with the data-driven model,an SSA-RBF-VMD-LSTM fusion model was constructed,which enables accurate predictions of seepage water lev-els.The engineering case demonstrates that the model proposed in this paper possesses high predictive accuracy,with improvements of 89.64%,69.59%,and 60.45%in prediction accuracy compared to statistical models,LSTM models,and SSA-RBF-LSTM models,respectively.Notably,even when the seepage process line under-goes significant fluctuations,the model is still capable of providing timely and accurate predictions,showcasing good stability and extrapolation capabilities.These attributes make the model worthy of practical application and dissemination.

关键词

土石坝/代理模型/麻雀搜索算法/变分模态分解/LSTM神经网络/机理-数据驱动融合

Key words

earth-rock dam/surrogate models/sparrow search algorithm/Variational Modal Decomposition/LSTM neural networks/mechanism-data-driven fusion

分类

建筑与水利

引用本文复制引用

黄昊冉,谷艳昌,陈斯煜,王士军,黄海兵..机理-数据融合与残差修正的土石坝渗压预测模型研究[J].水利学报,2025,56(3):398-410,13.

基金项目

国家自然科学基金项目(51979175,52309157) (51979175,52309157)

南京水利科学研究院研究生学位论文基金项目(Yy724005) (Yy724005)

南京水利科学研究院中央级公益性科研院所基本科研业务费(Y723008,Y722003,Y723002) (Y723008,Y722003,Y723002)

水利学报

OA北大核心

0559-9350

访问量1
|
下载量0
段落导航相关论文