水利水电科技进展2025，Vol.45Issue(4)：76-84,9.DOI:10.3880/j.issn.1006-7647.2025.04.011
基于概率性预测的抽水蓄能电站大坝渗流安全监控模型
Seepage safety monitoring model for pumped storage power station dams based on probabilistic prediction
摘要
Abstract
To address the issue of low prediction accuracy caused by uncertainties in the selection of factors and construction of the seepage safety monitoring model for pumped storage power station dams,this study integrated deep learning models with probabilistic prediction methods.By incorporating the feature extraction capability of convolutional neural network(CNN),the data mining potential of bidirectional gated recurrent units(BiGRU),the parameter optimization advantage of the dung beetle optimization(DBO)algorithm,and the probabilistic prediction capability of quartile regression(QR),a probabilistic dam seepage prediction model based on DBO,CNN,BiGRU,and QR was established.At the same time,to construct an optimal factor set suitable for the seepage safety monitoring model for pumped storage power stations,the lag effect of seepage was fully taken into account,and the kernel principal component analysis(KPCA)was adopted to optimize the influencing factors of the model.Engineering case studies demonstrate that the established probabilistic dam seepage prediction model can not only provide high-accuracy deterministic prediction results of dam seepage pressure,but also yield corresponding probabilistic prediction intervals to reflect the uncertainty of seepage changes,which can provide more comprehensive evaluation information for seepage safety monitoring of pumped storage power station dams.关键词
大坝安全监控/抽水蓄能电站/监控模型/渗流预测/深度学习/概率性预测Key words
dam safety monitoring/pumped storage power station/monitoring model/seepage prediction/deep learning/probabilistic prediction分类
建筑与水利引用本文复制引用
李心如,宋锦焘,杨杰,许增光..基于概率性预测的抽水蓄能电站大坝渗流安全监控模型[J].水利水电科技进展,2025,45(4):76-84,9.基金项目
国家自然科学基金面上项目(52279140) （52279140）
国家自然科学基金青年基金项目(52109166) （52109166）
