文章摘要
傅蜀燕, 杨石勇, 陈德辉, 王子轩, 欧 斌.土石坝渗流预测的BiTCN-Attention-LSSVM模型研究Journal of Water Resources and Water Engineering[J].,2025,36(1):118-128
土石坝渗流预测的BiTCN-Attention-LSSVM模型研究
BiTCN-Attention-LSSVM Modeling for seepage prediction of earth-rock dams
  
DOI:10.11705/j.issn.1672-643X.2025.01.13
中文关键词: 土石坝测压管水位  渗流预测  双向时序卷积神经网络  注意力机制  最小二乘支持向量机
英文关键词: piezometer water level in earth-rock dam  seepage prediction  bidirectional temporal convolutional network (BiTCN)  attention mechanism (Attention)  least square support vector machine (LSSVM)
基金项目:国家自然科学基金项目(52069029、52369026); “一带一路”水与可持续发展科技基金资助项目(2023490411); 云南省农业基础研究联合专项面上项目(202401BD070001-071)
Author NameAffiliation
FU Shuyan1,2,3, YANG Shiyong1,3, CHEN Dehui1,3, WANG Zixuan1,3, OU Bin1,2,3 (1.云南农业大学 水利学院 云南 昆明 650201
2.河海大学 水灾害防御全国重点实验室 江苏 南京 210098
3.云南省中小型水利工程智慧管养工程研究中心云南 昆明 650201) 
Hits: 142
Download times: 71
中文摘要:
      为了克服常规机器学习模型在处理时序数据时难以有效捕捉长期依赖关系和局部重要性的局限,提出了一种基于双向时序卷积神经网络(BiTCN)、注意力机制(Attention)和最小二乘支持向量机(LSSVM)的土石坝渗流预测耦合模型。该模型利用BiTCN从前、后两个方向捕获时序数据中的长期依赖关系,引入Attention机制帮助模型专注于与预测相关的关键局部特征,并将BiTCN-Attention深度处理后的特征输入LSSVM模型中进行预测,最后以2个不同的数据集分析了模型的预测效果。案例分析表明:与LSSVM、CNN-LSSVM和TCN-LSSVM相比,BiTCN-Attention-LSSVM模型预测的各项评价指标均为最优,在土石坝测压管水位预测中展现出更高的模型精度和稳定性;BiTCN与Attention的相互结合能够更好地提取时序数据中的相互依赖关系,将BiTCN-Attention提取的特征输入LSSVM中进行预测可获得良好的预测性能,数据集扩充处理后有效提高了模型的学习能力。
英文摘要:
      Conventional machine learning models often fail the task of identifying long-term dependencies and local importance when dealing with time-series data. To address this problem, we proposed a coupled model for seepage prediction of earth and rock dams based on bidirectional temporal convolutional network (BiTCN), attention mechanism (Attention), and least squares support vector machine (LSSVM). The model uses BiTCN to capture the long-term dependencies in the time-series data from both forward and backward directions, introduces the attention mechanism to help the model focus on the key local features related to the prediction, and inputs the deeply processed BiTCN-Attention features into the LSSVM model for better prediction results. To analyze the prediction effect, the model was used to process two different datasets. The results of case analysis show that compared with LSSVM, CNN-LSSVM and TCN-LSSVM, the evaluation indexes of BiTCN-Attention-LSSVM model are the best, and the proposed model shows higher accuracy and stability in the prediction of piezometer water level in the earth-rock dam. The combination of BiTCN and Attention can better extract the interdependence relationship in time-series data. Inputting the features extracted by BiTCN-Attention into LSSVM for prediction can achieve better prediction performance. After the data set is expanded, the learning ability of the model is effectively improved.
View Full Text   View/Add Comment  Download reader
Close
function PdfOpen(url){ var win="toolbar=no,location=no,directories=no,status=yes,menubar=yes,scrollbars=yes,resizable=yes"; window.open(url,"",win); } function openWin(url,w,h){ var win="toolbar=no,location=no,directories=no,status=no,menubar=no,scrollbars=yes,resizable=no,width=" + w + ",height=" + h; controlWindow=window.open(url,"",win); } &et=0E0AE80293F9EEDDFD5BFDD55BD739261652F0E3205BD5B5C6367AA333A70D1011C106B6B3A196D00E653D1540327057C3D59BE246E7D5C7EA3E039963B2AE4F076819359DCA00E7B86FC03412329016&pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=3ECA06F115476E3F&jid=BC473CEDCB8CE70D7B12BDD8EA00FF44&yid=E6A891D2134F30C0&aid=&vid=&iid=CA4FD0336C81A37A&sid=7F5DDA4924737DF5&eid=1F199509C0B6C4D6&fileno=20250113&flag=1&is_more=0">