SBL驱动的可解释性大坝变形区间预测模型  

Sparse Bayesian learning-driven interpretable interval prediction model for dam deformation

作　　者：陈斯煜 顾冲时[3] 盛金保[1,2,4] 谷艳昌 林潮宁[3] CHEN Siyu;GU Chongshi;SHENG Jinbao;GU Yanchang;LIN Chaoning(Dam Safety Management Department,Nanjing Hydraulic Research Institute,Nanjing 210029,China;Dam Safety Management Center of the Ministry of Water Resources,Nanjing 210029,China;College of Water Conservancy and Hydropower Engineering,Hohai University,Nanjing 210098,China;Key Laboratory of Reservoir and Dam Safety Ministry of Water Resources,Nanjing 210024,China)

机构地区：[1]南京水利科学研究院大坝安全与管理研究所,南京210029 [2]水利部大坝安全管理中心,南京210029 [3]河海大学水利水电学院,南京210098 [4]水利部水库大坝安全重点实验室,南京210024

出　　处：《水力发电学报》2025年第1期18-29,共12页Journal of Hydroelectric Engineering

基　　金：国家自然科学基金项目(52309157,52309151);水利部水库大坝安全重点实验室开放研究基金(YK323007)。

摘　　要：变形是反映大坝结构性态的重要效应量。针对现有大坝变形预测中不确定性量化和模型可解释性欠佳的问题,本文综合考虑数据噪声和模型参数不确定性,提出了稀疏贝叶斯学习(SBL)驱动的大坝变形区间预测模型。借助并行Rao-3算法和交叉验证策略对核函数参数进行自适应优化,建立了经参数优化的稀疏贝叶斯学习模型,能够准确表征库水位、气温和时效变量与大坝变形的非线性映射关系。进一步,将全局敏感度分析与预测模型相结合,计算了大坝变形影响变量的特征重要度,剖析并解释了特征变量对变形预测的影响。以第16届国际大坝数值分析基准研讨会中的EDF混凝土拱坝为研究案例进行分析,研究结果表明:与多元线性回归、RBFN模型和GPR模型相比,所提出的预测模型具有较高的点预测和区间预测精度,并兼有良好的可解释性。Deformation is a crucial indicator of the structural behaviors of a water dam.To address the issues of uncertainty quantification and model interpretability in dam deformation prediction,this study presents a sparse Bayesian learning(SBL)-driven model for interval prediction of dam deformation,considering both data noise and parameter uncertainty.We adopt a parallel Rao-3 algorithm and a crossvalidation strategy to optimize adaptively the parameters of the kernel function,and then construct an optimized sparse Bayesian learning model that accurately captures the nonlinear relationship between the input variables(i.e.reservoir water level,temperature,and time-dependent variables)and output variables(i.e.dam displacements).For the variables that influence dam deformation,we calculate their feature importance by integrating global sensitivity analysis with this new prediction model,and gain valuable insights into the impact of feature variables on deformation prediction.A case study is made on an EDF concrete arch dam originating from the 16th International Benchmark Workshop on Numerical Analysis of Dams.The results demonstrate our prediction model outperforms the multiple linear regression statistical models,radial basis function networks,and Gaussian process regression models in terms of point prediction and interval prediction accuracy while maintaining good interpretability.

关 键 词：大坝变形预测 区间预测 安全监控 稀疏贝叶斯学习 全局敏感度分析 可解释性 

分 类 号：TV698.1[水利工程—水利水电工程]