基于OWOA-RFWSVR-DLM的高寒区混凝土坝变形预测模型  

An OWOA-RFWSVR-DLM-based Model for Predicting DamDeformation in the Alpine Region

作　　者：葛盼猛 陈波[1,2] 陈伟楠 朱明远 GE Pan-meng;CHEN Bo;CHEN Wei-nan;ZHU Ming-yuan(College of Water Conservancy and Hydropower Engineering,Hohai University,Nanjing 210098,China;State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering,Hohai University,Nanjing 210098,China;Xinjiang Institute of Water Resources and Hydropower Research,Urumqi 830049,China)

机构地区：[1]河海大学水利水电学院,南京210098 [2]河海大学水文水资源与水利工程科学国家重点实验室,南京210098 [3]新疆水利水电科学研究院,乌鲁木齐830049

出　　处：《长江科学院院报》2023年第5期153-159,165,共8页Journal of Changjiang River Scientific Research Institute

基　　金：国家自然科学基金面上项目(52079049);江苏省基础研究计划青年项目(BK20160872)。

摘　　要：对于寒冷地区的混凝土大坝,由于表层保温层的影响,其内部温度往往滞后于气温变化。当内部温度计缺失时,使用水力-季节-时间(HST)模型进行大坝预测时存在较大的误差,且即使利用内部温度计进行多元回归(MR)模型的建模也无法反映温度与变形的非线性关系。因此,针对现阶段对高寒区变形预测精度低的问题,提出利用反向学习后的鲸群(OWOA)算法对RReliefF因子加权支持向量机(RFWSVR)与分布滞后线性模型(DLM)的温度因子的超参数进行寻优,以构建缺乏内部温度计的寒区混凝土大坝变形预测模型。结果表明:通过对所建立的变形预测模型与传统统计模型和其余常用机器学习算法的性能比较,证明所建立模型具有较高的预测精度,能更好地反映保温混凝土大坝的工作特点。Due to the protection of surface thermal insulation layer,the internal temperature of concrete dam in cold region lags behind the air temperature.When internal thermometers are lacking,HST(hydrostatic-seasonal-time)model generates large error in predictions;even when internal thermometers are present,MR(multiple regression)model can not refelct the nonlinear relation between temperature and deformation.To address the problem of inaccurate deformation prediction in alpine regions,we propose to use a support vector regression(SVR)weighted by the RReliefF algorithm and DLM(Distribution Lag Model)temperature factors to predict dam displacement.The necessary hyperparameters are optimized using an improved whale swarm approach with OBL(Opposition-based Learning).By comparing the performance of the proposed model with MR and other machine learning algorithms,we found that the proposed model has higher prediction accuracy and better reflects the working characteristics of an insulated concrete dam.

关 键 词：RFWSVR OWOA算法 DLM 大坝变形预测 高寒区 

分 类 号：TV698.1[水利工程—水利水电工程]