基于ABCA-SVM的大坝变形预警模型  

Dam Deformation Early Warning Model Based on ABCA-SVM Model

作　　者：钱程[1,2] 李连基 周子东 QIAN Cheng;LI Lianji;ZHOU Zidong(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)

机构地区：[1]河海大学水利水电学院,江苏南京210098 [2]河海大学水文水资源与水利工程科学国家重点实验室,江苏南京210098

出　　处：《人民黄河》2018年第4期124-127,共4页Yellow River

基　　金：江苏省杰出青年基金资助项目(BK2012036);高等学校博士学科点专项科研基金资助课题(20130094110010);国家自然科学基金资助项目(51179066;51139001;41323001;51079086);水利部公益性行业科研专项(201301061;201201038)

摘　　要：合理分析大坝变形监测数据序列特征,精确预测大坝变形状况,是大坝安全监测的重要内容。针对常用大坝安全监测分析模型存在的不足,将人工蜂群算法与支持向量机模型结合起来,利用人工蜂群算法全局搜索能力强、收敛速度快等优点对支持向量机模型的惩罚因子C和核参数δ进行优化,建立了ABCA-SVM模型。某水电站大坝坝顶某点的112组径向位移预测实例表明,ABCA-SVM模型预测精度高于标准SVM模型的,可以在大坝安全监测领域推广应用。Reasonably analyzing the features of the measuring data series and accurately predicting the dam deformation are two important parts of dam safety monitoring.Aiming at the weaknessesof dam safety monitoring analysis models,a new composite model was established by combining artificial bee colony algorithm(ABCA)with support vector machine(SVM).ABCA had strong global search capability and was easy to converge,which could be used to optimize the parameters of SVM.Based on the measured data,the forecasting research shows that ABCASVM model has a higher precision than the standard SVM model.And the new model can be used in the dam safety monitoring field.

关 键 词：大坝安全 变形监测 人工蜂群算法 支持向量机 

分 类 号：TV698.1[水利工程—水利水电工程]