摘要
大坝变形分析是研究大坝变形规律和保证大坝安全的重要组成部分。基于大坝变形时间序列的分形特征,同时考虑到分形插值在大坝变形时间序列拟合和预测时的分数维特点,以及外延序列越远、预测精度越差的缺点,引入支持向量机算法对分形插值模型进行优化。针对大坝变形时间序列特点,通过优化垂直比例因子和核函数,建立了分形插值和支持向量机混合模型。以某混凝土重力坝引张线8号测点水平位移为例,建立了分形插值和支持向量机混合模型,对变形时间序列进行拟合和预测分析,计算结果表明混合模型具有更高的精度,可以应用于大坝变形分析中。
Dam deformation analysis is an important component of researching dam deformation regulation and ensuring dam safety. Support vector machine algorithm is integrated to optimize the fractal interpolation model. According to the characteristics of dam deformation time series, a hybrid model of fractal interpolation and support vector machine is established by optimizing vertical scale factor and kernel function.Deformation data of No 8 Observation Point in a concrete gravity dam is analyzed as an example, a hybrid model of fractal interpolation and support vector machine is established to fit and predict the deformation time series. The calculation results show that the hybrid model has higher accuracy than the corresponding singular-model, and can be applied to analyze dam deformation.
作者
向亚红
张峰
邓念武
谢雨航
XIANG Ya-hong;ZHANG Feng;DENG Nian-wu;XIE Yu-hang(Hubei Flood Control and Drought Relief Mobile Rescue Corps,Wuhan 430064,Hubei Province,China;School of Water Resources and Hydropower Engineering,Wuhan University,Wuhan 430072,Hubei Province,China)
出处
《中国农村水利水电》
北大核心
2023年第1期185-188,193,共5页
China Rural Water and Hydropower
基金
国家自然科学基金资助项目(51278387)。
关键词
变形分析
大坝
分形插值
支持向量机
deformation analysis
dam
fractal interpolation
support vector machine
