摘要
针对高层建筑物沉降变形的准确预测对保障人民生命财产安全意义重大。本文充分发挥小波分解在数据处理领域以及支持向量机(Support Vector Machine,SVM)模型、AR模型在数据预测中的优势,提出了一种基于小波分解的SVM-AR组合预测模型。该组合模型实现建筑物沉降预测的流程为:首先对建筑物沉降监测序列进行小波分解,得到不同频段的分量;其次使用SVM模型对低频分量进行预测,使用自相关性强的AR模型对平稳序列的高频分量进行预测;最后重构不同分量预测结果得到最终预测结果。将本文提出组合预测模型应用于实际高层建筑物沉降预测中,并与单一的SVM模型、AR模型预测结果进行对比,结果表明,本文提出的组合预测模型在小样本、低信噪比条件下表现出了更好的预测性能,能够对高层建筑物沉降进行准确模拟与预报。
The accurate prediction of settlement deformation of high-rise buildings is of great significance to ensure the safety of people's lives and property.This paper gives full play to the advantages of wavelet decomposition in the field of data processing and support vector machine(SVM)model and AR model in data prediction,and proposes a SVM-AR combined prediction model based on wavelet decomposition.The process of building settlement prediction based on the combined model is as follows:Firstly,the building settlement monitoring sequence is decomposed by wavelet to obtain the components of different frequency bands;Secondly,SVM model is used to predict the low-frequency component,and AR model with strong autocorrelation is used to predict the high-frequency component of stationary series;Finally,the final prediction results are obtained by reconstructing the prediction results of different components.The combined prediction model proposed in this paper is applied to the actual settlement prediction of high-rise buildings,and compared with the prediction results of single SVM model and AR model.The results show that the combined prediction model proposed in this paper shows better prediction performance under the conditions of small samples and low signal-to-noise ratio,and can accurately simulate and predict the settlement of high-rise buildings.
作者
孙策
张杰
叶送
杨小央
SUN Ce;ZHANG Jie;YE Song;YANG Xiaoyang(Zhejiang Institute of Surveying and Mapping Science and Technology,Hangzhou 311100,China)
出处
《测绘与空间地理信息》
2023年第10期221-224,共4页
Geomatics & Spatial Information Technology
关键词
高层建筑物
沉降预测
支持向量机
AR模型
组合预测模型
high-rise buildings
settlement prediction
support vector machine
AR model
combined forecasting model
