基于主成分分析和优化支持向量机的砂土地震液化预测  

Prediction of Seismic Liquefaction of Sand Based on Principal ComponentAnalysis and Optimized Support Vector Machine

作　　者：刘佩瑶 LIU Peiyao(College of International Education(Ural Institute),North China University of Water Resources and Electric Power,Zhengzhou 450045,China)

机构地区：[1]华北水利水电大学国际教育学院(乌拉尔学院),郑州450045

出　　处：《华北地震科学》2024年第3期35-41,49,共8页North China Earthquake Sciences

摘　　要：对影响砂土地震液化的9个影响因素进行主成分分析,提取了4个主成分,同时引入支持向量机建立了砂土地震液化预测模型,并结合工程实例,将预测结果与未进行主成分提取的优化支持向量机模型预测结果进行对比。结果表明:基于主成分分析和优化支持向量机的砂土地震液化预测模型精度更高,可以为震灾防治工作提供有效支撑。Seismic liquefaction of sand is a dynamic geological phenomenon caused by the joint action of multipleinfluencing factors,and it is difficult to accurately distinguish the seismic liquefaction state of sand by conventionalmodels.In this paper,the principal component analysis was carried out on the selected nine influencing factors of sandseismic liquefaction,and four principal components were extracted.At the same time,the support vector machine wasintroduced to establish the prediction model of sand seismic liquefaction.Combined with an engineering example,theprediction results were compared with the prediction results of optimized support vector machine model withoutprincipal component extraction.The results showed that the prediction model of sand seismic liquefaction based onprincipal component analysis and optimized support vector machine had higher accuracy,and could provide effectivesupport for earthquake disaster prevention and control work.

关 键 词：砂土液化 主成分分析 支持向量机 

分 类 号：P315.93[天文地球—地震学]