砂土地震液化判别的支持向量机多分类模型
|
摘要
砂土地震液化判别对指导水利工程的设计和施工具有非常重要的意义。本文基于支持向量机分类算法,分析了影响砂土液化的主要因素,建立了砂土液化预测的支持向量机模型。在此模型中,选取地震烈度、标准贯入击数、平均粒径、相对密度和上覆有效压力5个指标作为主要评价影响因素,同时将液化程度划分为不液化、轻度液化、中等液化和严重液化4个等级,进而使其评判结果更为细化。以砂土地震实测数据作为学习样本进行训练,建立相应判别函数对待判样本进行分类。通过算例分析,表明文中方法对砂土液化评判的合理性与有效性,可以在实际工程中推广。
The identification of sand seismic liquefaction is significant in the hydraulic design and construction.In this work,a support vector machine(SVM) model is established with a SVM classification algorithm and the major factors that influence sand seismic liquefaction,such as earthquake intensity,standard penetration number,mean diameter,relative density and effective overburden pressure.To improve the evaluation accuracy,liquefaction is divided into three grades of no,medium and serious liquefaction,and the discriminate functions are obtained by training a large sample of sand seismic liquefactions.Application to sand soil liquefaction of practical projects shows a success and effectiveness of the proposed method.
The identification of sand seismic liquefaction is significant in the hydraulic design and construction.In this work,a support vector machine(SVM) model is established with a SVM classification algorithm and the major factors that influence sand seismic liquefaction,such as earthquake intensity,standard penetration number,mean diameter,relative density and effective overburden pressure.To improve the evaluation accuracy,liquefaction is divided into three grades of no,medium and serious liquefaction,and the discriminate functions are obtained by training a large sample of sand seismic liquefactions.Application to sand soil liquefaction of practical projects shows a success and effectiveness of the proposed method.
引文
[1]薛新华,张我华,刘红军.基于遗传神经网络的地震砂土液化判别研究[J].西北地震学报,2006,28(1):42～45.XUE Xinhua,ZHANG Wohua,LIU Hongjun.Research on sand liquefaction based on the genetic neural network[J].NorthwesternSeismological Journal,2006,28(1):42～45.(in Chinese)
[2]陈新民,罗国煜.地震砂土液化可能性的非确定性灰色预测方法[J].桂林工学院学报,1997,17(2):106～109.CHEN Xinmin,LUO Guoyu.Indeterminate gray prediction method of possibility of sand liquefaction during earthquake[J].Journalof Guilin Institute of Technology,1997,17(2):106～109.(in Chinese)
[3]翁焕学.砂土地震液化模糊综合评判实用方法[J].岩土工程学报,1993,15(2):74～79.WENG Huanxue.Saturated sand liquefaction potential estimation method based on fuzzy comprehensive evaluation[J].ChineseJournal Geotechnical Engineering,1993,15(2):74～79.(in Chinese)
[4]金志仁.距离判别分析方法的砂土液化预测模型及应用[J].岩土工程学报,2008,30(5):776～780.Jin zhiren.Prediction of sand liquefaction based on discriminant analysis and its application[J].Chinese Journal GeotechnicalEngineering,2008,30(5):776～780.(in Chinese)
[5]夏建中,罗战友,龚晓南,等.基于支持向量机的砂土液化预测模型[J].岩石力学与工程学报,2005,24(22):4139～4144.XIA Jianzhong,LUO Zhanyou,GONG Xiaonan,et al.Support vector machine model for predicting sand liquefaction[J].ChineseJournal of Rock Mechanics and Engineering,2005,24(22):4139～4144.(in Chinese)
[6]师旭超,范量,韩阳.基于支持向量机方法的砂土地震液化分析[J].河南科技大学学报(自然科学版),2004,25(3):74～76.SHI Xuchao,FAN Liang,HAN Yang.Analysis on sand seismic liquefaction on support vector machine[J].Journal of HenanUniversity of science technology,2004,25(3):74～76.(in Chinese)
[7]李志雄.基于最小二乘支持向量机的砂土液化预测方法[J].西北地震学报,2007,29(2):133～136.LI Zhixiong.Research on sand liquefaction based on the LS support vector machine[J].Northwestern Seismological Journal,2007,29(2):133～136(in Chinese)
[8]Vapnik V.统计学习理论的本质[M].张学工(译).北京:清华大学出版社,2000.Vapnik V.The nature of statistical learning theory[M].ZHNANG Xuegong(Translator).Beijing:Tsinghua University Press 2004.(in Chinese)
[9]Burge C J C.A tutorial on support vector machines for pattern recognition[J].Data Mining and Knowledge Discovery,1998.(2):121～167.
[10]Engin AVCi.Selecting of the optimal feature subset and kernel parameters in digital modulation classification by using geneticsalgorithm support vector machine[J].Expert Systems with Application,2009,36(1):1391～1402.
[11]苏金明.MATLAB工具箱应用[M].北京:电子工业出版社,2004.SU Jinming.The application of toolbox in MATLAB[M].Beijing:Electronics Industry Press,2004.(in Chinese)
[2]陈新民,罗国煜.地震砂土液化可能性的非确定性灰色预测方法[J].桂林工学院学报,1997,17(2):106～109.CHEN Xinmin,LUO Guoyu.Indeterminate gray prediction method of possibility of sand liquefaction during earthquake[J].Journalof Guilin Institute of Technology,1997,17(2):106～109.(in Chinese)
[3]翁焕学.砂土地震液化模糊综合评判实用方法[J].岩土工程学报,1993,15(2):74～79.WENG Huanxue.Saturated sand liquefaction potential estimation method based on fuzzy comprehensive evaluation[J].ChineseJournal Geotechnical Engineering,1993,15(2):74～79.(in Chinese)
[4]金志仁.距离判别分析方法的砂土液化预测模型及应用[J].岩土工程学报,2008,30(5):776～780.Jin zhiren.Prediction of sand liquefaction based on discriminant analysis and its application[J].Chinese Journal GeotechnicalEngineering,2008,30(5):776～780.(in Chinese)
[5]夏建中,罗战友,龚晓南,等.基于支持向量机的砂土液化预测模型[J].岩石力学与工程学报,2005,24(22):4139～4144.XIA Jianzhong,LUO Zhanyou,GONG Xiaonan,et al.Support vector machine model for predicting sand liquefaction[J].ChineseJournal of Rock Mechanics and Engineering,2005,24(22):4139～4144.(in Chinese)
[6]师旭超,范量,韩阳.基于支持向量机方法的砂土地震液化分析[J].河南科技大学学报(自然科学版),2004,25(3):74～76.SHI Xuchao,FAN Liang,HAN Yang.Analysis on sand seismic liquefaction on support vector machine[J].Journal of HenanUniversity of science technology,2004,25(3):74～76.(in Chinese)
[7]李志雄.基于最小二乘支持向量机的砂土液化预测方法[J].西北地震学报,2007,29(2):133～136.LI Zhixiong.Research on sand liquefaction based on the LS support vector machine[J].Northwestern Seismological Journal,2007,29(2):133～136(in Chinese)
[8]Vapnik V.统计学习理论的本质[M].张学工(译).北京:清华大学出版社,2000.Vapnik V.The nature of statistical learning theory[M].ZHNANG Xuegong(Translator).Beijing:Tsinghua University Press 2004.(in Chinese)
[9]Burge C J C.A tutorial on support vector machines for pattern recognition[J].Data Mining and Knowledge Discovery,1998.(2):121～167.
[10]Engin AVCi.Selecting of the optimal feature subset and kernel parameters in digital modulation classification by using geneticsalgorithm support vector machine[J].Expert Systems with Application,2009,36(1):1391～1402.
[11]苏金明.MATLAB工具箱应用[M].北京:电子工业出版社,2004.SU Jinming.The application of toolbox in MATLAB[M].Beijing:Electronics Industry Press,2004.(in Chinese)
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心