基于GA-SVR的建筑物液化震陷预测方法
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
根据影响建筑物液化震陷量的9个主要因素,建立了基于遗传算法和回归型支持向量机(support vector regression,SVR)的建筑物液化震陷量预测模型.该模型通过有限的60组实例数据学习,利用遗传算法自动确定ν-SVR的最优模型参数,建立了建筑物液化震陷量与其各种影响因素之间的非线性关系.运用所建立的模型对另外10个实例进行推广预测,取得了较好的效果,与实际液化震陷量的平均相对误差在5%左右,显示了该方法的有效性和可行性.同时,本文的思路和方法也可推广至建筑结构的震害预测.
According to the nine main factors,which affect building settlements due to earthquake liquefaction,a method is proposed to predict building settlements due to earthquake liquefaction based on support vector regression(ν-SVR)and genetic algorithm(GA).Since the modeling of this method uses the genetic algorithm to automatically determine the optimal parameters of ν-SVR,and it is directly based on 60 real measured seismic settlement samples,the nonlinear relation between building settlements and the various factors is established.The other 10 examples are predicated by the training model to achieve good results with the average relative error of around 5% compared with the actual building settlements.The effectiveness and feasibility have been proven.The analytic method and process discussed in this paper can also be applied to the seismic damage prediction of other structures of different forms.
引文
[1]何玉敖,何亚东.基于人工神经网络的液化震陷预估方法[J].土木工程学报,1999,32(1):71-74.He Yu-ao,HE Ya-dong.A neural networks based on method for evaluation building settlements due to earthquake liquefaction[J].China Civil Engineering Journal,1999,32(1):71-74.(in Chinese)
    [2]ZHANG Zhen-zhong,ZHANG Dong-li,LIU Hong-mei.Comprehensive study on seismic subsidence of loess under earthquake[J].Northwestern Seismological Journal,2005,27(1):36-41.
    [3]陈国兴.岩土地震工程学[M].北京:科学出版社,2007.
    [4]何广讷,杨斌.计算软土震陷的综合应变势法[G]∥第五届全国土动力学学术会议论文集.大连:大连理工大学出版社,1998:215-218.
    [5]章在庸.地震危险性分析及其应用[M].上海:同济大学出版社,1996.
    [6]邓乃扬,田英杰.数据挖掘中的新方法——支持向量机[M].北京:科学出版社,2004.
    [7]王威,马东辉,苏经宇,等.基于RS-SVM的地下管线震害预测方法研究[J].应用基础与工程科学学报,2009,17(2):274-280.WANG Wei,MA Dong-hui,SU Jing-yu,et al.Study on predicting method for earthquake damage to underground pipelinessystem based on rough set and support vector machine[J].Journal of Basic Science and Engineering,2009,17(2):274-280.(in Chinese)
    [8]SCHOLKOPF B,SMOLA A,WILLIAMSON R C,et al.New support vector algorithms[J].Neural Computation,2000,12(5):1207-1245.
    [9]赵洪波,冯夏庭.支持向量机函数拟合在边坡稳定性估计中的应用[J].岩石力学与工程学报,2003,22(2):241-245.ZHAO Hong-bo,FENG Xia-ting.Application of support vector machines function fitting in slope stability evaluation[J].Chinese Journal of Rock Mechanics and Engineering,2003,22(2):241-245.(in Chinese)
    [10]杨志民,刘广利.不确定性支持向量机原理及应用[M].北京:科学出版社,2007.
    [11]雷英杰,张善文,李续武,等.MATLAB遗传算法工具箱及应用[M].西安:西安电子科技大学出版社,2005.
    [12]杜京义,侯媛彬.基于遗传算法的支持向量回归机参数选取[J].系统工程与电子技术,2006,28(9):1430-1433.DU Jing-yi,HOU Yuan-bin.Parameters selection of support vector regression by genetic algorithms[J].Systems Engineeringand Electronics,2006,28(9):1430-1433.(in Chinese)
    [13]刘惠珊,张在明.地震区的场地与地基基础[M].北京:中国建筑工业出版社,1994.
    [14]刘颖,谢君斐.砂土震动液化[M].北京:地震出版社,1984.
    [15]刘勇健.人工神经网络原理在建筑物震陷预测中的应用[J].地震研究,2001,24(3):262-266.LIU Yong-jian.The application of principle of artificial neural networks to prediction of building settlements due to earthquakeliquefaction[J].Journal of Seismological Research,2001,24(3):262-266.(in Chinese)

版权所有:© 2021 中国地质图书馆 中国地质调查局地学文献中心