基于二值Logistic回归模型的砂土液化指标敏感性分析
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
将二值Logistic回归模型应用到砂土液化预测中,以国内外173组样本数据作为研究对象,通过相关性分析选择震级M、有效应力σ′0、平均粒径D50、修正的CPT锥尖阻力qc1和地震剪应力比SSR5个指标作为敏感性分析指标,对砂土液化指标的敏感性进行了分析。结果表明:二值Logistic回归模型预测准确率达到了90.8%,其概率表达式可用于砂土液化预测;各指标的敏感性排序为M>qc1>σ′0>D50≈SRR;σ′0和qc1指标与砂土液化的相对危险性呈负相关趋势,以qc1指标敏感性较大,M、D50、SRR指标与砂土液化的相对危险性呈正相关趋势,以M敏感性最大。
This paper adopts the binary logistic regression model in the prediction of soil liquefaction,selects173 groups of sample data from home and abroad as the research object to establish the binary logistic regression model,and chooses five indicators including earthquake magnitude M,the effective vertical stressσ′0,the mean grain size D50,the measured CPT tip resistance qc and the cyclic stress ratio SSR as the basic indicators for the prediction of soil liquefaction according to correlation analysis.Analysis results show that the binary logistic regression model has a good forecast accuracy of 90.8%,and its expression of probability of soil liquefaction can be used for the prediction of soil liquefaction.The ranking result of the sensitivity of indicators is M>qc1>σ′0>D50≈SRR.The indicators includingσ′0,qc1 are negatively correlated with the relative risk of soil liquefaction while M,D50,SRRare positively correlated with the relative risk of soil liquefaction.
引文
[1]陈建伟,苏经宇,苏幼坡.场地地震液化的主要影响因素分析[J].安全与环境工程,2013,20(4):18-22.
    [2]刘勇健.基于聚类-二叉树支持向量机的砂土液化预测模型[J].岩土力学,2008,29(10):2764-2768.
    [3]Lai S Y,Hsu S C,Hsieh M J.Discriminant model for evaluating soil liquefaction potential using cone penetration test data[J].Journal of Geotechnical and Geoenvironmental Engineering,2004,130(12):1271-1282.
    [4]陈国兴,李方明.基于径向基函数神经网络模型的砂土液化概率判别方法[J].岩土工程学报,2006,28(3):301-305.
    [5]林志红,项伟.基于贝叶斯正则化BP神经网络的砂土地震液化研究[J].安全与环境工程,2011,18(2):23-27.
    [6]薛新华,张我华,刘红军.砂土地震液化的模糊综合评判法[J].重庆建筑大学学报,2006,28(1):55-58.
    [7]金志仁.基于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.
    [8]Xue,X H,Yang,X G.Application of the adaptive neuro-fuzzy inference system for prediction of soil liquefaction[J].Natural Hazards,2013,67(2):901-917.
    [9]吴令云,吴家祺,吴诚鸥,等.MINITAB软件入门:最易学实用的统计分析教程[M].北京:高等教育出版社,2012.
    [10]Stark T D,Olson S M.Liquefaction resistance using CPT and field case histories[J].Journal of Geotechnical Engineering,1995,121(12):856-869.
    [11]Kayan R E,Mitchell J K,Seed R B,et al.Evaluation of SPT-,CPT-,and Shear Wave-based Methods for Liquefaction Potential Assessments Using Lorna Prieta Data[R].Buffalo,USA:National Center for Earthquake Engineering Research,1992:177-192.
    [12]袭炯良,郏剑宁,张扬.主成分改进的logistic回归模型方法在流行病学分析中的应用[J].中国热带医学,2005,5(2):207-209.
    [13]叶宗裕.关于多指标综合评价中指标正向化和无量纲化方法的选择[J].浙江统计,2003(4):24-25.
    [14]罗战友,龚晓南.基于经验的砂土液化灰色关联系统分析与评价[J].工业建筑,2002,32(11):36-39.

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