基于BP神经网络的砂土液化影响因素的综合评估

英文篇名：Integrated Evaluation of Factors to Affect Liquefaction of Sandy Soil Based on BP Neural Network
中文刊名：华南理工大学学报(自然科学版)
英文刊名：Journal of South China University of Technology(Natural Science Edition)
作者：潘健 ; 刘利艳 ; 林慧常
英文作者：Pan Jian~1 Liu Li-yan~1 Lin Hui-chang~2(1.School of Architecture and Civil Engineering ; South China Univ.of Tech. ; Guangzhou 510640 ; Guangdong ; China ; 2.Maoming Quality Supervision Checkpoint of Constructing Engineering ; Maoming 525000 ; Guangdong ; China)
中文关键词：砂土 ; 液化 ; 影响因素 ; 评估 ; 神经网络 ; Vogl快速算法
英文关键词：sand ; liquefaction ; influencing factor ; evaluation ; neural network ; Vogl fast algorithm
出版日期：2006-11-30
机构：华南理工大学建筑学院,华南理工大学建筑学院,茂名市建设工程质量监督检测站广东广州510640,广东广州510640,广东茂名525000
年：2006
期：11
出版单位：华南理工大学学报(自然科学版)

摘要

为了充分考虑影响砂土液化的多种因素,选取不同的参数组合,建立不同的砂土液化判别BP神经网络模型,编写了饱和砂土液化判别BP神经网络程序SLV,并根据现场实测资料进行计算和分析.结果表明,地震作用是液化的直接原因,砂土处于饱和状态是液化的前提条件,影响液化的主要因素包括标准贯入锤击数、砂土不均匀系数以及地震剪应力比.文中建立的BP神经网络模型具有高度的分类和识别能力,可用于评估砂土液化的影响因素.
In order to investigate various factors to affect the liquefaction of sandy soil,different BP neural network models for liquefaction evaluation were established based on different combinations of the input neurons.A BP neural network-based program,namely SLV,was then presented for the liquefaction evaluation of saturated sandy soil.Some comparison analyses were finally carried out according to the results of field observation.It is shown that the earthquake action is a direct cause of the liquefaction,that the saturation state of sandy soil is the precondition of the liquefaction,and that the standard penetration blow-count,the non-uniformity coefficient and the shearing stress ratio are the main influencing factors of the liquefaction.Moreover,it is indicated that the proposed BP neural network model can effectively evaluate the factors to affect the liquefaction of sandy soil due to its strong classifying and distinguishing ability.

引文

[1]叶洪东,王志军,别慧中,等.对《建筑抗震设计规范》中地震液化判别公式的讨论[J].河北建筑科技学院学报,2003,20(4):36-38.Ye Hong-dong,W ang Zh i-jun,B ie Hu i-zhong,et al.D is-cussion on the prob lem in the dec isive equation of groundliquefaction of the arch itecture anti-se ism ic codes[J].Journal of Hebe i Institute of Arch itectural Sc ience andTechnology,2003,20(4):36-38.
    [2]陈国兴,张克绪,谢君斐.以剪切波速为指标的液化判别方法及其适用性[J].哈尔滨建筑大学学报,1996,29(1):97-103.Chen Guo-xing,Zhang Ke-xu,X ie Jun-fe i.M ethods of li-quefaction potential pred iction w ith shearwave veloc ity asa field index and the adaptab ility[J].Journal of Harb inUn iversity ofArch itecture and Engineering,1996,29(1):97-103.
    [3]Juang C H,Yuan H,Lee D H,et al.S imp lified cone pene-tration test-based m ethod for evaluating liquefaction resis-tance of soils[J].J Geotech Engrg,ASCE,2003,129(1):66-80.
    [4]张克绪,谢君斐.土动力学[M].北京:地震出版社,1989.
    [5]汪明武,罗国煜.可靠性分析在砂土液化势评价中的应用[J].岩土工程学报,2000,22(5):542-544.W ang M ing-wu,Luo Guo-yu.App lication of reliab ilityanalysis to assessm ent of sand liquefaction potential[J].Ch inese Journal of Geotechn ical Engineering,2000,22(5):542-544.
    [6]杨健,陈庆寿.砂土液化影响因素及其判别方法[J].西部探矿工程,2004(2):1-2.Yang Jian,Chen Q ing-shou.A ffecting factors and d istin-gu ish ing m ethods of sandy soil liquefaction[J].W est-Ch ina Exp loration Engineering,2004(2):1-2.
    [7]董长虹.M atlab神经网络与应用[M].北京:国防工业出版社,2005.
    [8]张乃尧,阎平凡.神经网络与模糊控制[M].北京:清华大学出版社,1998.
    [9]焦李成.神经网络计算[M].西安:西安电子科技大学出版社,1995:35-42.
    [10]刘恢先.唐山大地震震害(一)[M].北京:地震出版社,1985.
    [11]Seed H B,Idriss IM.S imp lified procedure for evaluatingsoil liquefaction potential[J].Journal of the Soil M e-chan ics and Foundations D ivision,ASCE,1971,97(9):1 249-1 273.
    [12]林慧常.砂土地震液化评价的改进方法及其在工程中的应用[D].广州:华南理工大学建筑学院,2005.