摘要
利用日本KiK-net台网提供的407个台站的30952条地震动记录,提出了一种基于BP神经网络的场地等效剪切波速比变化预测模型。模型采用了均方误差函数及Adam优化算法,由3个输入参数、5个隐藏神经元及1个输出参数组成。输入参数为地面峰值加速度PGA、Arias烈度I_(a)及场地剪切波速V_(S30),输出为场地等效剪切波速比(V_(S r))。研究结果表明:该神经网络模型残差对于各输入变量整体呈现出无偏的特性,在大部分的软硬场地中均有较好的预测性能,该模型预测得到的PGA关于V_(S30)的相关系数曲线与用传统的最小二乘法回归得到的函数曲线相比,其相关系数有更好的表现。该模型预测曲线显示,B类场地在PGA达到175 cm/s^(2)时,场地剪切波速下降5%,D、E类场地在PGA达到140 cm/s^(2)时,场地剪切波速下降5%,多数场地的非线性阈值为50~100 cm/s^(2)。PGA在该网络模型中占据着较高的权重,为场地等效剪切波速变化的最主要控制参数。该网络模型捕捉到场地等效剪切波速比随PGA的增大有下降的趋势,而较为松软的D、E类场地受PGA影响更大,下降幅度更大。
In this paper,a total of 30952 records from 407 stations of the Japanese KiK-net is used to propose a prediction model for the change of equivalent shear wave velocity ratio based on BP neural network.The model adopts the mean square error function and the Adam optimization algorithm,consists of three inputs,five hidden neurons and one output.The input parameters are Peak Ground Acceleration(PGA),Arias intensity(I_(a))and site V_(S30).The output parameter is site equivalent shear wave velocity ratio(V_(Sr)).The research shows that the residual error of the network model is unbiased for each input variable,and has good prediction performance in many kinds of sites.Compared with the function curve of the traditional least-square method,the neural network model has a relatively better performance.In the prediction curve of the network model,the shear wave velocity of the site of Class B decreases by 5%when the PGA reaches about 175 cm/s^(2),and the shear wave velocity of the sites of Class D and E decreases by 5%when the PGA reaches about 140 cm/s^(2).The nonlinear threshold of most sites is between 50~100 cm/s^(2).PGA occupies a high weight in the network model and is the main controlling parameter of the site equivalent shear wave velocity change.The network model captures that the equivalent shear wave velocity ratio of the site has a downward trend with the increase of PGA.At the same time,it shows that the Class D and E sites are greatly affected by PGA,and the declineing range is larger.
作者
苏闻浩
刘启方
SU Wenhao;LIU Qifang(Suzhou University of Science and Technology,Key Laboratory of Structure Engineering of Jiangsu Province,Suzhou 215009,Jiangsu,China)
出处
《地震研究》
CSCD
北大核心
2024年第2期280-289,共10页
Journal of Seismological Research
基金
国家自然科学基金项目(51978434)。
关键词
神经网络
等效剪切波速
场地非线性
参数预测
地表峰值加速度
neural network
equivalent shear wave velocity
site nonlinearity
parameter prediction
peak ground acceleration