AFSs-RBF神经网络模型在轻亚黏土地震液化判别中应用研究
|
摘要
以自适应模糊系统AFSs为基础,运用径向基高斯函数RBF所建立的AFSs-RBF神经网络模型能够同时容纳模糊系统的推理功能和自适应性,动态调节隐节点数即模糊规则数,具有广泛的适用性.将这种模型应用于轻亚黏土地震液化评价中,选择震中距、上覆有效应力、黏粒含量、标贯击数、地下水位、循环应力比等6个与地震和场地条件有关的影响因子作为网络输入参数,对于轻亚黏土场地的液化势判别具体地建立了模糊神经网络模型AFSs-RBF.以唐山7.8级地震中天津某地区的轻亚黏土液化数据为训练样本,经验证和应用表明,这种AFSs-RBF网络具备更高的自适应性和非线性映射能力.
The adaptive fuzzy systems(AFSs) are incorporated with the radial basic function(RBF) to develop an integrated neural network model AFSs-RBF.In this model,the number of the hidden layers or units,i.e.fuzzy rule number,can be dynamically adjusted and widely used in engineering practice.This model is applied to evaluation of earthquake-induced liquefaction potential in light loam sites.The six parameters related to earthquake and site condition which are composed of epicentral distance of earthquake,effective overburden stress,clay percentage,SPT-blow counts,water table,cyclic stress ratio are chosen to develop the AFSsRBF neural network model with six-index input.The proposed model is applied to the classification of liquefaction potential of sites located in Tianjin area occurring in the Tangshan earthquake with the magnitude of 7.8.It is shown that such an AFSs-RBF network model is capable to offer a more rational prediction of liquefaction potentials of light loam site compared with those by conventional artificial neural network methods.
The adaptive fuzzy systems(AFSs) are incorporated with the radial basic function(RBF) to develop an integrated neural network model AFSs-RBF.In this model,the number of the hidden layers or units,i.e.fuzzy rule number,can be dynamically adjusted and widely used in engineering practice.This model is applied to evaluation of earthquake-induced liquefaction potential in light loam sites.The six parameters related to earthquake and site condition which are composed of epicentral distance of earthquake,effective overburden stress,clay percentage,SPT-blow counts,water table,cyclic stress ratio are chosen to develop the AFSsRBF neural network model with six-index input.The proposed model is applied to the classification of liquefaction potential of sites located in Tianjin area occurring in the Tangshan earthquake with the magnitude of 7.8.It is shown that such an AFSs-RBF network model is capable to offer a more rational prediction of liquefaction potentials of light loam site compared with those by conventional artificial neural network methods.
引文
[1]石兆吉,郁寿松,王余庆,等.饱和轻亚黏土地基液化可能性判别[J].地震工程与工程振动,1984,4(3):71-81
[2]何广讷,郭莹.粉土液化的模糊综合评判方法[J].地震工程与工程振动,1988,8(3):48-56
[3]陈国兴,张克绪,谢君斐.液化判别的可靠性研究[J].地震工程与工程振动,1991,11(2):85-95
[4]蔡煜东,宫家文,姚林声.砂土液化预测的人工神经网络模型[J].岩土工程学报,1993(6):53-58
[5]GOH A T C.Seismic liquefaction potential assessedby neural networks[J].J Geotech Eng,ASCE,1994,120(9):1467-1480
[6]GOH A T C.Neural-network modeling of CPTseismic liquefaction data[J].J Geotech and Geoenviron Eng,ASCE,1996,122(1):70-73
[7]汪明武,李丽,章杨松,等.混合遗传算法在砂土液化势评价中的应用[J].合肥工业大学学报,2002,25(4):505-509
[8]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
[9]张晓晖,吴亚萍,尚伟宏,等.利用模糊神经网络进行砂土液化势评判[J].工程地质学报,2001,9(2):209-213
[10]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
[11]CHEN S G,HU R F,CHANG Y J,et al.Fuzz-ART neural networks for predicting Chi-Chiearthquake induced liquefaction in Yuan-Lin area[J].J Marine Sci and Technol,2002,10(1):21-31
[12]闻新,周露.MATLAB神经网络应用设计[M].北京:科学出版社,2000
[13]刘恢先.唐山大地震震害[M].北京:地震出版社,1986
[14]郭莹.轻亚黏土液化的能量分析方法[D].大连:大连理工大学,1987
[15]TOKIMATSU K,YOSHIMI Y.Empiricalcorrelation of soil liquefaction based on SPTN-value and fines content[J].Soils and Foundations,1983,23(4):56-74
[16]金富,祁冰,贺可强.轻亚黏土液化机制的动三轴特性与模糊综合评价[J].水文地质工程地质,1992,19(5):38-41
[17]潘品蒸,闫俊爱.天津滨海区轻亚黏土地震液化研究——模糊模式识别的应用[J].地质灾害与防治,1990,1(4):29-37
[18]魏海坤.神经网络结构设计的理论与方法[M].北京:国防工业出版社,2005
[19]URAL D N,SAKA H.Liquefaction assessment byartificial neural networks[J/BL].Electronic Journal of Geotechnical Engineering.[1998-03-01].http://www.ejge.com/1998/Ppr9803/Ppr9803.htm
[2]何广讷,郭莹.粉土液化的模糊综合评判方法[J].地震工程与工程振动,1988,8(3):48-56
[3]陈国兴,张克绪,谢君斐.液化判别的可靠性研究[J].地震工程与工程振动,1991,11(2):85-95
[4]蔡煜东,宫家文,姚林声.砂土液化预测的人工神经网络模型[J].岩土工程学报,1993(6):53-58
[5]GOH A T C.Seismic liquefaction potential assessedby neural networks[J].J Geotech Eng,ASCE,1994,120(9):1467-1480
[6]GOH A T C.Neural-network modeling of CPTseismic liquefaction data[J].J Geotech and Geoenviron Eng,ASCE,1996,122(1):70-73
[7]汪明武,李丽,章杨松,等.混合遗传算法在砂土液化势评价中的应用[J].合肥工业大学学报,2002,25(4):505-509
[8]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
[9]张晓晖,吴亚萍,尚伟宏,等.利用模糊神经网络进行砂土液化势评判[J].工程地质学报,2001,9(2):209-213
[10]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
[11]CHEN S G,HU R F,CHANG Y J,et al.Fuzz-ART neural networks for predicting Chi-Chiearthquake induced liquefaction in Yuan-Lin area[J].J Marine Sci and Technol,2002,10(1):21-31
[12]闻新,周露.MATLAB神经网络应用设计[M].北京:科学出版社,2000
[13]刘恢先.唐山大地震震害[M].北京:地震出版社,1986
[14]郭莹.轻亚黏土液化的能量分析方法[D].大连:大连理工大学,1987
[15]TOKIMATSU K,YOSHIMI Y.Empiricalcorrelation of soil liquefaction based on SPTN-value and fines content[J].Soils and Foundations,1983,23(4):56-74
[16]金富,祁冰,贺可强.轻亚黏土液化机制的动三轴特性与模糊综合评价[J].水文地质工程地质,1992,19(5):38-41
[17]潘品蒸,闫俊爱.天津滨海区轻亚黏土地震液化研究——模糊模式识别的应用[J].地质灾害与防治,1990,1(4):29-37
[18]魏海坤.神经网络结构设计的理论与方法[M].北京:国防工业出版社,2005
[19]URAL D N,SAKA H.Liquefaction assessment byartificial neural networks[J/BL].Electronic Journal of Geotechnical Engineering.[1998-03-01].http://www.ejge.com/1998/Ppr9803/Ppr9803.htm
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