岩质边坡结构面参数反演的免疫遗传算法
|
摘要
基于均匀设计、有限元法、人工神经网络和免疫遗传算法建立了新的岩质边坡结构面参数的反演方法.按照均匀设计要求,确定数值模拟方案;用有限元程序计算出相应的神经网络训练样本,建立边坡变形的神经网络预测模型,再利用免疫遗传算法进行反演分析,其中反演过程适应度的计算则采用已训练好的神经网络预测来替代有限元数值仿真,大大缩短了计算时间.通过实际工程的算例分析,反演结果比较理想.
A new backward analysis method for mechanical parameters of fault surface in slope was developed based on uniform testing design,finite element method,artificial neural network and immunization-genetic algorithm.According to uniform testing design,the value levels of the mechanical parameters were chosen,and simulation schemes were arranged;the related analytical samples for neural network were given by FEM calculations.Thus,a BP neural network which was used to forecast displacement of the slope's character points was erected and trained.The physical and mechanical parameters could be analyzed backwards by immunization-genetic algorithm.In this algorithm the trained BP neural network was used to calculating the fitness value instead of the FEM method and the calculation time was much reduced.An actual engineering using immunization-genetic algorithm to solve the mechanical parameters of fault surface was analyzed.The result is reasonable and the backward analysis method is feasible and accurate.
A new backward analysis method for mechanical parameters of fault surface in slope was developed based on uniform testing design,finite element method,artificial neural network and immunization-genetic algorithm.According to uniform testing design,the value levels of the mechanical parameters were chosen,and simulation schemes were arranged;the related analytical samples for neural network were given by FEM calculations.Thus,a BP neural network which was used to forecast displacement of the slope's character points was erected and trained.The physical and mechanical parameters could be analyzed backwards by immunization-genetic algorithm.In this algorithm the trained BP neural network was used to calculating the fitness value instead of the FEM method and the calculation time was much reduced.An actual engineering using immunization-genetic algorithm to solve the mechanical parameters of fault surface was analyzed.The result is reasonable and the backward analysis method is feasible and accurate.
引文
[1]杜时贵.岩体结构面抗剪强度经验估算[M].北京:地震出版社,2005.Du Shigui.Shear strength estimation-method of rock joint[M].Beijing:Earthquake Press,2005.
[2]冯夏庭,杨成祥.智能岩石力学(2)——参数与模型的智能辨识[J].岩石力学与工程学报,1999,18(3):350-353.Feng Xiating,Yang Chengxiang.Intelligent rock mechanics(2):intelligent recognition of input parameters and constitutivemodels[J].Chinese Journal of Rock Mechanics and Engineering,1999,18(3):350-353.
[3]方开泰.均匀设计与均匀设计表[M].北京:科学出版社,1994.Fang Kaitai.Unifrom design and uniform design table[M].Beijing:Science Press,1994.
[4]樊琨,刘宇敏,张艳华.基于人工神经网络的岩土工程力学参数反分析[J].河海大学学报,1998,26(4):98-102.Fan Kun,Liu Yunmin,Zhang Yanhua.Inverse analysis of rock soil mechanics parameters based on neural network[J].Jour-nal of Hehai University,1998,26(4):98-102.
[5]葛增杰,李锡夔.深基坑开挖工程多层土体物性参数识别的BP方法[J].大连理工大学学报,2000,40(3):271-275.Ge Zengjie,Li Xikui.Multi-layer of soil parameters to identify the object of BP for the deep excavation engineer[J].Journalof Dalian University of Technology,2000,40(3):271-275.
[6]孙海涛,吴限.深基坑工程变形预报神经网络法的初步研究[J].岩土力学,1998,19(4):63-68.Sun Haitao,Wu Xian.Study on neural networks method of deformation prediction of foundation pit based on artificial[J].Rock and Soil Mechanics,1998,19(4):63-68.
[7]李立新,王建党,李造鼎.神经网络模型在非线性位移反分析中的应用[J].岩土力学,1997,18(2):62-66.Li Lixin,Wang Jiandang,Li Zaoding.Application of neural network model in non-linear displacement back analysis[J].Rock and Soil Mechanics,1997,18(2):62-66.
[8]Sambridge M.Geophysical inversion with a neighbourhood algorithm-Searching a parameter space[J].Geophys.J.Int.,1999,138:479-494.
[9]姚磊华,李竞生.综合改进的遗传算法反演三维地下水流模型参数[J].岩石力学与工程学报,2004,23(4):625-630.Yao Leihua,Li Jingsheng.Parameter identification of 3D groundwater flowmodel with improved genetic algorithm[J].Chi-nese Journal of Rock Mechanics and Engineering,2004,23(4):625-630.
[10]吴祥松,朱合华,叶飞岩.土工程参数反分析的可辨识性研究[J].地下空间与工程学报,2006,2(3):377-379.Wu Xiangsong,Zhu Hehua,Ye Feiyan.Research on identification of the parameter in the back analysis of geotechnical engi-neering problems[J].Chinese Journal of Underground Space and Engineering,2006,2(3):377-379.
[11]丁永生,任立红.人工免疫系统:理论与应用[J].模式识别与人工智能,2000,13(1):52-59.Ding Yongsheng,Ren Lihong.Artificial immune systems:theory and applications[J].Pattern Recognition and ArtificialIntelligence,2000,13(1):52-59.
[12]高玮,郑颖人,冯夏庭.岩土本构模型识别的仿生算法研究[J].岩土力学,2004,25(1):31-36.Gao Wei,Zheng Yingren,Feng Xiating.Study on bionics algorithm for geo-material constitutive model identification[J].Rock and Soil Mechanics,2004,25(1):31-36.
[2]冯夏庭,杨成祥.智能岩石力学(2)——参数与模型的智能辨识[J].岩石力学与工程学报,1999,18(3):350-353.Feng Xiating,Yang Chengxiang.Intelligent rock mechanics(2):intelligent recognition of input parameters and constitutivemodels[J].Chinese Journal of Rock Mechanics and Engineering,1999,18(3):350-353.
[3]方开泰.均匀设计与均匀设计表[M].北京:科学出版社,1994.Fang Kaitai.Unifrom design and uniform design table[M].Beijing:Science Press,1994.
[4]樊琨,刘宇敏,张艳华.基于人工神经网络的岩土工程力学参数反分析[J].河海大学学报,1998,26(4):98-102.Fan Kun,Liu Yunmin,Zhang Yanhua.Inverse analysis of rock soil mechanics parameters based on neural network[J].Jour-nal of Hehai University,1998,26(4):98-102.
[5]葛增杰,李锡夔.深基坑开挖工程多层土体物性参数识别的BP方法[J].大连理工大学学报,2000,40(3):271-275.Ge Zengjie,Li Xikui.Multi-layer of soil parameters to identify the object of BP for the deep excavation engineer[J].Journalof Dalian University of Technology,2000,40(3):271-275.
[6]孙海涛,吴限.深基坑工程变形预报神经网络法的初步研究[J].岩土力学,1998,19(4):63-68.Sun Haitao,Wu Xian.Study on neural networks method of deformation prediction of foundation pit based on artificial[J].Rock and Soil Mechanics,1998,19(4):63-68.
[7]李立新,王建党,李造鼎.神经网络模型在非线性位移反分析中的应用[J].岩土力学,1997,18(2):62-66.Li Lixin,Wang Jiandang,Li Zaoding.Application of neural network model in non-linear displacement back analysis[J].Rock and Soil Mechanics,1997,18(2):62-66.
[8]Sambridge M.Geophysical inversion with a neighbourhood algorithm-Searching a parameter space[J].Geophys.J.Int.,1999,138:479-494.
[9]姚磊华,李竞生.综合改进的遗传算法反演三维地下水流模型参数[J].岩石力学与工程学报,2004,23(4):625-630.Yao Leihua,Li Jingsheng.Parameter identification of 3D groundwater flowmodel with improved genetic algorithm[J].Chi-nese Journal of Rock Mechanics and Engineering,2004,23(4):625-630.
[10]吴祥松,朱合华,叶飞岩.土工程参数反分析的可辨识性研究[J].地下空间与工程学报,2006,2(3):377-379.Wu Xiangsong,Zhu Hehua,Ye Feiyan.Research on identification of the parameter in the back analysis of geotechnical engi-neering problems[J].Chinese Journal of Underground Space and Engineering,2006,2(3):377-379.
[11]丁永生,任立红.人工免疫系统:理论与应用[J].模式识别与人工智能,2000,13(1):52-59.Ding Yongsheng,Ren Lihong.Artificial immune systems:theory and applications[J].Pattern Recognition and ArtificialIntelligence,2000,13(1):52-59.
[12]高玮,郑颖人,冯夏庭.岩土本构模型识别的仿生算法研究[J].岩土力学,2004,25(1):31-36.Gao Wei,Zheng Yingren,Feng Xiating.Study on bionics algorithm for geo-material constitutive model identification[J].Rock and Soil Mechanics,2004,25(1):31-36.
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