索风营水电站地下洞室岩体力学参数的位移反分析
|
摘要
利用支持向量机和模拟退火算法对索风营地下洞室岩体的力学参数进行位移反分析,一方面支持向量机代替有限元计算提高了计算分析速度,另一方面用模拟退火算法代替传统的优化算法,避免优化过程中目标函数陷入局部极小值而无法继续寻优的状态,提高了反演的效率精度。利用反演得到的岩体力学参数进行有限元正分析所得位移与现场实测结果更加接近。
Parameters of rockmass of Suofengying Hydraulic Power Plant were derived from displacement back analysis based on the support vector machine and simulated annealing.Firstly the support vector machine was used to substitute the time-consuming finite element analysis,and secondly the simulated annealing was used for the optimization of objective function to avoid that the search fell in one of the minimums and could not go any further when the conventional mathematical optimization methods were employed.The displacement calculated by FEM with parameters obtained from back analysis was close to the measured value.
Parameters of rockmass of Suofengying Hydraulic Power Plant were derived from displacement back analysis based on the support vector machine and simulated annealing.Firstly the support vector machine was used to substitute the time-consuming finite element analysis,and secondly the simulated annealing was used for the optimization of objective function to avoid that the search fell in one of the minimums and could not go any further when the conventional mathematical optimization methods were employed.The displacement calculated by FEM with parameters obtained from back analysis was close to the measured value.
引文
[1]河海大学土木工程学院,国家电力公司贵阳勘测设计研究院.乌江索风营水电站右岸地下厂房洞室群围岩稳定三维有限元分析研究报告[R].2003.(School of Civil Engineering of Hehai University,Guiyang Hydroelectric Investigation Design and Research Institute.3-D FEM stability analysis of underground caves of right bank of Suofenying Hydropower Station with[R].2003.)
[2]赵洪波,冯夏庭.位移反分析的进化支持向量机研究[J].岩石力学与工程学报,2003,22(10):1618–1622.(ZHAO Hong-bo,FENG Xia-ting.Study on genetic-support vector machine in displacement back analysis[J].Chinese Journal of Rock Mechanics and Engineering,2003,22(10):1618–1622.)
[3]VAPNIK V N.The nature of statistical learning theory[M].New York:Springer-Verlag,1995:55–69.
[4]YONAS B.DIBIKE,SLAVCO Velickov,et al.Model induction with support vector machines:introduction and application[J].Journal of Computing in Civil Engineering,2001(7):208–216.
[5]刘开云,乔春生,腾文彦.边坡位移非线性时间序列采用支持向量机算法的智能建模与预测研究[J].岩土工程学报,2004,26(1):57–61.(LIU Kai-yun,QIAO Chun-sheng,TENG Wen-yan.Research on non-linear time sequence intelligent model construction and prediction of slope displacement by using support vector machine algorithm[J].Chinese Jounal of Geotechnical Engineering,2004,26(1):57–61.)
[6]KIRKPATRICK S,GELATT C D,VECCKI M P.Optimization by simulated annealing[J].Science,1983,220:671–680.
[7]徐果明.反演理论及其应用[M].北京:地震出版社,2003:135–144.(XU Guo-ming.Theories of back analysis and its application[M].Beijing:Earthquake Press,2003:135–144.)
[8]许传华,任青文,周庆华.基于支持向量机和模拟退火算法的位移反分析[J].岩石力学与工程学报,2005,24(22):134–4138.(XU Chuan-hua,REN Qing-wen,ZHOU Qing-hua.Displacement back analysis based on support vector machine and simulated annealing[J].Chinese Journal of Rock Mechanics and Engineering,2005,24(22):4134–4138.)
[9]丁德馨,张志军.位移反分析的自适应神经模糊推理方法[J].岩石力学与工程学报,2004,23(18):3087–3092.(DING De-xin,ZHANG Zhi-jun.Adaptive neuro-fuzzy inference approach for back analysis of displacements[J].Chinese Journal of Rock Mechanics and Engineering,2004,23(18):3087–3092.)
[10]杨林德.岩土工程问题的反演理论与工程实践[M].北京:科学出版社,1996:8–20.(YANG Lin-de.Theories of back analysis and its application on geotechnique[M].Beijing:Science Press,1996:8–20.)
[2]赵洪波,冯夏庭.位移反分析的进化支持向量机研究[J].岩石力学与工程学报,2003,22(10):1618–1622.(ZHAO Hong-bo,FENG Xia-ting.Study on genetic-support vector machine in displacement back analysis[J].Chinese Journal of Rock Mechanics and Engineering,2003,22(10):1618–1622.)
[3]VAPNIK V N.The nature of statistical learning theory[M].New York:Springer-Verlag,1995:55–69.
[4]YONAS B.DIBIKE,SLAVCO Velickov,et al.Model induction with support vector machines:introduction and application[J].Journal of Computing in Civil Engineering,2001(7):208–216.
[5]刘开云,乔春生,腾文彦.边坡位移非线性时间序列采用支持向量机算法的智能建模与预测研究[J].岩土工程学报,2004,26(1):57–61.(LIU Kai-yun,QIAO Chun-sheng,TENG Wen-yan.Research on non-linear time sequence intelligent model construction and prediction of slope displacement by using support vector machine algorithm[J].Chinese Jounal of Geotechnical Engineering,2004,26(1):57–61.)
[6]KIRKPATRICK S,GELATT C D,VECCKI M P.Optimization by simulated annealing[J].Science,1983,220:671–680.
[7]徐果明.反演理论及其应用[M].北京:地震出版社,2003:135–144.(XU Guo-ming.Theories of back analysis and its application[M].Beijing:Earthquake Press,2003:135–144.)
[8]许传华,任青文,周庆华.基于支持向量机和模拟退火算法的位移反分析[J].岩石力学与工程学报,2005,24(22):134–4138.(XU Chuan-hua,REN Qing-wen,ZHOU Qing-hua.Displacement back analysis based on support vector machine and simulated annealing[J].Chinese Journal of Rock Mechanics and Engineering,2005,24(22):4134–4138.)
[9]丁德馨,张志军.位移反分析的自适应神经模糊推理方法[J].岩石力学与工程学报,2004,23(18):3087–3092.(DING De-xin,ZHANG Zhi-jun.Adaptive neuro-fuzzy inference approach for back analysis of displacements[J].Chinese Journal of Rock Mechanics and Engineering,2004,23(18):3087–3092.)
[10]杨林德.岩土工程问题的反演理论与工程实践[M].北京:科学出版社,1996:8–20.(YANG Lin-de.Theories of back analysis and its application on geotechnique[M].Beijing:Science Press,1996:8–20.)
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