采用神经网络反演岩体抗剪强度参数, 当把安全系数作为网络输入时, 由于网络输入参数个数小于输出个数, 神经网络无法建立输入与输出之间的映射关系, 导致反演结果误差偏大。针对这一问题, 提出一种用于岩体抗剪强度参数神经网络反分析的新方法首先利用神经网络反分析确定反演抗剪强度参数的范围, 然后利用神经网络正分析在上述范围内进行仿真, 预测其对应的安全系数, 最后用最优化方法, 把安全系数的预测值与反演值差值的绝对值作为目标函数, 找出与反演工况下安全系数差值最小的安全系数相对应的黏聚力与内摩擦角组合, 认为该组合即为最终反演的岩体抗剪强度参数。工程实例表明, 由该方法得到的岩体抗剪强度参数计算出的安全系数与反演工况下安全系数相等, 说明该方法能有效解决上述问题, 是可行的。
Abstract
Neural network has been used to inverse the shear strength parameters of rock mass. When safety factor is used as network input, the number of input parameters less than the number of output parameters will result in big errors as the mapping between input and output could not be established. In view of this, a new method of neural network back analysis suitable for the shear strength parameters of rock mass is presented. Firstly, neural network back analysis is employed to determine the range of inversion parameter, and then normal analysis is used for simulation in the above range to predict the safety factor. Finally, by using method of optimization, the absolute difference value between predicted and inversed values of safety factor is taken as objective function to find out the combination of cohesion and internal friction angle in correspondence with the safety factor which has minimum difference with the safety factor in the inversion conditions. This combination is thus regarded as the final inversed shear strength parameters of rock mass. Engineering examples show that the safety factor obtained by the method is equal to the safety factor in inversion conditions, indicating that this method is effective and feasible to solve the above problems.
关键词
神经网络 /
抗剪强度参数 /
安全系数 /
反分析 /
最优化
Key words
neural network /
shear strength parameters /
safety factor /
back analysis /
optimization
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 李端有, 甘孝清, 周 武. 基于均匀设计及遗传神经网络的大坝力学参数反分析方法[J]. 岩土工程学报, 2007, 29(1):125-130. (LI Duan-you, GAN Xiao-qing, ZHOU Wu. Back Analysis on Mechanical Parameters of Dams Based on Uniform Design and Genetic Neural Network[J]. Chinese Journal of Geotechnical Engineering, 2007, 29(1):125-130.(in Chinese))
[2] 杨林德, 朱合华, 冯紫良, 等. 岩土工程问题的反演理论与工程实践[M]. 北京: 科学出版社, 1998. (YANG Lin-de, ZHU He-hua, FENG Zi-liang, et al. Geotechnical Problems of Inversion Theory and Engineering Practice[M]. Beijing: Science Press, 1998. (in Chinese))
[3] 吕爱钟, 蒋斌松. 岩石力学反问题[M]. 北京: 煤炭工业出版社, 1998.(LV Ai-zhong, JIANG Bin-song. Problems of Inversion in Rock Mechanics [M]. Beijing: Coal Industry Press, 1998. (in Chinese))
[4] 李素华, 徐天平. 优化反分析方法在桩基工程中的应用[J]. 土木工程学报, 1993, 26(1):12-19.(LI Su-hua, XU Tian-ping. Application of Optimization Methods to Back Analysis of Wave Equation in Pile Foundation Engineering[J]. Chinese Journal of Civil Engineering, 1993, 26(1): 12-19.(in Chinese))
[5] 邓 勇. 边坡岩体力学参数反分析遗传-神经网络算法[J]. 地下空间与工程学报, 2007, 3(4):751-757.(DENG Yong. A Genetic-artificial Neural Network Algorithm for Mechanical Parameters of Rock Slope[J]. Chinese Journal of Underground Space and Engineering, 2007, 3(4): 751-757.(in Chinese))
[6] 郝 哲. 基于均匀设计差分法和模糊神经网络的隧道围岩物理力学参数反分析[J]. 中国矿业, 2004, 13(12):85-89, 26.(HAO Zhe. Back Analysis of Physics and Mechanics Parameters of Surrounding Rock of Tunnel Based on Uniform Design Calculus of Differences and Fuzzy Neural Networks[J]. China Mining Magazine, 2004, 13(12):85-89, 26. (in Chinese))
[7] 贠永峰, 范永慧, 孙 扬. 基于BP神经网络的隧道围岩力学参数反分析方法[J]. 沈阳建筑大学学报(自然科学版), 2011, 27(2):292-296, 306. (YUN Yong-feng, FAN Yong-hui, SUN Yang. Back Analysis of Mechanical Parameters of Tunnel Surrounding Rock by BP Neural Network Method[J]. Journal of Shenyang Jianzhu University (Natural Science), 2011, 27(2):292-296, 306.(in Chinese))
基金
三峡大学2012年研究生科研创新基金项目(2012CX018)
PDF(1615 KB)
