摘要
以石黔高速公路白水隧道为例,采用敏感性分析与数值模拟相结合的方法计算出隧道围岩各力学参数的敏感度,确定影响隧道变形的主要力学参数。首先,基于正交试验设计构造BP神经网络的样本,建立待反演参数与围岩变形的非线性映射关系,将现场监控量测实测值作为输入样本,得到围岩力学参数。然后,将反演得到的力学参数代入到数值模拟中,计算出隧道围岩变形值,对比分析实测值与计算值。结果表明,两者误差较小,这说明该方法应用于该工程的可行性。
Taking Baishui Tunnel of Shiqian Expressway as an example,sensitivity analysis and numerical simulation are used to calculate the sensitivity of mechanical parameters of tunnel surrounding rock and determine the main influencing parameters.Based on orthogonal experimental design,BP neural network samples are constructed to obtain the nonlinear mapping relationship between parameters to be inverted and surrounding rock deformation.The mechanical parameters of surrounding rock can be obtained by using the monitoring data of tunnel site as input samples.The inverted mechanical parameters are substituted into the numerical simulation to calculate the deformation value of surrounding rock of tunnel,and that the error between the measured and calculated values is small verifies the feasibility of the method applied to the project.
作者
祝江林
陈秋南
Zhu Jianglin;Chen Qiunan(College of Civil Engineering,Hunan University of Science and Technology,Xiangtan 411201,China;Hunan Provincial Key Laboratory of Geotechnical Engineering for Stability Control and Health Monitoring,Xiangtan 411201,China)
出处
《湖南文理学院学报（自然科学版）》
CAS
2019年第2期85-89,共5页
Journal of Hunan University of Arts and Science(Science and Technology)
基金
国家自然科学基金项目(41172275)
关键词
敏感性分析
正交试验
BP神经网络
位移反分析
sensitivity analysis
orthogonal experiment
BP neural network
displacement back analysis
