论文部分内容阅读
岩土体的流变特性是影响边坡变形及稳定性的重要因素,对边坡进行稳定性评价、结合变形监测资料对边坡进行预警预报,都有必要考虑岩土体的流变效应。本文以京珠高速K108边坡为研究对象,采用粘弹塑性数值方法建立该边坡的计算模型,通过大量的数值分析获得神经网络的训练样本,由人工神经网络的非线性映射功能建立岩土体流变位移与待反演参数之间的特征关系,将实测位移代入训练好的神经网络进行反分析得到软弱夹层的流变参数,通过后验差的方法验证了反演结果的合理性,得到的结果可用于后续的边坡稳定分析及预警。
The rheological properties of rock and soil body are the important factors that affect the deformation and stability of the slope. It is necessary to consider the rheological effect of the rock and soil in order to evaluate the stability of the slope and predict the slope with deformation monitoring data. In this paper, the K108 slope of Beijing-Zhuhai Expressway is taken as the research object. The viscoelasto-plastic numerical method is used to establish the calculation model of the slope. Neural network training samples are obtained through a large number of numerical analysis. The nonlinear mapping function of artificial neural network The relationship between body rheological displacement and the parameter to be inverted is substituted into the trained neural network to obtain the rheological parameters of the weak interlayer. The posterior difference method is used to verify the rationality of the inversion results. The results obtained can be used for subsequent slope stability analysis and early warning.