花岗岩类土质滑坡抗剪强度参数反演研究

摘要

从Mohr-Coulomb模型和Hardening-Soil模型入手,通过阐述摩尔库伦经典公式,引入具体工程算例,综合多断面传递系数反演法、单变量回归方程逐级反演法、BP神经网络训练统计反演法等新方法对强度参数进行预测,对花岗岩类土质滑坡工程参数优化选取,解决了传统实验工作量大、尺寸效应影响显著、反演结果精确度较低的问题.%Based on Mohr-Coulomb and Hardening-Soil models Mohr-Coulomb classical formula is illustrated.Through specific project examples, the new methods such as inversion BP neural network are applied to predict the strength parameters for the purpose of optimizing, on granite soil landslide parameters of granite soil project.