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

    BACK ANALYSIS OF PHYSICS AND MECHANICS PARAMETERS OF SURROUNDING ROCK OF TUNNEL BASED ON UNIFORM DESIGN CALCULUS OF DIFFERENCES AND FUZZY NEURAL NETWORKS

    • 摘要: 基于均匀设计、差分法和模糊人工神经网络建立了新的隧道围岩物理力学参数反分析方法。按照均匀设计要求,选取不同物理力学参数;用FLAC差分程序进行计算,得出了相应的神经网络分析样本;进行了网络结构及学习参数的优化;对模糊神经网络进行了学习训练;据学习结果,利用各监测断面实测数据,对韩家岭隧道围岩物理力学参数进行了反分析,反分析结果满足精度要求。

       

      Abstract: The new back analysis method of physics and mechanics parameters of surrounding rock was established by uniform design, calculus of differences and fuzzy artificial neural networks in this paper. According to uniform design, different physics and mechanics parameters were chosen. Using FLAC program to calculate, the related analytical samples of neural networks were given. Structure and training parameters of networks were optimized. Training was conduced by fuzzy artificial neural networks. Physics and mechanics parameters of surrounding rock of Hanjialing tunnel were back analyzed by training results and the on-the-spot survey data of every measured section.

       

    /

    返回文章
    返回