BP网络在双连拱隧道围岩参数反分析中的应用

BP Neural Networks Applied to Displacement Back-Analysis for Two-Arch Tunnel

该文以模拟隧道开挖的有限元为正演工具,通过BP神经网络,对在隧道工程施工过程中量测到的围岩位移进行反分析,确定出围岩岩体的力学特性参数,从而可以通过数值分析方法对隧道围岩稳定性作出合理的评价和符合实际的预测,使得现场量测结果能更加有效地应用于隧道工程的施工决策.

In this paper, an FEM program simulating a two-arch tunnel construction is used as a tool in the forward process. Back-analysis is then performed for the rock displacement in a tunnel project to find the mechanical parameter of the rock based on BP neural network. A rational assessment prediction about the stability of the rock can be made by analyzing mechanical characteristic parameters of the rock therefore on-the-spot measurement results can be applied to the tunnel project more effectively.