论文部分内容阅读
以某浅埋偏压小净距隧道先行洞施工监测为工程依托,根据正交设计思想,确立实验方案,结合弹塑性非线性有限元计算构造训练样本,借助BP神经网络的超强非线性映射能力对隧道先行洞开挖所揭露的围岩变形模量E、泊松比μ进行了位移反演,及时掌握先行洞开挖后围岩物理力学参数,从而达到优化设计并指导后行洞施工的目的,以实现隧道的信息化施工与设计。
Based on the engineering design of the pilot tunnel construction monitoring of a shallowly-buried shallowly-spaced tunnel with a small distance, an experimental scheme was established based on the orthogonal design idea, and the nonlinear nonlinear finite element method was used to construct the training samples. With the help of the BP neural network’s super-nonlinear mapping The ability to reverse displacement of the surrounding rock deformation modulus E, Poisson’s ratio μ revealed by the tunnel excavation of the tunnel and to grasp the physical and mechanical parameters of the surrounding rock after excavation in time so as to optimize the design and guide the construction of the post-tunneling , In order to achieve the construction of the tunnel information and design.