关键词: 地下水封洞库, 力学参数, 围岩稳定性, 神经网络, 数值试验

Abstract:

Reasonably and accurately determining the mechanical parameters of surrounding rock is of great significance to the stability analysis of surrounding rock and the design of supporting structure during the construction stage of underground water-sealed storage cavern. Based on the engineering geological characteristics of the underground water-sealed storage cavern, an intelligent inversion method of the mechanical parameters of the surrounding rock during the construction stage is proposed for the equivalent continuous medium model. Firstly, the constitutive model of the cavern rock mass is determined through laboratory tests and numerical tests. Then, the mechanical parameters of the constitutive model are estimated through Hoek-Brown strength criterion and other methods, and the sensitivity of each parameter to the deformation and relaxation of surrounding rock is analyzed. Based on these results, the orthogonal test scheme of the parameters to be inverted can be designed. Finally, the intelligent inversion model of the mechanical parameters of the surrounding rock is constructed by the samples obtained through numerical simulation and the evolutionary neural network model. The comprehensive estimation for the initial value range of the mechanical parameters of the surrounding rock under different class of rock mass basic quality can overcome the large deviation of the inversion results caused by the intelligent algorithm's wide range of optimization. The sensitivity analysis of the mechanical parameters to the deformation and relaxation of the surrounding rock can reduce the number of inversion parameters. The application of the intelligent inversion method is carried out in a typical underground water-sealed storage cavern project in Shandong province. The results show that, the relative errors of the settlement of the peripheral rock vault, the maximum displacement of the cavern circumference, the internal deformation and the average depth of relaxation are less than 10%, which satisfy the precision of engineering application. Thereby, the proposed intelligent inversion method has high feasibility and reliability through application, and it can provide references to the similar projects.

Key words: underground water-sealed storage cavern, mechanical parameters, stability of surrounding rock, neural network, numerical test