Real-time inversion method for creep parameters of surrounding rock mass

Abstract

The invention discloses a real-time inversion method for creep parameters of a surrounding rock mass. The real-time inversion method comprises the following steps: determining creep parameters of thesurrounding rock mass to be inversed; establishing a surrounding rock body numerical calculation model; constructing a creep parameter inversion recurrent neural network agent model data set; trainingan optimal creep parameter inversion recurrent neural network agent model; and optimizing and determining the creep parameters of the surrounding rock mass to be inverted by utilizing the creep parameter inversion recurrent neural network agent model and a random global optimization algorithm according to the field actual measurement mechanical response. The real-time inversion method solves theproblem of large calculation time consumption of a traditional inversion method, also solves the bottleneck problems that the time effect of creep surrounding rock mass mechanical response cannot be considered and the creep parameter of the surrounding rock mass cannot be predicted and adjusted in real time, has the advantages of small workload, low cost, high precision, high reliability and the like, can greatly improve the inversion efficiency of the creep parameter of the surrounding rock mass, and is high in universality.

Description

technical field [0001] The invention relates to the technical field of geotechnical engineering, in particular to a real-time inversion method for creep parameters of surrounding rock mass. Background technique [0002] Creep of surrounding rock mass refers to the relationship between stress-strain-time of surrounding rock mass, and is one of the important properties that cannot be ignored in the study of rock mechanics. With the continuous development of underground rock mass engineering, the rock types of the surrounding rock mass become more and more complex, and are easily affected by the high underground stress field. These complex and changeable environments make the creep characteristics of rock more significant, which in turn affects the long-term stability and safety of underground rock mass engineering. Due to the complexity of deep underground rock mass engineering itself and stress distribution, the stability of creeping surrounding rock mass is usually carried ...

AI Technical Summary

Problems solved by technology

However, a large number of numerical calculations increase the calculation time and greatly increase the calculation cost.

Moreover, at present, the creep parameter inversion is generally only performed once at a specific moment, and the creep parameters are updated and adjusted in real time without relying on new measured data, which seriously restricts the efficiency and accuracy of the inversion.

Images