Method for acquiring mechanical parameters of rock-soil body

Abstract

The invention relates to a method for acquiring mechanical parameters of rock-soil body, which comprises the following steps of: 1, selecting a to-be-inverted soil mass parameter, determining a parameter range and generating a specified number of parameter data sets; 2, calculating parameters in the parameter data set through FLAC3D, and obtaining the displacement of a specified measuring point; step 3, performing normalization processing on the displacement of the specified measuring point obtained in the step 2; 4, generating a neural network hyper-parameter initial population, and selecting an optimal hyper-parameter combination by adopting a particle swarm algorithm to obtain an optimal agent model; and 5, inverting the to-be-solved soil mass parameters on the basis of the proxy model by adopting an NSGA-II algorithm, and obtaining final rock-soil mass mechanical parameters. Compared with the prior art, the method has the advantages of high precision, high accuracy and the like.

Description

technical field [0001] The invention relates to the fields of tunnel engineering, geotechnical engineering and geological engineering, in particular to a method for acquiring rock and soil mechanics parameters. Background technique [0002] In engineering practice, the mechanical parameters of rock and soil are often obtained through in-situ survey and laboratory test. However, due to the characteristics of uneven spatial distribution and susceptibility to disturbance of geotechnical materials, general indoor tests and on-site in-situ surveys are limited by factors such as manpower, time, and cost, and cannot fully and effectively cover the construction area. Usually, only Limited survey results exist in some parts of the construction area. At the same time, due to the differences between the test environment and the actual stress environment, the mechanical parameters of the rock mass obtained from the laboratory test are also difficult to accurately reflect the actual pro...

AI Technical Summary

Problems solved by technology

[0005] (1) The above method does not normalize the data, which will lead to different orders of displacement of the measuring points due to the different positions of different measuring points and the different deformation characteristics of the surrounding rock when calculating the final objective function. The measuring points will contribute more errors in the objective function, while the smaller measuring points will contribute little, which will be covered by the errors of other measuring points, resulting in the inability to be effectively optimized and reducing the accuracy

[0006] (2) The above method uses the single-objective optimization theory, which integrates the prediction errors of measuring points in different construction stages and different measuring point positions into one objective function for optimization, and the accuracy and reliability are low

Images