Surrounding rock distinguishing and grading method

Abstract

The invention discloses a surrounding rock distinguishing and grading method. The method comprises the following steps: S0, performing data conversion on Rc and Jv to obtain converted R'c and J'v; S1, by utilizing the converted R'c, J'v, S1, S2 and S3, carrying out factor analysis to obtain comprehensive factors F'1 and F'2, wherein the comprehensive factor F '1 is a surrounding rock integrity comprehensive factor and mainly reflects the influence of Jv and S1 factors, and the comprehensive factor F'2 is a surrounding rock strength comprehensive factor and mainly reflects the influence of Rc and S2 factors; S2, taking the comprehensive factors F'1 and F'2 as training samples to train a surrounding rock grading model to obtain a Fisher discrimination model; and S3, performing surrounding rock grade prediction on the test sample by using the Fisher discriminant model, thereby solving the problem of low accuracy when the Fisher discriminant model is verified by using a back substitution method due to the fact that influence factors are not preprocessed. The surrounding rock discriminant grading method is high in accuracy and wide in applicability.

Description

technical field [0001] The invention belongs to the field of underground structures and mountain tunnel engineering, and more specifically relates to a method for distinguishing and grading surrounding rocks. Background technique [0002] At present, there are more and more underground projects and mountain tunnel projects in my country, and the complexity of construction is also increasing. Before the design and construction of these projects, it is often necessary to make a classification judgment of the surrounding rock according to the hydrogeological conditions of the project site for subsequent support. Protection design and construction. It is very important to classify the surrounding rocks correctly. For example, if the surrounding rocks of grade IV are classified into grade V by mistake, there will be too much surplus in engineering support design, resulting in waste; Insufficient support design results in safety accidents. [0003] At present, many codes and stan...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem that the accuracy of the Fisher discriminant model is not high when using the back-substitution method to verify the Fisher discriminant model due to the lack of pretreatment of the influencing factors, the present invention provides a method for discriminating and grading the surrounding rock, which can be used for the rock uniaxial compressive strength R in the influencing factors c and volume joint number of surrounding rock J v Perform data transformation and obtain the comprehensive factor F' by factor analysis 1 and F' 2 As a training sample to train the surrounding rock classification model, the surrounding rock discrimination and classification method of the present invention has high accuracy and wide applicability

Images