Rock-burst acoustic emission predicting method based on support vector machine (SVM)

Abstract

The invention belongs to the field of mining safety and relates to a rock-burst acoustic emission predicting method based on a support vector machine (SVM). The rock-burst acoustic emission predicting method includes using SVM regression prediction as a means, selecting energy release value as judgment indicator for predicting rock burst on the basis of test research analysis, using burst tendency physical and mechanic parameters and acoustic emission signal feature parameters as influence factor of rock burst, and generating SVM input vector by extracting sample data according to these parameters; selecting Gauss radial basis function (RBF) as kernel function of the SVM in setup of a SVM prediction model, and using the K-CV cross validation algorithm to optimize and select the optimal penalty parameter C and kernel function parameter g; applying a fuzzy information granulating data processing method into the regression prediction of the SVM so as to predict change trends and change space of the predicted values of the rock burst.

Description

technical field [0001] The invention belongs to the field of mining safety, and in particular relates to a method for predicting acoustic emission of rock mass rock burst based on a support vector machine. Background technique [0002] Rock burst is a violent dynamic phenomenon caused by changes in the stress state of the rock mass caused by underground mining, resulting in stress concentration. When the rock strength limit is reached, the elastic energy accumulated in the rock mass is released suddenly and sharply. Rock mass vibration and damage caused by rock burst may cause various mine disasters, posing a great threat to mine production and workers' lives. In the process of rock burst, the phenomenon that the strain energy of the rock mass is released in the form of elastic waves is called the acoustic emission phenomenon. Relevant studies have shown that acoustic emission is closely related to the elastic waves generated by the impact stress of the rock mass, and the a...

AI Technical Summary

Problems solved by technology

Although there are clear evaluation parameter indicators and the rich information provided by the acoustic emission signal is well used, the physical and mechanical parameters of the impact tendency induced by the rock mass burst are not considered, and the selection of evaluation parameters is not comprehensive and effective. prediction model, so the reliability of its prediction results is not strong

Images