A rockburst grade prediction method based on information vector machine

Abstract

The invention discloses a rockburst grade prediction method based on an information vector machine, which mainly solves the problem of poor prediction effect of rockburst geological disasters in the current underground engineering construction process. Firstly, the rockburst evaluation index and grading standard are selected, and a rich training sample library is established by extensively collecting major deep rock engineering rockburst examples at home and abroad; The non-linear mapping relationship between the burst evaluation index and the rockburst grade, and the initial parameter setting of the model and the training sample library are adjusted according to the training results, and finally the IVM model for rockburst grade prediction is established. Applying the method of the present invention to predict the grade of rockburst does not require complex mechanical analysis and calculation, and only needs to input the input feature vector of the sample to be predicted into the above prediction model to obtain the predicted value of the grade of rockburst. The method is economical and efficient, has high prediction accuracy, and has good engineering application prospects.

Description

technical field [0001] The invention belongs to the technical field of underground engineering, and relates to a method for predicting rockburst grades based on an information vector machine. Background technique [0002] Rockburst is a dynamic geological disaster phenomenon that occurs when the elastic strain energy accumulated in the rock mass is released suddenly during the excavation of underground engineering in high geostress areas. Low-intensity rockbursts are characterized by the peeling off of surrounding rocks, with sound and air waves, and are less dangerous; high-intensity rockbursts are manifested in the collapse and ejection of surrounding rocks, which produce large dust and air shock waves, and often cause rocks to collapse. The body and the surface vibrate, similar to a small earthquake. The phenomenon of rockburst geological disaster directly threatens the safety of construction personnel and equipment, affects the progress of the project, and increases the...

AI Technical Summary

Problems solved by technology

[0008] In order to overcome the defects existing in the prior art, the present invention proposes a rockburst level prediction method based on information vector machine, aiming to solve the problem of poor prediction effect of rockburst geological disasters in the current underground engineering construction process, and improve the rockburst level prediction method. Engineering Practicability of the Method of Explosion Level Prediction

Images