Deep phosphorite rock burst tendency evaluation method based on neural network
The invention discloses a deep phosphorite rock burst tendency evaluation method based on a neural network. The method comprises the following steps: selecting rock uniaxial compressive strength sigma c, a brittleness coefficient B, a rock mass integrity coefficient KV and a ratio T of tangential st...
Saved in:
Main Authors | , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
01.12.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention discloses a deep phosphorite rock burst tendency evaluation method based on a neural network. The method comprises the following steps: selecting rock uniaxial compressive strength sigma c, a brittleness coefficient B, a rock mass integrity coefficient KV and a ratio T of tangential stress to the uniaxial compressive strength as input layer indexes; the rockburst tendency grades are divided into four types of rockburst-free, weak rockburst, medium rockburst and strong rockburst as output layer indexes; the node number of the middle layer is set to be n, and n is an integer from 4 to 12; using round and rand functions in excel to perform random valuing in an input layer index limit range corresponding to each rockburst tendency grade to generate a learning sample; a Bayesian Regulation mathematical model of an MATLAB neural network toolbox is called for training, an expected error sum of squares index err-goal is set to be equal to 0.01 until a target error requirement is met, and a trained neura |
---|---|
Bibliography: | Application Number: CN202311008261 |