Inversion of Rheological Parameters of Surrounding Rocks in a Mine Roadway Based on BP Neural Network

Jump To References Section

Authors

  • Department of Information Technology, Beijing Vocational College of Agriculture, Beijing 102442 ,CN
  • Architectural Design and Research Institute of Tsinghua University Co. Ltd., Beijing 100 084 ,CN
  • Department of Civil Engineering, Tsinghua University, Beijing 100 084 ,CN
  • Department of Information Technology, Beijing Vocational College of Agriculture, Beijing 102442 ,CN

DOI:

https://doi.org/10.18311/jmmf/2017/27034

Keywords:

Numerical Simulation, Creep, BP Neural Network.

Abstract

For weak rock mass with notable rheological property, instability is mostly caused by flowing deformation. As the basis for the design of roadway supporting structure, the rheological parameters of surrounding rocks are of great importance. Unfortunately, the rheological parameters obtained from indoor tests often fail to reflect the geological defects in a large research area due to the impact from constraints of sampling representativeness, sampling disturbance and testing technical level. What is worse, field tests are time-consuming, unrepeatable and costly. To solve these problems, this paper conducts inversion of the rheological parameters of surrounding rocks based on the BP neural network. Taking a mine roadway as an example and considering the vault subsidence data in the entrance section, the author applies FLAC3D in numerical simulation, adopts BP neural network for network learning and sample training, and performs displacement inversion of the rheological parameters of the surrounding rocks in the section.

Downloads

Download data is not yet available.

Metrics

Metrics Loading ...

Downloads

Published

2017-03-01

How to Cite

Liu, H., Meng, X., He, W., & Li, R. (2017). Inversion of Rheological Parameters of Surrounding Rocks in a Mine Roadway Based on BP Neural Network. Journal of Mines, Metals and Fuels, 65(3), 149–155. https://doi.org/10.18311/jmmf/2017/27034

Issue

Section

Articles

 

Most read articles by the same author(s)