Prediction for Damage Depth of Coal Seam Floor Based on the BP Neural Network

DOI

10.2991/icmsa-15.2015.3How to use a DOI?

Keywords

Artificial Neural Network, Floor Damage Depth, Inrush, Matlab Software, Forecasting Formula.

Abstract

On the basis summary of forecasting methods and theoretical depth of stope floor, combining a large number of actual data analysis, it is induced that the following six aspects are the main factors influencing the floor damage depth the: mining depth, dip angle of coal seam, mining thickness and length of working face, floor ability to resist damage and presence of cutting wear fault or fracture zone. Based on artificial neural network input required samples and test samples, through the Matlab software to network training, it is concluded that the optimization of the network model, and according to the established network model, Chensilou coal mine 21201, 2408 and 20301 working faces damage depth has been established. Compared with the measured results, the floor damage prediction formula of depth and deep relationship was obtained.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Shun-Feng Li
PY  - 2014/06
DA  - 2014/06
TI  - Prediction for Damage Depth of Coal Seam Floor Based on the BP Neural Network
BT  - Proceedings of the 2015 International Conference on Material Science and Applications
PB  - Atlantis Press
SP  - 14
EP  - 19
SN  - 2352-541X
UR  - https://doi.org/10.2991/icmsa-15.2015.3
DO  - 10.2991/icmsa-15.2015.3
ID  - Li2014/06
ER  -