A Research on the Methods for Prediction of the Slope Stability of Open-pit Mine

DOI

10.2991/coal-18.2018.13How to use a DOI?

Keywords

slope stability, back propagation, naive bayes classifier, support vector machine, decision tree, prediction

Abstract

In order to improve the slope stability of open-pit mine, this paper proposed four prediction methods BP (Back Propagation)Neural Network, Naive Bayes Classifier, Decision Tree and Support Vector Machine for predicting the classification of slope stability of open-pit mine.Firstly, the sample data of slope stability in open-pit mine are preprocessed, and the new sample data are obtained after data standardization, discretization and attribute reduction. Then, the corresponding prediction model is established by selecting different methods. All the four methods have been successfully applied to the prediction of 8 groups of samples to be tested. In order to determine the optimal method, the detailed accuracy and node error rate are compared to analyze the prediction results. The research shows that the BP neural network has high reliability and good practicability in the evaluation of the slope stability of open-pit mine.

Copyright

© 2018, 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  - Xiwen Feng
AU  - Yue Guo
AU  - Junyong Li
PY  - 2018/10
DA  - 2018/10
TI  - A Research on the Methods for Prediction of the Slope Stability of Open-pit Mine
BT  - Proceedings of the 9th China-Russia Symposium "Coal in the 21st Century: Mining, Intelligent Equipment and Environment Protection" (COAL 2018)
PB  - Atlantis Press
SP  - 73
EP  - 77
SN  - 2352-5401
UR  - https://doi.org/10.2991/coal-18.2018.13
DO  - 10.2991/coal-18.2018.13
ID  - Feng2018/10
ER  -