Development of a Stope Stability Prediction Model Using Ensemble Learning Techniques-A Case Study

Authors

  • Festus Saadaari University of Mines and Technology https://orcid.org/0000-0002-8202-2021
  • Daniel Mireku-Gyimah University of Mines and Technology
  • Boluwaji Muriana Olaleye The Federal University of Technology, Akure

Abstract

The consequences of collapsed stopes can be dire in the mining industry. This can lead to the revocation of a mining license in most jurisdictions, especially when the harm costs lives. Therefore, as a mine planning and technical services engineer, it is imperative to estimate the stability status of stopes. This study has attempted to produce an empirical stope stability prediction model adopted from stability graph using ensemble learning techniques and making use of 472 case histories from 120 stopes of AngloGold Ashanti Ghana, Obuasi Mine. Random Forest, Gradient Boosting, Bootstrap Aggregating and Adaptive Boosting classification algorithms were used to produce the models. A comparative analysis was done using six classification performance metrics to determine which ensemble learning technique performed best in predicting the stability of a stope. At a 95% confidence interval using Wilson Score Interval, the results showed that the Bootstrap Aggregating model produced the minimal error and hence was selected as the alternative stope design tool for predicting the stability status of stopes.

Author Biographies

Festus Saadaari, University of Mines and Technology

F. Saadaari is a Postgraduate Assistant in the Mining Engineering Department of the University of Mines and Technology (UMaT), Tarkwa. He obtained his BSc (Hons.) degree and is currently reading for a PhD degree in Mining Engineering from UMaT He is also a student member of the Canadian Institute of Mining, Metallurgy and Petroleum (CIM). His research interests include Artificial Intelligence, Machine Learning, Intelligent Rock Mechanics and Excavation Stability, Rock Mass Characterisation, Slope Stability and Surface Mining.

Daniel Mireku-Gyimah, University of Mines and Technology

D. Mireku-Gyimah is a Professor of Mining Engineering and a Consulting Engineer currently working at the University of Mines and Technology, Tarkwa, Ghana. He holds the degrees of MSc from the Moscow Mining Institute, Moscow, Russia, and PhD and DIC from the Imperial College of Science, Technology and Medicine, London, UK. He is a member of Institute of Materials, Minerals and Mining of UK and a fellow of Ghana Institution of Engineers, Ghana Academy of Arts and Science, Ghana Institution of Geoscientists and West African Institute of Mining, Metallurgy and Petroleum. His research and consultancy works cover Mine Design and Planning, Mine Feasibility Study, Operations Research, Environmental Protection and Corporate Social Responsibility Management.

Boluwaji Muriana Olaleye, The Federal University of Technology, Akure

B. M. Olaleye is a Professor of Mining Engineering working at the Federal University of Technology, Akure, Nigeria. He holds the degrees of MEng and PhD in Mining Engineering from the Federal University of Technology, Akure, Nigeria. He is a Registered Engineer with Council for Regulation of Engineering in Nigeria and Council of Nigerian Mining Engineers and Geoscientists. He is also a Fellow of the Nigerian Society of Mining Engineers. His research and consultancy works cover Rock Mechanic and Rock Engineering; Rock Characterisation and Rock Slope Stability Investigation.

Downloads

Published

2020-12-26