The 4th International Symposium on Mine Safety Science and Engineering (ISMSSE2018)

267 / 2018-04-07 03:16:33

Machine Learning Methods for Rockburst Prediction – State-of-the-art Review

Rockbursts,,Machine Learning

Mine Dynamics Disaster > Rock burst impact

One of the most serious mine disasters in underground mines are rockburst phenomena. They can lead to serious injuries and even fatalities let alone damage to underground openings and mining equipment. This has forced many researchers around the world to investigate alternative methods to predict the potential for rockburst occurrence. However, due to the highly complex nature between the geological, mechanical and geometric parameters of the mining environment, the traditional mechanics-based prediction methods do not always yield precise results. With the emergence of machine learning methods, a new breakthrough in the prediction of rockbursts has become possible in recent years. In this paper, a state-of-the-art review of the various applications of machine learning methods for the prediction of rockburst potential is presented. First, existing rockburst prediction methods are introduced, and the limitations of such methods are highlighted. A brief overview of typical machine learning methods and their main features as predictive tools is then presented. The current applications of machine learning models in rockbursting prediction are surveyed, with related mechanisms, technical details and performance analysis.