Rockburst process evaluation using experimental and artificial intelligence techniques

Rockburst is characterized by a violent explosion of a certain block causing a sudden rupture in the rock and is quite common in deep tunnels. It is critical to understand the phenomenon of rockburst, focusing on the patterns of occurrence so these events can be avoid andor managed saving costs and possibly lives. The failure mechanism of rockburst needs to be better understood. Laboratory experiments are one of the ways. A description of a system developed at the State Key Laboratory for Geomechanics and Deep Underground Engineering (SKLGDUE) of Beijing is described. Also, several cases of rockburst that occurred around the world were collected, stored in a database and analyzed. The analysis of the collected cases allowed one to build influence diagrams, listing the factors that interact and influence the occurrence of rockburst, as well as the relation between them. Data Mining (DM) techniques were also applied to the database cases in order to determine and conclude on relations between parameters that influence the occurrence of rockburst during underground construction. A methodology was developed based on the use of Bayesian Networks (BN) and applied to the existing information of the database and some numerical applications were analyzed. Conclusions and recommendations are established.