Narrow Results

The theory studies have showed that, rock burst is a kind of dynamic phenomenon of rock mass in mining, and is a kind of dynamic disaster from mining. The time series of magnitude is a very important exterior behavior of rock burst. The previous studies show that, to model this complicated non-linear time series, the neural network is a very good method. To overcome the shortcomings of traditional neural network, a new kind of evolutionary neural network based on immunized evolutionary programming proposed by author is proposed here. At last, the proposed evolutionary neural network model is verified by a real magnitude series of rock burst. And the result is compared with other method, such as grey system method. The results have showed that, evolutionary neural network model not only has high approaching precision, but also has high predicting precision, and is a good method to construct the non-linear model of rock burst. And this method can be used in a large number of engineering examples.

Rock burst is a multiscale dynamic fracturing process induced by unloading. To further investigate the dynamic fracturing mechanism of rock burst, a grain-based discretized virtual internal bond (GB-DVIB) method is developed. The Voronoi diagram is used to discretize the background discretized virtual internal bond (DVIB) mesh to generate the micro-structure of rock. The bond cell within a Voronoi diagram is termed as the grain cell, characterized by the linear Stillinger–Weber potential. While the bond cell cut by the Voronoi polygon edge is termed as the interface cell, in which both the tension and the shear failure are considered. The simulation results suggest that this method can reflect the contact and friction between grains and reproduce the confining pressure-dependency of compressive strength of rock. With this method, the unloading effects of the in situ stress, the grain size and the heterogeneity on rock failure are studied. The simulated results show that more tensile cracks and less shear cracks are generated when unloading a higher confining stress. When the axial stress is fixed, the total created crack area is almost a constant. The tensile crack area is basically a constant while the shear crack area increases under the condition of a higher axial stress. With decreasing the grain size, more cracks are generated, but the area ratio of the shear to the tensile cracks is almost a constant. It is suggested that GB-DVIB is an effective method for the rock burst simulation. The findings provide deep insight into the rock burst from the standpoint of dynamic fracture.