Abstract In order to predict the rockburst intensity efficiently,the main control factors of rockburst including the values of in-situ stresses ,the compressive strength ,the tensile strength of rock and the elastic energy index of rock Wet were considered,and three factors , and Wet were defined as the original criterion indices for rockburst intensity prediction in the proposed model. The concept lattice was used as the reduction tool to get the maximum reductions. A comparison between the reduced concept lattice and the reduction of discernible matrix in the traditional dominance rough sets was made. Then rough sets were applied to establish the prediction model of rockburst intensity,and then preferences decision rules were generated. The quality of classification was 100% and the model was applied to predict the rockburst intensity in some projects in China. The prediction results using rough sets based on the reduced concept lattice agree well with the actual situation and those methods using three control factors. The model reduced the required control factors and improved the efficiency of prediction.
|
Received: 17 March 2014
|
|
|
|