Classified prediction model of rockburst using rough sets-normal cloud

In view of complexity and uncertainty of problems in the prediction of rockburst, a classified prediction model of rockburst using rough sets-normal cloud is established. Seven main influencing factors including uniaxial compressive strength of rock sigma (c), uniaxial tensile strength of rock sigma (t), maximum tangential stress of surrounding rock sigma (theta), rock integrality coefficient k(v), ratio between uniaxial compressive strength of rock and uniaxial tensile strength of rock sigma (c)/sigma (t), ratio between maximum tangential stress of surrounding rock and uniaxial compressive strength of rock sigma (theta)/sigma (c) and rock elastic deformation energy index w(et) are selected as the evaluation index of rockburst. Sixteen groups of rockburst examples at home and abroad are used as model construction samples. Then, the weight value of evaluation index of rockburst is obtained by rough sets and fuzzy sets. According to normal cloud theory and classification standard of rockburst, the cloud maps of evaluation index of rockburst are generated. Based on the normal cloud generator and sample data, the evaluation index of the classified sample is determined, and the comprehensive determination of evaluation index of the classified sample is obtained by combining the weight of the evaluation index of rockburst. Finally, the rockburst level is identified according to the principle of maximum membership degree. The classified prediction model of rockburst is used to predict five groups of rockburst samples at home and abroad, and the rockburst classification is coincident with the actual situation. The results show that the classified prediction model of rockburst using rough sets-normal cloud has great practicability.