Rockburst prediction based on optimization of unascertained measure theory with normal cloud

Abstract Rockburst is one of the common geological disasters in deep underground areas with high stress. prediction an important measure to know advance risk rockburst hazards take a scientific approach response. In view fuzziness and uncertainty between quantitative indexes qualitative grade assessments prediction, this study proposes use normal cloud model optimize theory unascertained measures (NC-UM). The uniaxial compressive strength ( σ c ), stress coefficient θ / elastic deformation energy index (Wet), brittleness rock t ) are selected as prediction. After data screening, 249 groups case original set. To reduce influence subjective objective factors weight on results, game used synthesize three weighting methods Criteria Importance Through Intercriteria Correlation (CRITIC), Entropy Weight (EW), Analytic Hierarchy Process (AHP) obtain comprehensive index. validating example data, results showed that was 93.3% accurate no more than level deviation. Compared traditional (UM) model, accuracy 15–20% higher model. It shows valid applicable predicting propensity level.