Research on evaluation model of rock failure integrity under complex geological conditions in karst area

Blasting lumpiness prediction is one of the most important research contents in engineering blasting. Although traditional KUZ-RAM model widely used, it often overestimates size Therefore, was updated or corrected this paper by simplifying difficult problem statistical burst fragmentation LS-DYNA. Based on theory area measurement method, fitting mechanism machine learning used to study simulation results. The adds a coefficient 0.623 original equation average x m . linear R 2 between predicted results and field blasting increases from −1.99 0.97, which significantly improves lumpiness.