Abstract The characteristic variables of blasting vibration have great effects on its damage degree. The prediction of characteristic variables caused by blasting vibration is helpful to study blasting vibration effect. For the first time, the prediction of the PPV and first dominant frequency band and its duration are achieved on the basis of rough set and Fuzzy-Neural Network (FNN) theory. The purpose of this study is to explore a method which can avoid the limitation of the prediction by only one index and to improve the prediction precision. Firstly, the drawback of prediction of the PPV based on Sadov’s vibration formula was analyzed. Secondly, Rough Set and Fuzzy-Neural Network (RSFNN) theory were introduced briefly. Thirdly, Rough set-based FNN prediction model for the characteristic variables of blasting vibration is established based on the analysis of factors affecting blasting vibration characteristic variables. Finally, the model was trained by data come form Tonglvshan Copper Mine and was tested by 15 groups of data. The results show that rough set and FNN prediction model reflects the nonlinear relationship between factors and characteristic variables and can be used to predict the characteristic variables of blasting vibration. It is also found that the precision of prediction single index a time is higher than that of prediction three indexes at the same time.