Blasting vibration hazard classification and prediction research

This paper explores the hazard classification method of blasting vibration on nearby buildings. The ratio self-vibration frequency f 0 protected buildings to main and actual measured peak velocity permissible safety regulations are used as two indicators method, index calculation formula was proposed, classified into four levels according index. An open pit mine project for monitoring, collected data were processed by random forest method. After processing, bursting heart distance, total explosive quantity required one blast, hole distance meter delay, row delay selected input parameters; optimal kernel function parameter gamma c applied SVR (Support Vector Regression) model changing search step expand search, improved GS-SVR (Grid Search-Support constructed, through which values predicted. results show: is effective in predicting velocity, with lowest relative error 0.15% average 7.96%; minimum prediction 0.03% 2.54%. literature related scholars verified that scientific feasible. It can provide reference similar projects.