Blasting vibrations in open-pit mines can potentially lead to damage in surrounding rock formations,slope instability,ground fissures,and structural damage to buildings. Additionally,these vibrations may disrupt the daily activities and safety of nearby residents and facilities. Accurate prediction of blasting vibrations is essential for scientifically assessing their impact on the surrounding environment and infrastructure,optimizing blasting design parameters,ensuring construction safety,and providing informed decision-making support. Currently,in China,the assessment and verification of blasting vibration safety primarily focus on peak particle velocity and particle frequency. However,relying solely on these parameters as safety criteria is insufficiently reliable. A comprehensive evaluation of the entire blasting vibration process is necessary to objectively assess its characteristics and effects. Consequently,the prediction of blasting vibration waveforms has emerged as a significant area of research. The waveform of blasting vibrations in open-pit mines is influenced by various factors,including geological terrain,blasting parameters,and charge structure.Accurately predicting the waveform of blasting vibrations holds significant practical importance for the analysis of blasting vibration velocity,frequency,duration,and the design and evaluation of safety measures. To facilitate the prediction of blasting vibration waveforms in open-pit mines,this study proposes a novel method that integrates the characteristic value U, representing the distance from the blast source(R), with principal component analysis (PCA) and a backpropagation(BP) neural network. Initially,this method involves extracting the extreme values from the blasting vibration waveform data and defining an idealized feature value U for R, establishing a corresponding relationship between R and the vibration signal waveform. PCA is employed to conduct a principal component analysis on variables such as step height,R,and explosive consumption,ultimately reducing these variables to two principal components. These components, combined with U, serve as input parameters for the BP neural network,while the corresponding vibration velocities at each time point in the waveform are utilized as output parameters. Extreme value prediction was conducted on the blasting vibration waveform,and the predicted waveform was derived through interpolation calculations. The findings of the study demonstrate that,when comparing the predicted results with the empirical data,the PCA-BP model exhibits a closer approximation to zero than the BP model in terms of root mean square error (RMSE) and mean absolute error (MAE). Furthermore,the relative error in the peak vibration velocity predicted by the PCA-BP model is less than 11%,and the absolute error in the main frequency is less than 10 Hz. The predictive accuracy of the PCA-BP model surpasses that of the BP model,thereby confirming the model’s accuracy and reliability. This method offers an enhanced capability for predicting blasting vibration waveforms in open-pit mines under consistent topographical,geomorphological,and geological conditions,thereby providing a significant reference for blasting design and safety assessment.
Álvarez-VigilA E, González-NiciezaC, López GayarreF,et al,2012.Predicting blasting propagation velocity and vibration frequency using artificial neural networks[J].International Journal of Rock Mechanics and Mining Sciences,55:108-116.
[2]
AndersonD A, RitterA P, WinzerS R,et al,1985. A method for site-specific prediction and control of ground vibration from blasting[C]//Proceedings of the First Mini-Symposium on Explosives and Blasting Research. San Diego: Society of Explosives Engineers.
[3]
BakhshandehA H, MozdianfardM R, SiamakiA,2010.Predicting of blasting vibrations in Sarcheshmeh copper mine by neural network[J].Safety Science,48(3):319-325.
[4]
BlairD P,2008.Non-linear superposition models of blast vibration[J].International Journal of Rock Mechanics and Mining Sciences,45(2):235-247.
[5]
DindarlooS R,2015.Prediction of blast-induced ground vibrations via genetic programming[J].International Journal of Mining Science and Technology,25(6):1011-1015.
[6]
DongL J, LiX B, XuM,et al,2011.Comparisons of random forest and support vector machine for predicting blasting vibration characteristic parameters[J].Procedia Engineering,26:1772-1781.
[7]
GhasemiE, AtaeiM, HashemolhosseiniH,2013.Development of a fuzzy model for predicting ground vibration caused by rock blasting in surface mining[J].Journal of Vibration and Control,19(5):755-770.
[8]
KhandelwalM, SinghT N,2009.Prediction of blast-induced ground vibration using artificial neural network[J].International Journal of Rock Mechanics and Mining Sciences,46(7):1214-1222.
[9]
SinghT N, DonthaL K, BhardwajV,2008.Study into blast vibration and frequency using ANFIS and MVRA[J].Mining Technology,117(3):116-121.
ChenQiusong, ZhangQinli, ChenXin,et al,2016.Prediction of blasting-vibration-peak-speed based on GRA-GEP[J].Journal of Central South University (Science and Technology),47(7):2441-2447.
ChenShihai, ChuShaofeng, GongJiachen,et al,2022.Blasting vibration response of sandstone tunnel surrounding rock under high ground stress[J].Journal of Vibration and Shock,41(17):73-80,92.
FeiHonglu, ZuoZhuangzhuang, JiangAnjun,et al,2023.Prediction of peak blasting vibration velocity based on KS-GS-SVR[J].Engineering Blasting,29(2):120-128.
[16]
雷振,2015.台阶爆破振动效应非线性预测方法研究及应用[D].北京:中国矿业大学(北京).Lei Zhen,2015.Research and application on nonlinear prediction methods of bench blasting vibration effect[D].Beijing:China University of Mining & Technology,Beijing.
LiQiyue, XiaoYuhang, WeiKuaikuai,et al,2024.Characterization of blasting vibration in open slopes[J].Gold Science and Technology,32(3):491-500.
[21]
廖晓目,2023.高陡边坡微差爆破振动主动控制与频谱特征研究[D].长沙:中南大学.Liao Xiaomu,2023.Study on active control and spectrum characteristics of millisecond blasting vibration in high and steep slope[D].Changsha:Central South University.
LiuXiaoming, ChenShihai,2020.Prediction of surface vibration waveforms and analysis of their effects in group-hole differential blasting[J].Chinese Journal of Geotechnical Engineering,42(3):551-560.
LouChuyun, LiuJun, LanPeng,2017.A predicting method for time domain waveform of blasting vibration based on spline interpolation [J].Engineering Blasting,23(2):24-31.
ShiJianjun, LiQingya, ZhangQi,et al,2017.Forecast system for blasting vibration velocity peak based on Matlab and BP neural network[J].Explosion and Shock Waves,37(6):1087-1092.
WangJiaxin, ZhouZonghong, LiKegang,et al,2017.A multi-parameter identification model for classification of rock burst risk and its application[J].Journal of China Coal Society,42():311-322.
[30]
王帅,2022.基于麻雀搜索算法优化的BP神经网络爆破振速峰值预测研究[D].阜新:辽宁工程技术大学.Wang Shuai,2022.Prediction of blasting vibration velocity peak value based on BP neural network optimized by sparrow search algorithm[D].Fuxin:Liaoning Technical University.
WangYong, TangXu, ZouFei,et al,2017.Research on application of blasting vibration characteristic parameters by SVM and predicting of neural network[J].Highway,62(4):12-17.
WenTingxin, ZhuChengwei, KongXiangbo,2015.Predicting analysis on damage to residential house by blasting vibration in open pit mining based on PCA-ELM model [J].China Safety Production Science and Technology,11(8):119-125.
[35]
徐芳妹,唐健,2014.爆破振动波形预测模型及应用[J].山西建筑,40(27):35-37.
[36]
XuFangmei, TangJian,2014.The prediction model and application of blasting vibration waveform [J].Shanxi Architecture,40(27):35-37.
[37]
徐全军,毛志远,张庆明,1998.深孔微差爆破震动预报浅析[J].爆炸与冲击,(2):87-91.
[38]
XuQuanjun, MaoZhiyuan, ZhangQingming,1998.The analysis of ground vibration prediction of delay-fired bench blasting [J].Explosion and Shock Waves,(2):87-91.
YanYongfeng, ChenShihai, ZhangAnkang,et al,2011.Optimization research on waveform prediction model of blasting vibration signal[J].Blasting,28(1):23-27.
ZhangPengfei, YuanYong, HeYunhua,et al,2025.Blasting vibration velocity prediction of open pit mines based on GRA-EPSO-SVM model[J].Coal Science and Technology,53(7):105-115.