The law of blasting vibration caused by blasting in rock is very complex.Traditional numerical methods cannot well characterize all the influencing factors in the blasting process.The effects of millisecond time,charg...The law of blasting vibration caused by blasting in rock is very complex.Traditional numerical methods cannot well characterize all the influencing factors in the blasting process.The effects of millisecond time,charge length and detonation velocity on the blasting vibration are discussed by analyzing the characteristics of vibration wave generated by finite length cylindrical charge.It is found that in multi-hole millisecond blasting,blasting vibration superimpositions will occur several times within a certain distance from the explosion source due to the propagation velocity difference of P-wave and S-wave generated by a short column charge.These superimpositions will locally enlarge the peak velocity of blasting vibration particle.The magnitude and scope of the enlargement are closely related to the millisecond time.Meanwhile,the particle vibration displacement characteristics of rock under long cylindrical charge is analyzed.The results show that blasting vibration effect would no longer increase when the charge length increases to a certain extent.This indicates that the traditional simple calculation method using the maximum charge weight per delay interval to predict the effect of blasting vibration is unreasonable.Besides,the effect of detonation velocity on blasting vibration is only limited in a certain velocity range.When detonation velocity is greater than a certain value,the detonation velocity almost makes no impact on blasting vibration.展开更多
Blasting technology is widely used to prevent coal bursts by presplitting the overburden in underground coal mines.The control of blasting intensity is important in achieving the optimal pre-split effectiveness and re...Blasting technology is widely used to prevent coal bursts by presplitting the overburden in underground coal mines.The control of blasting intensity is important in achieving the optimal pre-split effectiveness and reducing the damage to roadway structures that are subjected to blasting vibrations.As a critical parameter to measure the blasting intensity,the peak particle velocity(PPV)of vibration induced by blasting,should be accurately predicted,and can provide a useful guideline for the design of blasting parameters and the evaluation of the damage.In this paper,various factors that influence PPV,induced by roof pre-split blasting,were analyzed using engineering blasting experiments and numerical simulations.The results showed that PPV was affected by many factors,including charge distribution design(total charge and maximum charge per hole),spacing of explosive centers,as well as propagation distance and path.Two parameters,average charge coefficient and spatial discretization coefficient were used to quantitatively characterize the influences of charge distribution and spacing of explosive centers on the PPV induced by roof pre-split blasting.Then,a model consisting of the combination of artificial neural network(ANN)and genetic algorithm(GA)was adopted to predict the PPV that was induced by roof presplit blasting.A total of 24 rounds of roof pre-split blasting experiments were carried out in a coal mine,and vibration signals were collected using a microseismic(MS)monitoring system to construct the neural network datasets.To verify the efficiency of the proposed GA-ANN model,empirical correlations were applied to predict PPV for the same datasets.The results showed that the GA-ANN model had superiority in predicting PPV compared to empirical correlations.Finally,sensitivity analysis was performed to evaluate the impacts of input parameters on PPV.The research results are of great significance to improve the prediction accuracy of PPV induced by roof pre-splitting blasting.展开更多
Accurately estimating blasting vibration during rock blasting is the foundation of blasting vibration management.In this study,Tuna Swarm Optimization(TSO),Whale Optimization Algorithm(WOA),and Cuckoo Search(CS)were u...Accurately estimating blasting vibration during rock blasting is the foundation of blasting vibration management.In this study,Tuna Swarm Optimization(TSO),Whale Optimization Algorithm(WOA),and Cuckoo Search(CS)were used to optimize two hyperparameters in support vector regression(SVR).Based on these methods,three hybrid models to predict peak particle velocity(PPV)for bench blasting were developed.Eighty-eight samples were collected to establish the PPV database,eight initial blasting parameters were chosen as input parameters for the predictionmodel,and the PPV was the output parameter.As predictive performance evaluation indicators,the coefficient of determination(R2),rootmean square error(RMSE),mean absolute error(MAE),and a10-index were selected.The normalizedmutual information value is then used to evaluate the impact of various input parameters on the PPV prediction outcomes.According to the research findings,TSO,WOA,and CS can all enhance the predictive performance of the SVR model.The TSO-SVR model provides the most accurate predictions.The performances of the optimized hybrid SVR models are superior to the unoptimized traditional prediction model.The maximum charge per delay impacts the PPV prediction value the most.展开更多
This study considered and predicted blast-induced ground vibration(PPV)in open-pit mines using bagging and sibling techniques under the rigorous combination of machine learning algorithms.Accordingly,four machine lear...This study considered and predicted blast-induced ground vibration(PPV)in open-pit mines using bagging and sibling techniques under the rigorous combination of machine learning algorithms.Accordingly,four machine learning algorithms,including support vector regression(SVR),extra trees(ExTree),K-nearest neighbors(KNN),and decision tree regression(DTR),were used as the base models for the purposes of combination and PPV initial prediction.The bagging regressor(BA)was then applied to combine these base models with the efforts of variance reduction,overfitting elimination,and generating more robust predictive models,abbreviated as BA-ExTree,BAKNN,BA-SVR,and BA-DTR.It is emphasized that the ExTree model has not been considered for predicting blastinduced ground vibration before,and the bagging of ExTree is an innovation aiming to improve the accuracy of the inherently ExTree model,as well.In addition,two empirical models(i.e.,USBM and Ambraseys)were also treated and compared with the bagging models to gain a comprehensive assessment.With this aim,we collected 300 blasting events with different parameters at the Sin Quyen copper mine(Vietnam),and the produced PPV values were also measured.They were then compiled as the dataset to develop the PPV predictive models.The results revealed that the bagging models provided better performance than the empirical models,except for the BA-DTR model.Of those,the BA-ExTree is the best model with the highest accuracy(i.e.,88.8%).Whereas,the empirical models only provided the accuracy from 73.6%–76%.The details of comparisons and assessments were also presented in this study.展开更多
基金Project(50878123)supported by the National Natural Science Foundation of ChinaProject(20113718110002)supported by the Specialized Research Fund for the Doctoral Program of Higher Education of China+1 种基金Project(DPMEIKF201307)supported by the Fund of the State key Laboratory of Disaster Prevention&Mitigation of Explosion&Impact(PLA University and Technology),ChinaProject(13BS402)supported by Huaqiao University Research Foundation,China
文摘The law of blasting vibration caused by blasting in rock is very complex.Traditional numerical methods cannot well characterize all the influencing factors in the blasting process.The effects of millisecond time,charge length and detonation velocity on the blasting vibration are discussed by analyzing the characteristics of vibration wave generated by finite length cylindrical charge.It is found that in multi-hole millisecond blasting,blasting vibration superimpositions will occur several times within a certain distance from the explosion source due to the propagation velocity difference of P-wave and S-wave generated by a short column charge.These superimpositions will locally enlarge the peak velocity of blasting vibration particle.The magnitude and scope of the enlargement are closely related to the millisecond time.Meanwhile,the particle vibration displacement characteristics of rock under long cylindrical charge is analyzed.The results show that blasting vibration effect would no longer increase when the charge length increases to a certain extent.This indicates that the traditional simple calculation method using the maximum charge weight per delay interval to predict the effect of blasting vibration is unreasonable.Besides,the effect of detonation velocity on blasting vibration is only limited in a certain velocity range.When detonation velocity is greater than a certain value,the detonation velocity almost makes no impact on blasting vibration.
基金the Postgraduate Research&Practice Innovation Program of Jiangsu Province,China(Grant No.KYCX21_2378)National Natural Science Foundation of China(Grant Nos.51874292 and 51804303).
文摘Blasting technology is widely used to prevent coal bursts by presplitting the overburden in underground coal mines.The control of blasting intensity is important in achieving the optimal pre-split effectiveness and reducing the damage to roadway structures that are subjected to blasting vibrations.As a critical parameter to measure the blasting intensity,the peak particle velocity(PPV)of vibration induced by blasting,should be accurately predicted,and can provide a useful guideline for the design of blasting parameters and the evaluation of the damage.In this paper,various factors that influence PPV,induced by roof pre-split blasting,were analyzed using engineering blasting experiments and numerical simulations.The results showed that PPV was affected by many factors,including charge distribution design(total charge and maximum charge per hole),spacing of explosive centers,as well as propagation distance and path.Two parameters,average charge coefficient and spatial discretization coefficient were used to quantitatively characterize the influences of charge distribution and spacing of explosive centers on the PPV induced by roof pre-split blasting.Then,a model consisting of the combination of artificial neural network(ANN)and genetic algorithm(GA)was adopted to predict the PPV that was induced by roof presplit blasting.A total of 24 rounds of roof pre-split blasting experiments were carried out in a coal mine,and vibration signals were collected using a microseismic(MS)monitoring system to construct the neural network datasets.To verify the efficiency of the proposed GA-ANN model,empirical correlations were applied to predict PPV for the same datasets.The results showed that the GA-ANN model had superiority in predicting PPV compared to empirical correlations.Finally,sensitivity analysis was performed to evaluate the impacts of input parameters on PPV.The research results are of great significance to improve the prediction accuracy of PPV induced by roof pre-splitting blasting.
基金financially supported by the NationalNatural Science Foundation of China(Grant No.42072309)the Fundamental Research Funds for National University,China University of Geosciences(Wuhan)(Grant No.CUGDCJJ202217)+1 种基金the Knowledge Innovation Program of Wuhan-Basic Research(Grant No.2022020801010199)the Hubei Key Laboratory of Blasting Engineering Foundation(HKLBEF202002).
文摘Accurately estimating blasting vibration during rock blasting is the foundation of blasting vibration management.In this study,Tuna Swarm Optimization(TSO),Whale Optimization Algorithm(WOA),and Cuckoo Search(CS)were used to optimize two hyperparameters in support vector regression(SVR).Based on these methods,three hybrid models to predict peak particle velocity(PPV)for bench blasting were developed.Eighty-eight samples were collected to establish the PPV database,eight initial blasting parameters were chosen as input parameters for the predictionmodel,and the PPV was the output parameter.As predictive performance evaluation indicators,the coefficient of determination(R2),rootmean square error(RMSE),mean absolute error(MAE),and a10-index were selected.The normalizedmutual information value is then used to evaluate the impact of various input parameters on the PPV prediction outcomes.According to the research findings,TSO,WOA,and CS can all enhance the predictive performance of the SVR model.The TSO-SVR model provides the most accurate predictions.The performances of the optimized hybrid SVR models are superior to the unoptimized traditional prediction model.The maximum charge per delay impacts the PPV prediction value the most.
基金funded by Vietnam National Foundation for Science and Tech-nology Development(NAFOSTED)under Grant No.105.99-2019.309.
文摘This study considered and predicted blast-induced ground vibration(PPV)in open-pit mines using bagging and sibling techniques under the rigorous combination of machine learning algorithms.Accordingly,four machine learning algorithms,including support vector regression(SVR),extra trees(ExTree),K-nearest neighbors(KNN),and decision tree regression(DTR),were used as the base models for the purposes of combination and PPV initial prediction.The bagging regressor(BA)was then applied to combine these base models with the efforts of variance reduction,overfitting elimination,and generating more robust predictive models,abbreviated as BA-ExTree,BAKNN,BA-SVR,and BA-DTR.It is emphasized that the ExTree model has not been considered for predicting blastinduced ground vibration before,and the bagging of ExTree is an innovation aiming to improve the accuracy of the inherently ExTree model,as well.In addition,two empirical models(i.e.,USBM and Ambraseys)were also treated and compared with the bagging models to gain a comprehensive assessment.With this aim,we collected 300 blasting events with different parameters at the Sin Quyen copper mine(Vietnam),and the produced PPV values were also measured.They were then compiled as the dataset to develop the PPV predictive models.The results revealed that the bagging models provided better performance than the empirical models,except for the BA-DTR model.Of those,the BA-ExTree is the best model with the highest accuracy(i.e.,88.8%).Whereas,the empirical models only provided the accuracy from 73.6%–76%.The details of comparisons and assessments were also presented in this study.
