Prediction of Ground Vibration Induced by Rock Blasting Based on Optimized Support Vector Regression Models

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.

Novel Soft ComputingModel for Predicting Blast-Induced Ground Vibration in Open-Pit Mines Based on the Bagging and Sibling of Extra Trees Models

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.

Impact of orientation of blast initiation on ground vibrations

The blast-induced ground vibrations can be significantly controlled by varying the location and orien-tation of point of interest from blast site.The blast waves generated due to individual holes get super-imposed and resultant peak particle velocity(PPV)generates.With the orientation sequence of holes blasts on site,the superimposition angle of wave changes and hence results in significant variation in resultant PPV.The orientation with respect to the initiation of blasts resulting in lowest PPV needs to be identified for any site.By knowing the PPV contour of vibration waves in mine sites,it is possible to reduce the vibration on the structures by changing the initiation sequence.In this paper,experimental blasts were conducted at two different mine sites and the PPV values were recorded at different ori-entations from the blast site and its initiation sequence.The PPV contours were drawn to identify the orientation with least and highest PPV generation line.It was found that by merely changing the initi-ation sequence of blasts with respect to the sensitive structure or point of interest,the PPV values can be reduced significantly up to 76.9%.

Dynamic responses and failure mechanisms of the existing tunnel under transient excavation unloading of an adjacent tunnel

Engineering disasters(e.g.rock slabbing and rockburst)of the tunnel groups induced by the transient excavation of an adjacent tunnel threaten the stability of the existing tunnel,especially for those excavated by using the drill and blast tunneling(D&B).However,the dynamic response and failure mechanism of surrounding rocks of the existing tunnel caused by adjacent transient excavation are not clear due to the difficulty in conducting field tests and laboratory experiments.Therefore,a novel transient unloading experimental system for deep tunnel excavation was proposed in this study.The real stress path and the unloading rate can be reproduced by using this proposed system.The experiments were conducted for observing the dynamic response of the existing tunnel induced by adjacent transient excavation under different lateral pressure coefficients l(?0.4,0.6,0.8,1,1.2,1.4,1.6,1.8)with a polymethyl methacrylate(PMMA)specimen.The propagation of the impact wave and unloading surface wave was detected through the digital image correlation(DIC)analysis.The reflection of the unloading surface wave on the incident side of the existing tunnel(tunnel-E)was observed and analyzed.Moreover,the dynamic characteristics of the stress redistribution,the particle displacement and vibration velocity of surrounding rocks of tunnel-E were analyzed and summarized.In addition,the Mohr-Coulomb(MeC)failure criterion with tension cut-off was adopted to evaluate the stability of the existing tunnel under adjacent transient excavation.The results indicate that the incident side of the existing tunnel under the dynamic disturbance of transient excavation of an adjacent tunnel was more prone to fail,followed by the shadow side and the top/bottom side.

Discussion on “Impact of orientation of blast initiation on ground vibrations” [J Rock Mech Geotech Eng 15 (2022) 255e261]

Recently,Garai et al.(2022)published a paper on the impact of orientation of blast initiation on ground vibrations.However,some of the claims are not supported by the results of the given tests.In Fig.1(see Fig.8 in Garai et al.,2022),there are contours of measured vibration velocities in 4 directions(every 90?)and an incorrect interpretation between them.By placing all measured vibration velocity values(Gerai et al.,2022)at well-defined points on a single figure,it was not possible to precisely determine the type of vibration velocity,such as radial,tangential and vertical vibration velocities,with their different shapes.An incorrect conclusion was also drawn about the direction of the highest vibration velocity.The paper by Garai et al.(2022)measured the vibrational velocity of the medium through which the seismic wave passed,but used the incorrect term shock wave.The shock wave would have destroyed the seismic measuring instruments.A superposition of the vibrational velocity was considered,but not combined with the vibrational frequency of the seismic wave.This paper presents a method for selecting the time delay between successively initiated explosive charges to the measured frequency of the seismic wave,so that the direction of initiation of the explosive charges does not affect the vibration velocity of the ground through which the seismic wave passes.The theoretical and measured shapes and waveforms of radial velocity and tangential velocity in an opencast lignite mine are then presented.Moreover,the conditions for the formation of shock wave,transition wave and seismic waves are presented.

Influence of millisecond time,charge length and detonation velocity on blasting vibration

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.

Study of blasting vibrations in Sarcheshmeh copper mine

Ground vibration is one of the side effects of blasting, in which way considerable amount of explosive energy is exhausted, and causes decrease in production and even decline in mine development workings. In this study, 57 recorded 3-C seismograms from 11 blasts in Sarcheshmeh copper mine, Kerman, Iran, are processed and analyzed. These data were recorded by digital seismograph PDAS-100 and analyzed by DADISP software. Finally, blasting parameters, such as explosive weight and type, distance between the structures and blasting site, blasting delays, affecting ground vibration are reviewed and their influence on peak particle velocity (PPV) are studied. Based on this study, suitable detonation delays and explosive type is determined. Considering these data, a graph of PPV versus scaled distance for Sarcheshmeh copper mine is prepared, by the help of which, safe distance for structures and accordingly explosive quantity could be determined.

Study on influencing factors and prediction of peak particle velocity induced by roof pre-split blasting in underground

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.