Prediction of blasting mean fragment size using support vector regression combined with five optimization algorithms

The main purpose of blasting operation is to produce desired and optimum mean size rock fragments. Smaller or fine fragments cause the loss of ore during loading and transportation, whereas large or coarser fragments need to be further processed, which enhances production cost. Therefore, accurate prediction of rock fragmentation is crucial in blasting operations. Mean fragment size (MFS) is a crucial index that measures the goodness of blasting designs. Over the past decades, various models have been proposed to evaluate and predict blasting fragmentation. Among these models, artificial intelligence (AI)-based models are becoming more popular due to their outstanding prediction results for multi-influential factors. In this study, support vector regression (SVR) techniques are adopted as the basic prediction tools, and five types of optimization algorithms, i.e. grid search (GS), grey wolf optimization (GWO), particle swarm optimization (PSO), genetic algorithm (GA) and salp swarm algorithm (SSA), are implemented to improve the prediction performance and optimize the hyper-parameters. The prediction model involves 19 influential factors that constitute a comprehensive blasting MFS evaluation system based on AI techniques. Among all the models, the GWO-v-SVR-based model shows the best comprehensive performance in predicting MFS in blasting operation. Three types of mathematical indices, i.e. mean square error (MSE), coefficient of determination (R²) and variance accounted for (VAF), are utilized for evaluating the performance of different prediction models. The R², MSE and VAF values for the training set are 0.8355, 0.00138 and 80.98, respectively, whereas 0.8353, 0.00348 and 82.41, respectively for the testing set. Finally, sensitivity analysis is performed to understand the influence of input parameters on MFS. It shows that the most sensitive factor in blasting MFS is the uniaxial compressive strength.     

松散破碎介质中气体渗流规律试验研究

 原地爆破浸出采场的铀矿堆,是一种松散破碎介质,其颗粒级配服从Rosin-Rammler分布。这种介质中的气体渗流同时受到介质的特征粒径、粒径分布指数和孔隙率的影响。为了研究这种影响,根据Rosin-Rammler分布,选配具有不同颗粒级配的7组试样,采用自制的松散破碎介质气体渗流试验装置,对其中气体渗流的规律进行试验研究,并利用试验结果,采用自适应神经模糊推理系统,建立根据特征粒径、粒径分布指数和孔隙率预测渗透率和惯性系数的自适应神经模糊推理系统(ANFIS)模型。结果表明：松散破碎介质中的气体渗流不满足Darcy定律,而满足Darcy-Forchheimer定律;所建立的预测渗透率和惯性系数的ANFIS模型,能够给出具有足够精度的预测结果,这为渗透率和惯性系数的预测开辟新的途径。     

Optimized blasting design for large-scale quarrying based on a 3-D spatial distribution of rock factor

Rock fragmentation plays a critical role in large-scale quarrying operations because of its direct effects on the costs of drilling, blasting, secondary blasting and crushing. In this aspect, it is essential to consider rock fragmentation in blasting design. The optimum blasting pattern to excavate a quarry efficiently and economically can be determined based on the minimum production cost which is generally estimated according to rock fragmentation. By comparing various prediction models, it can be ascertained that the results obtained from the Kuz–Ram model relatively coincide with the results from field measurements. This model uses the rock factor to signify conditions of rock mass such as block size, rock jointing, strength, and others. The rock factor is estimated from geologic data such as block size of rock mass, rock jointing, strength, and others, and its 3-D spatial distribution was predicted by a sequential indicator simulation (SIS) technique. The entire quarry in question was classified into three types of rock mass and an optimum blasting pattern was proposed for each type based on the 3-D spatial distribution of the rock factor. It can, therefore, be concluded that it is possible to design a blasting pattern to achieve a minimum production cost in large-scale quarrying operations by predicting rock fragmentation based on the 3-D spatial distribution of the rock factor.     

楔形掏槽微差爆破模型试验与分析

针对煤矿硬岩巷道掘进掏槽效果差、炮眼利用率低的难题,采用混凝土作为相似材料进行不同掏槽方式的模型试验研究。从掏槽体积、炮眼利用率、破碎块度等方面分析不同掏槽方式的爆破效果。采用楔形微差掏槽,中间炮眼比掏槽眼深200 mm,装1～2支药卷,其余长度用水炮泥和炮泥封堵,起爆雷管为2段。试验结果表明,中间炮眼增加自由面,有利于克服岩石的夹制作用,保证在掏槽眼先爆的基础上,把掏槽的残岩进一步抛出;微差爆破延长爆轰气体在炮眼内的作用时间,爆破的块度小,分布均匀,从而提高炮眼利用率和掏槽体积。     

基于原生节理统计和爆破裂纹模拟的堆石料块度分布预测

 水电工程堆石料爆破级配要求高、块度预测难,以岩体原生节理统计和爆破裂纹模拟为切入点,采用现场调查、室内试验、数值仿真和工程检验等方式,开展堆石料爆破块度分布研究,尝试建立一套堆石料爆破块度预测方法。通过现场调查,绘制研究区域的天然节理分布网络图,建立基于原生节理统计的三维节理岩体模型;通过SHPB试验装置获取岩石在冲击荷载作用下的动力学参数,利用Ansys/Ls-Dyna模拟了爆破裂纹的扩展范围;综合原生节理调查信息和爆破裂纹模拟成果,建立调查区域爆后三维节理岩体模型;利用ANSYS输出模型所有岩块的线–面–体数据并编制Matlab块度计算程序,采用基于爆破岩块第5条最长边的块度预测指标,得到调查岩体的预测级配曲线。工程应用表明,综合考虑原生节理和爆破次生裂纹联合切割作用的堆石料级配预测方法基本符合工程实际,且基于爆破岩块第5条最长边指标的级配预测结果要优于等体积球直径指标的级配预测结果,其在江咀料场级配预测中的整体误差为5.5%。研究可为类似工程的堆石料爆破开采提供可借鉴的级配预测手段。     

Prediction of rock fragmentation due to blasting in Gol-E-Gohar iron mine using fuzzy logic

Usually, the rock fragmentation is used in the mining industry as an index to estimate the effect of bench blasting. However, a good fragmentation is a concept that it mainly depends on the downstream process characteristics i.e. mucking equipment, processing plant, mining goal etc. As a matter of fact, the fragmentation has a direct effect on the costs of drilling and blasting as well as economics of the subsequent operations. Using regression analysis and fuzzy inference system (FIS), the present paper tries to develop predictive models in order to predict fragmentation caused by blasting at Gol-E-Gohar iron mine. It is worth mentioning that the rock fragmentation is influenced by various parameters such as rock mass properties, blast geometry and explosive properties. With regard to the aforementioned fuzzy system, the paper prepares a database of the blasting operations, which includes burden, spacing, hole-depth, specific drilling, stemming length, charge-per-delay, rock density and powder factor as input parameters and fragmentation as output parameter. Since the explosive was unchanged in all the blasts, therefore, it cannot be considered. To validate and compare the obtained results, determination coefficient (R²) and root mean square error (RMSE) index are chosen and calculated for both the models. It is observed that the fuzzy predictor performs, significantly, better than the statistical method. For the fuzzy model, R² and RMSE are equal to 0.96 and 3.26, respectively, whereas for regression model, they are 0.80 and 6.83, respectively.     

最小抵抗线对岩石破碎块度影响的能量分析

运用分形理论对台阶爆破块度分布规律进行描述,将断裂力学理论与块度分布规律结合推导了台阶爆破岩石破碎能计算方法。基于相似理论浇筑台阶模型并进行爆破试验,研究不同最小抵抗线条件下台阶爆破岩石块度分布规律、岩石破碎能变化规律,试验结果表明:岩块分形维数随最小抵抗线增大呈线性降低,并且分形维数越小,块度评价指标K₈₀、K越大,岩石破碎效果越差;炸药爆炸能量仅有5%~8%用于岩石断裂破碎,岩石破碎能随最小抵抗线增大呈现出二次函数的变化趋势。将块度分布变化规律与破碎能变化规律相结合评价岩石破碎效果,得到了试验最佳最小抵抗线范围,依据相似准则获得了矿山台阶的最佳最小抵抗线范围,对于矿山生产具有一定的指导意义。     

Velocity of detonation measurement and fragmentation analysis to evaluate blasting efficacy

In holes, the measurement of the velocity of detonation (VOD) helps in comparing and evaluating relative performance of explosives. In this paper a blast performance assessment was conducted based on the results obtained from the steady state VOD measurement of emulsion explosives HEF100 and degree of blast fragmentation conducted on an open pit blast. The aim of this study was to compare the steady state VOD measured in the field and the published VOD of HEF100 under ideal laboratory conditions and ascertain its efficacy. In the trial, a resistance wire continuous VOD measurement system connected to a SpeedVOD was employed to measure and record the steady state VOD values from five different blast holes. Furthermore, a post fragmentation analysis was conducted using the existing fragmentation models and an image processing software. The steady state VOD values recorded from the field ranged between 4981 m/s to 5387 m/s consistent with the published VOD subjected to ideal laboratory conditions and the analyzed fragmentation size distribution indicates that 90% of the blasted muck pile was within the allowable and optimal 700 mm passing size.     

Rock fragmentation control in opencast blasting

The blasting operation plays a pivotal role in the overall economics of opencast mines.The blasting subsystem affects all the other associated sub-systems,i.e.loading,transport,crushing and milling operations.Fragmentation control through effective blast design and its effect on productivity are the challenging tasks for practicing blasting engineer due to inadequate knowledge of actual explosive energy released in the borehole,varying initiation practice in blast design and its effect on explosive energy release characteristic.This paper describes the result of a systematic study on the impact of blast design parameters on rock fragmentation at three mines in India.The mines use draglines and shoveledumper combination for removal of overburden.Despite its pivotal role in controlling the overall economics of a mining operation,the expected blasting performance is often judged almost exclusively on the basis of poorly defined parameters such as powder factor and is often qualitative which results in very subjective assessment of blasting performance.Such an approach is very poor substitutes for accurate assessment of explosive and blasting performance.Ninety one blasts were conducted with varying blast designs and charging patterns,and their impacts on the rock fragmentation were documented.A high-speed camera was deployed to record the detonation sequences of the blasts.The efficiency of the loading machines was also correlated with the mean fragment size obtained from the fragmentation analyses.     

Optimizing overbreak prediction based on geological parameters comparing multiple regression analysis and artificial neural network

Underground mining becomes more efficient due to the technological advancements of drilling and blasting methods and the developing of highly productive mining methods that facilitate easier access to ore. In the perspective of maximizing productivity in underground mining by drilling and blasting methods, overbreak control is an essential component. The causing factors of overbreak can simply divided as blasting and geological parameters and all of the factors are nonlinearly correlated. In this paper, the blasting design of the tunnel was fixed as the standard blasting pattern and the research focus on effects of geological parameters to the overbreak phenomenon. 49 sets of rock mass rating (RMR) and overbreak data were applied to linear and nonlinear multiple regression analysis (LMRA and NMRA) and artificial neural network (ANN) to predict overbreak as input and output parameters, respectively. The performance of LMRA, NMRA, and optimized ANN models was evaluated by comparing coefficient correlations (R²) and their values are 0.694, 0.704 and 0.945, respectively, which means that the relatively high level of accuracy of the optimized ANN in comparison with LMRA and NMRA. The developed optimum overbreak predicting ANN model is suitable for establishing an overbreak warning and preventing system and it will utilize as a foundation reference for a practical drift blasting reconciliation at mines for operation improvements.     

Das Großraum-Grundwassermodell Rurscholle

A multilevel groundwater model was developed for the geological unit Rurscholle to forecast the impact of drainage from open pit mines on the groundwater balance and to evaluate measures to protect wetlands influenced by the drainage. The numerical model is based on a quasi-3D finite element scheme. Geological faults, wetlands, and the open pit mines are considered by a local mesh refinement. A special feature of the modelling of the open pit mines is the temporal change of the soil parameters caused by the mining process. The calibration challenges included the size of the modelling area and drainage wells with well filters in more than one aquifer. In order to reduce the number of calibration parameters, the soil parameters are divided into zones. The calibration results are presented and evaluated with examples.     

基于岩碴粒径分布规律的TBM破岩效率分析

岩碴的形状、大小及其粒径分布规律是综合反映TBM破岩效率的重要指标,也是TBM掘进参数与岩石性质的重要联系。根据盘形滚刀破岩机制,对TBM掘进岩碴进行了现场量测和筛分试验,获得了TBM岩碴尺寸特征和粒径分布规律。在此基础上,对实测岩碴尺寸和粒径分布数据进行了统计分析和理论分布函数拟合。分析了粗糙度指数与岩石强度、岩石耐磨性的关系,探讨了不同围岩等级下粗糙度指数随掘进推力的变化规律。研究结果表明:①片状岩碴的长轴与短轴之比约为1.5,而长轴与厚度之比则差别较大,其长轴、短轴和厚度均服从正态分布;②不同岩性条件下岩碴粒径分布均符合Rosin–Rammler函数分布;③岩碴粗糙度指数越大,TBM破岩效率越高;硬岩条件下岩碴粗糙度指数随单轴饱和抗压强度增大而减小,而中硬—软岩条件下则相反;④无论是软岩还是硬岩,岩碴粗糙度指数随岩石耐磨性增大而减小,岩石耐磨性越强,TBM破岩效率越低;⑤TBM破岩效率与围岩等级密切相关,可根据现场实测岩碴粒径分布规律,确定Ⅱ级和Ⅲ级围岩条件下TBM破岩效率最佳时的掘进推力区间。     

Flyrock in bench blasting: a comprehensive review

Flyrock is unwanted throw of rock fragments during bench blasting in mines and civil constructions. Perfunctory attempts by researchers to predict the flyrock range using mathematical, empirical and ANN based models do not address the issue in totality. Thus, flyrock continues to haunt the blaster. The research on the subject is, thus, still in its infancy. This paper identifies the lacunae, through a comprehensive review of the existing models, and suggests measures for better prediction and understanding of the problem on a holistic plane. One of the main reasons for improper predictions is the lack of data on flyrock in comparison to blast vibrations owing to statutory restrictions, avoidance of reporting and consequent constraints on experimentation. While fragmentation and throw of rock accompanied by subsequent vibration and air overpressure are essential constituents of the blasting, flyrock is not. This probably is one of the main errors in predictive domains. In addition, rock mass properties play a major role in heaving of rock fragments during blasting. Barring density of the rock, other rock mass properties have practically been ignored in all the models. At the end of this paper, for future investigations, a methodology for prediction of flyrock is also given.     

A comparative study on the application of various artificial neural networks to simultaneous prediction of rock fragmentation and backbreak

In blasting operation, the aim is to achieve proper fragmentation and to avoid undesirable events such as backbreak. Therefore, predicting rock fragmentation and backbreak is very important to arrive at a technically and economically successful outcome. Since many parameters affect the blasting results in a complicated mechanism, employment of robust methods such as artificial neural network may be very useful. In this regard, this paper attends to simultaneous prediction of rock fragmentation and backbreak in the blasting operation of Tehran Cement Company limestone mines in Iran. Back propagation neural network (BPNN) and radial basis function neural network (RBFNN) are adopted for the simulation. Also, regression analysis is performed between independent and dependent variables. For the BPNN modeling, a network with architecture 6-10-2 is found to be optimum whereas for the RBFNN, architecture 6-36-2 with spread factor of 0.79 provides maximum prediction aptitude. Performance comparison of the developed models is fulfilled using value account for (VAF), root mean square error (RMSE), determination coefficient (R²) and maximum relative error (MRE). As such, it is observed that the BPNN model is the most preferable model providing maximum accuracy and minimum error. Also, sensitivity analysis shows that inputs burden and stemming are the most effective parameters on the outputs fragmentation and backbreak, respectively. On the other hand, for both of the outputs, specific charge is the least effective parameter.     

GPS-RTK技术及其在露天矿边坡位移监测中的应用

高陡边坡的稳定性一直是露天矿开采中倍受关注的重要安全问题之一。露天矿高陡边坡在发生跨塌破坏前,会有一个缓慢的位移过程发生。因此,通过对高陡边坡微小位移的监测可以实现对其发生灾难性跨塌的预测。本文讨论了露天矿边坡位移传统监测方法的缺陷及新型的基于GPS的自动监测技术所具有的独特优势,介绍了适用于露天矿边坡位移监测的高精度的GPS技术—RTK技术,阐明了基于GPS-RTK的露天矿边坡位移自动监测系统、边坡安全预警准则及监测实施的基本原则。旨在为相关研究与应用提供有益的借鉴。     

复杂环境中深基坑的爆破开挖

根据工程处于复杂地理环境中的特点,通过试验性实施及适时优化,采用静力爆破与动力爆破相组合的方式进行深基坑中风化岩带的爆破与开挖,有效地限制约束边坡的位移发展,从而保证深基坑一次性爆破开挖成功.其中,动力爆破与静力爆破的区域划分是通过爆点距周边重要建筑物不同距离进行的安全用药量精确计算确定的.通过科学的施工管理,本工程最终取得了良好的效果.     

紫金山露天台阶爆破设计及施工管理

紫金山露天矿台阶爆破设计在实际工程中取得了很好的爆破效果,本文主要是叙述紫金山台阶爆破的爆破参数、网络连接及现场施工组织管理,为其他工程地质相近的露天矿提供科学合理的爆破设计参考。     

某金铜矿露天开采爆破震动对边坡影响之测试分析

为了解采场正常生产爆破产生的动力效应对边坡产生的影响,摸清边坡爆破开挖的动力响应规律,在紫金山金铜矿,采用施工现场爆破振动测试结果分析和数据回归分析相结合的方法,对露采边坡进行分析研究,结果显示:临近边坡控制爆破总药量并合理设计起爆顺序,在靠帮和并段爆破采用预裂爆破方法,将有利于形成完整台阶,减小爆破后冲对台阶的直接破坏,把正常的生产爆破对边坡稳定所造成的不利影响程度降到最小。     

岩石动态损伤特性实验及爆破模型

 探索岩石动态损伤参量及其演化表征方式以构造岩石爆破损伤模型。通过岩石冲击损伤实验,对冲击前后试件进行超声波测试, 得出岩石动态损伤与超声波衰减规律的关系。在考虑岩石冲击损伤过程的声波衰减规律及其与能量耗散率关系的基础上, 建立新的岩石爆破损伤模型。通过实验验证该模型的计算结果并实现了岩石台阶爆破数值计算。