王赟,薛大伟,汤万钧
WANG Yun,XUE Da-wei,TANG Wan-jun

• 1:中国煤炭科工集团太原研究院有限公司
• 2:皖北煤电集团
• 3:中国矿业大学矿业学院

摘要(Abstract)：

装载和运输成本占到露天矿运营总成本的50%以上,而爆破后岩石破碎程度直接影响到露天矿装载和运输成本。为了得到爆破参数和岩石破碎度之间的关系,收集了平朔东露天矿爆破参数和岩石破碎度数据,使用图像识别技术大规模收集分析爆破后岩块粒径分布,基于深度神经网络研究分析爆破参数和岩石破碎度之间的关系,建立了适用于东露天矿的爆破参数和破碎度的预测模型,并对爆破参数做敏感性分析,确立了炸药单耗和孔距是主要影响因素,并分别建立了炸药单耗和孔距与岩石破碎度之间的变化关系。研究结果可以指导矿山确定合理的穿孔和爆破参数以得到最佳的岩石破碎度,从而减少露天矿运营总成本。
Loading and transport costs constitute up to 50% of the total operational costs in open pit mines. Fragmentation of the rock after blasting is an important determinant of the cost associated with these two components of mine development.By collecting the data of blasting parameters and rock breakage of Pingshuo east open pit, based on the study of the relationship between blasting parameters and rock breakage based on deep neural network, a prediction model for blasting parameters and breakage suitable for east open pit mine is established, and the sensitivity analysis of blasting parameters is made and the single consumption of explosives is established. The distance between holes is the main factor, and then the relationship between explosive consumption and pore size and rock fragmentation is established according to the single factor analysis method. The results obtained in this study and the methodology introduced, can assist the mining design engineer to decide on a drilling and blasting pattern that produces the most suitable fragmentation of the blasted ore and hence minimize the total cost of the mining operations.

关键词(KeyWords)： 深度神经网络;爆破效果;破碎度;露天矿
deep neural network;blasting effect;fragmentation;open pit mine

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 王赟,薛大伟,汤万钧
WANG Yun,XUE Da-wei,TANG Wan-jun

参考文献(References)：

• [1]喻亚洲.基于GRNN的黄麦岭露夭矿爆破参数优化[J].现代矿业,2015,31(9):30-31,33.YU Y Z. Optimization of blasting parameters of Huangmailing Open-pit Mine based on GRNN[J].Modern Mining, 2015, 31(9):30-31, 33.
• [2]李洪超,刘殿书,李建丰,等.布沼坝露天矿爆破效果预测BP神经网络模型应用[J].工程爆破,2015,21(2):25-29,35.LI H C, LIU D S, LI J F, et al. Application of BP neural network model for blasting effect prediction in Buzhaoba Open-pit Mine[J]. Engineering Blasting,2015, 21(2):25-29, 35.
• [3]费志超.露天矿爆破震动效应分析与安全评价[D].包头:内蒙古科技大学,2014.FEI Z C. Blasting vibration effect analysis and safety evaluation of open pit mine[D]. Baotou:Inner Mongolia University of Science and Technology, 2014.
• [4]罗学东,范新宇,代贞伟,等.BP神经网络模型在露天矿爆破振动参数预测中的应用及修正[J].中南大学学报(自然科学版),2013,44(12):5 019-5 024.LUO X D, FAN X Y, DAI Z W, et al. Application and revision of BP neural network model in prediction of blasting vibration parameters of open pit mine[J].Journal of Central South University(Natural Science Edition), 2013, 44(12):5 019-5 024.
• [5]王涛.黄麦岭露天矿台阶爆破参数优化及爆破振动效应研究[D].武汉:武汉理工大学,2013.WANG T. The optimization of bench blasting parameters and the effect of blasting vibration in Huangmailing Open-pit Mine[D]. Wuhan:Wuhan University of Technology, 2013.
• [6]李家.人工神经网络在露天矿爆破参数优化中的应用研究[D].包头:内蒙古科技大学,2013.LI J. Application of artificial neural network in blasting parameter optimization of open-pit mine[D].Baotou:Inner Mongolia University of Science and Technology, 2013.
• [7]王创业,张飞天,韩万东.基于神经网络的露天矿爆破参数优化研究[J].金属矿山,2011(3):57-59.WANG C Y, ZHANG F T, HAN W D. Study on blasting parameters optimization of open pit mine based on neural network[J]. Metal Mine, 2011(3):57-59.
• [8]韩万东,曹华,李亮盼,等.马家塔露天矿爆破参数优化及效果分析[J].煤矿安全,2010,41(11):105-107.HAN W D, CAO H, LI L P, et al. Blasting parameters optimization and effect analysis of Majiata Open-pit Mine[J]. Coal Mine Safety, 2010, 41(11):105-107.
• [9]程良奎.地下矿山中深孔爆破设计专家系统研究[D].武汉:武汉科技大学,2004.CHENG L K. Research on expert system of mediumdeep hole blasting design in underground mines[D].Wuhan:Wuhan University of Science and Technology, 2004.
• [10]郭连军,王智静,牛成俊,等.爆破优化的神经网络模型[J].工程爆破,1996,2(2):11-15.GUO L J, WANG Z J, NIU C J, et al. Neural network model for blasting optimization[J].Engineering Blasting, 1996,2(2):11-15.