矿山预裂爆破效果预测的BP神经网络法

详细信息    查看全文 | 推荐本文 |

英文篇名：Prediction of Pre-split Blasting Effect Based on BP Neural Network 作者：齐留洋 ; 王德胜 ; 刘占全 ; 崔凤 ; 徐晓东 ; 郭建新 英文作者：Qi Liuyang;Wang Desheng;Liu Zhanquan;Cui Feng;Xu Xiaodong;Guo Jianxin;Civil and Resource Engineering School,University of Science and Technology Beijing;Barun Mining branch,Baotou Steel Union Co.,Ltd.; 关键词：露天开采 ; 预裂爆破 ; 效果预测 ; BP神经网络 ; 预测精度 英文关键词：Open-pit mining;;Pre-splitting blasting;;Effect prediction;;BP neural network;;Prediction accuracy 中文刊名：JSKS 英文刊名：Metal Mine 机构：北京科技大学土木与资源工程学院;包钢钢联巴润矿业分公司; 出版日期：2019-07-15 出版单位：金属矿山 年：2019 期：No.517 语种：中文; 页：JSKS201907011 页数：5 CN：07 ISSN：34-1055/TD 分类号：70-74

摘要

为简化矿山预裂爆破效果预测环节、提高预测精准度,针对传统预裂爆破效果评价注重预裂坡面成型的不足,考虑到露天矿山边坡时常受到爆破破岩振动等动态荷载影响的特点,结合BP神经网络,提出了既考虑坡面成型标准又顾及爆破振动对边坡影响的矿山预裂效果预测方法。将单孔装药量、平均孔深、孔距、振动速度峰值(水平、垂直)、振动主频(水平、垂直)、爆心距等参数作为神经网络输入参数,将预裂坡面的平均振动速度、半孔率、不平整度、裂隙系数等参数作为神经网络输出参数。基于24次临近边坡的爆破技术数据建立了矿山预裂爆破效果的BP神经网络预测模型。3次现场爆破预测试验表明:通过神经网络内部的自组织结构,将岩石性质、工程地质条件等与控制预裂爆破效果有关的因素进行简化,可将平均振动速度的预测相对误差控制在7%左右,将半孔率、不平整度、裂隙系数的预测相对误差控制在3%左右,对于提高爆破预裂效果的预测精度有一定的参考价值。
        In order to simplify the prediction process of mine pre-split blasting effect and improve the accuracy of prediction,in view of the traditional effect of pre-split blasting,which focuses on the defects of pre-split slope formation,considering that the slope of open-pit mine is often affected by the dynamic load such as blasting rock vibration,a neural network prediction method of mine pre-splitting effect based on considering both the slope forming standard and the impact of blasting vibration on slope is proposed.The parameters such as single hole charge,average hole depth,hole spacing,peak vibration velocity(horizontal,vertical),main vibration frequency(horizontal,vertical),blasting distance and so on are used as input parameters of neural network.Parameters such as average vibration speed,half-hole rate,roughness and fracture coefficient are taken as the output parameters of the neural network.An prediction method of mine pre-splitting blasting effect is established based on 24 blasting technical data of adjacent slope.3 on-site blasting prediction test results show that the rock properties,engineering geological conditions an other factors related to the control of pre-splitting blasting effect are simplified and integrated into the neural network by its self-organizing structure.Therefore,the relative error of the average vibration velocity can be controlled at about 7% by the trained neural network using this data type,and the relative error of the half-porosity,roughness and fracture coefficient can be controlled at about 3%.

引文

[1]李建华.预裂爆破技术在大型露天矿山的应用[J].有色金属:矿山部分,2015,67(3)74-76.Li Jianhua.Application of pre-blasting technology in large-scale open-pit mine[J].Nonferrous Metals:Mining Section,2015,67(3):74-76.
    [2]杨明财.爆破振动作用下南芬露天矿边坡稳定性分析[D].武汉:武汉科技大学,2018.Yang Mingcai.Analysis of Slope Stability of Nan-fen Open Pit Mine under Blasting Vibration[D].Wuhan:Wuhan University of Science and Technology,2018.
    [3]李海波,蒋会军,赵坚,等.动荷载作用下岩体工程安全的几个问题[J].岩石力学与工程学报,2003,22(11):1887-1891.Li Haibo,Jiang Huijun,Zhao Jian,et al.Some problems about safety analysis of rock engineering under dynamic load[J].Chinese Journal of Geotechnical Engineering,2003,22(11):1887-1891.
    [4]闫长斌.爆破作用下岩体累积损伤效应及其稳定性研究[D].长沙:中南大学,2006.Yan Changbin.Study on Cumulative Damage Effects and Stability of Rock Mass under Blasting Loading[D].Changsha:Central South University,2006.
    [5]刘美山.特高陡边坡开挖爆破技术及其对边坡稳定性的影响[D].合肥:中国科学技术大学,2007.Liu Meishan.The Excavation Blasting Technique of Particularly High and Steep Slope and the Influence on Its Stability[D].Hefei:University of Science and Technology of China,2007.
    [6]唐海,李海波,周青春,等.预裂爆破震动效应试验研究[J].岩石力学与工程学报,2010,29(11):2277-2285.Tang Hai,Li Haibo,Zhou Qingchun,et al.Experimental study of vibration effect of presplit blasting[J].Chinese Journal of Rock Mechanics and Engineering,2010,29(11):2277-2285.
    [7]夏祥.爆炸荷载作用下岩体损伤特征及安全阈值研究[D].武汉:中国科学院武汉岩土力学研究所,2006.Xia Xiang.Study of Damage Characteristics and Safety Threshold of Rock Vibration by Blast[D].Wuhan:Institute of Rock and Soil Mechanics,Chinese Academy of Sciences,2006.
    [8]胡英国,卢文波,陈明.不同开挖方式下岩石高边坡损伤演化过程比较[J].岩石力学与工程学报,2013,32(6):1176-1184.Hu Yingguo,Lu Wenbo,Chen Ming.Comparison of damage evolution process of high rock slope excavated by different methods[J].Chinese Journal of Rock Mechanics and Engineering,2013,32(6):1176-1184.
    [9]杜耀志,吕琦.建筑物爆破拆除后坐距离的预测研究[J].采矿技术,2013,13(5):125-127.Du Yaozhi,Lyu Qi.Prediction Study on the recoil distance of the demolition of buildings by blasting[J].Mining Technology,2013,13(5):125-127.
    [10]尹光志,李铭辉,李文璞,等.基于改进BP神经网络的煤体瓦斯渗透率预测模型[J].煤炭学报,2013,38(7):1179-1184.Yin Guangzhi,Li Minhui,Li Wenpu,et al.Model of coal gas permeability prediction based on improved BP neural network[J].Journal of China Coal Society,2013,38(7):1179-1184.
    [11]徐黎明,王清,陈剑平,等.基于BP神经网络的泥石流平均流速预测[J].吉林大学学报:地球科学版,2013,43(1):186-191.Xu Liming,Wang Qing,Chen Jianping,et al.Forcast for average velocity of debris flow based on BP neural network[J].Journal of Jilin University:Earth Science Edition,2013,43(1):186-191.
    [12]汪学清,单仁亮.人工神经网络在爆破块度预测中的应用研究[J].岩土力学,2008,29(S1):529-532.Wang Xueqing,Shan Renliang.Application of on artificial neural networks to blasting fragment prediction[J].Rock and Soil Mechanics,2008,29(S1):529-532.
    [13]梅金,张志国,张立鹏.高陡露天矿边坡稳定性评价中若干问题的思考[J].勘察科学技术,2018(4):7-11.Mei Jin,Zhang Zhiguo,Zhang Lipeng.Thinking of some problems about stability evaluation of high and steep open-pit slope[J].Site Investigation Science and Technology,2018(4):7-11.
    [14]李平,岳祖州.人工神经网络的理论、应用与实现研究[J].大连理工大学学报,1997(S2):91.Li Ping,Yue Zuzhou.Research on the theory,application and realization of artificial neural network[J].Journal of Dalian University of Technology,1997(S2):91.
    [15]范孝锋,周传波,陈国平.爆破震动影响因素的灰关联分析[J].爆破,2005(2):100-102.Fan Xiaofeng,Zhou Chuanbo,Chen Guoping.The influential factors of blasting vibration by grey correlation analysis[J].Blasting,2005(2):100-102.
    [16]常斌,李宁.前馈逆传播算法优化及其在岩土工程中的应用[J].岩土工程技术,2002(5):249-251.Chang Bin,Li Ning.Optimization of BP arithmetic and its application in geotechnical engineering[J].Geotechnical Engineering Technique,2002(5):249-251.
    [17]闫大洋.露天矿台阶预裂爆破参数优化的研究与应用[D].淮南:安徽理工大学,2014.Yan Dayang.Opencast Step Presplit Research and Application of Blasting Parameter Optimization[D].Huainan:AnHui University of Science and Technology,2014.
    [18]龙浩,高睿,孔德新,等.基于BP神经网络-马尔科夫链模型的隧道围岩位移预测[J].长江科学院院报,2013,30(3):40-43.Long Hao,Gao Rui,Kong Dexin,et al.Forecast of tunnel’s surrounding rock displacement by BP neural network and Markov chain[C].Journal of Yangtze River Scientific Research Institute,2013,30(3):40-43.
    [19]孙文彬,刘希亮,谭正龙,等.基于抛掷爆破预测的BP神经网络参数优化方法[J].煤炭学报,2012,37(S1):59-64.Sun Wenbin,Liu Xiliang,Tan Zhenglong,et al.Parameter optimization of BP-neural network based on the forecast of cast blasting[J].Journal of China Coal Society,2012,37(S1):59-64.