黄晶柱,钟依禄,黄裘俊,肖维灵,孙俊涛,廖占象,胡玮锋
HUANG Jing-zhu,ZHONG Yi-lu,HUANG Qiu-jun,XIAO Wei-ling,SUN Jun-tao,LIAO Zhan-xiang,HU Wei-feng

• 1:江西理工大学土木与测绘工程学院
• 2:江西理工大学江西省环境岩土与工程灾害控制重点实验室
• 3:中建深圳装饰有限公司
• 4:深圳职业技术学院汽车与交通学院

摘要(Abstract)：

为了提高矿山爆破飞石距离预测结果的精度，首先，根据马来西亚某矿山52次爆破作业记录的飞石距离相关参数，建立由6个输入(炮孔孔径、炮孔长度、最小抵抗线/孔距、炮孔填塞长度、最大一段装药量、炸药单耗)和1个输出(飞石距离)组成的数据库。然后，基于高斯过程回归机器学习算法，建立爆破飞石距离的预测模型，将其应用于马来西亚某矿山中，并与2种主流的机器学习方法(支持向量回归和神经网络)的预测结果进行对比。结果表明：从实际图-预测值图和残差分析看，基于双层神经网络构建的飞石距离预测模型的预测效果最差；从回归评价指标看，基于二次有理高斯过程回归建立的飞石距离预测模型的预测效果最优，其R-平方(R~2)值为0.9、均方根误差(RMSE)值为24.67、均方误差(MSE)值为608.61、平均绝对误差(MAE)值为21.42。由此可知，基于高斯过程回归预测矿山爆破飞石距离更精确。可为类似矿山爆破安全警戒范围计算提供理论基础。
In order to improve the accuracy of the prediction results of flyrock distance in mine. First, according to the parameters related to the flyrock distance recorded by 52 blasting operations in a mine in Malaysia, 6 inputs(borehole diameter, length of blasthole, burden to spacing, stemming length, maximum charge per delay, and powder factor) and 1 output(flyrock distance). Then, based on the Gaussian process regression machine learning algorithm, the prediction model of the flyrock distance from blasting was established, which is applied to a mine in Malaysia, and compared with two mainstream machine learning methods(support vector regression and neural network) were used to establish flyrock distance prediction models. The results show that from the actual value-predicted value graph and residual analysis, the flyrock distance prediction model based on two-layer neural network has the worst prediction effect; from the regression evaluation index, the flyrock distance prediction model based on quadratic rational Gaussian process regression has the best prediction effect. Its R-square(R~2) value is 0.9, root mean square error(RMSE) value is 24.67, mean square error(MSE) value is 608.61, and mean absolute error(MAE) value is 21.42. Conclusion: Based on the Gaussian process, the flyrock distance of mines is more accurate. It can provide the theoretical basis for calculation of similar mining blasting safety alert range.

关键词(KeyWords)： 矿山爆破;高斯过程回归;飞石距离;预测模型
mine blasting;gaussian process regression;flyrock distance;predictive model

Abstract:

Keywords:

基金项目(Foundation): 江西省教育厅科技基金资助项目(GJJ200871,GJJ180503);; 江西理工大学高层次人才启动基金资助项目(205200100486);; 深圳职业技术学院校级科研启动基金资助项目(6022312007K);; 广东省基础与应用基础研究基金资助项目(2021A1515110730)

作者(Author): 黄晶柱,钟依禄,黄裘俊,肖维灵,孙俊涛,廖占象,胡玮锋
HUANG Jing-zhu,ZHONG Yi-lu,HUANG Qiu-jun,XIAO Wei-ling,SUN Jun-tao,LIAO Zhan-xiang,HU Wei-feng

DOI: 10.19931/j.EB.20210265

参考文献(References)：

• [1] 翁春林，叶加冕.工程爆破[M].北京：冶金工业出版社，2016:219-222.WENG C L,YE J M.Engineering blasting [M].Beijing:Metallurgical Industry Press,2016:219-222.
• [2] 徐颖，孟益平，吴德义.爆破工程[M].武汉：武汉大学出版社，2014:219-221.XU Y,MENG Y P,WU D Y.Blasting engineering [M].Wuhan:Wuhan University Press,2014:219-221.
• [3] 国家安全生产监督管理总局.爆破安全规程：GB 6722-2014[S].北京：中国标准出版社，2015.State Adiministration of Work Safety.Safety regulation for blasting:GB 6722-2014[S].Beijing:Standards Press of China,2015.
• [4] 曹兰柱，王珍，王东，等.边排孔位置与爆破飞石距离控制的匹配[J].辽宁工程技术大学学报(自然科学版),2017,36(7):673-678.CAO L Z,WANG Z.WANG D,et al.Matching the location of side hole and the contral of blasting slungshot distance[J].Journal of Liaoning Technical University (Natural science),2017,36(7):673-678.
• [5] HAN H,ARMAGHANI D J,TARINEJAD R,et al.Random forest and bayesian network techniques for probabilistic prediction of flyrock induced by blasting in quarry sites[J].Natural Resources Research,2020,29(2):655-667.
• [6] LU X,HASANIPANAH M,BRINDHADEVI K,et al.ORELM:A novel machine learning approach for prediction of flyrock in mine blasting[J].Natural Resources Research,2020,29(2):641-654.
• [7] 兰振.深孔爆破飞石产生的机理计算及控制措施[J].世界有色金属，2018(13):182-184.LAN Z.Mechanism calculation and control measures of fly rock produced by deep hole blasting[J].World Nonferrous Metals,2018(13):182-184.
• [8] 肖伟.爆破开挖飞石抛掷距离研究[D].赣州：江西理工大学，2017:34-42.XIAO W.Study on throwing distance of flying stone in blasting excavation[D].Ganzhou:Jiangxi University of Science and Technology,2017:34-42.
• [9] 高毓山，张敢生，陈庆凯，等.露天矿山爆破飞石的控制方法[J].现代矿业，2014,30(2):102-104.GAO Y S,ZHANG G S,CHEN Q K,et al.Control method of flying stone blasting in open pit mine[J].Modern Mining,2014,30(2):102-104.
• [10] 王怀，黎谟炬，林大能，等.基于Ansys-autodyn的水下爆破抛掷距离研究[J].采矿技术，2020,20(6):194-198.WANG H,LI M J,LIN D N,et al.Research on throwing distance of underwater blasting based on Ansys-autodyn[J].Mining Technology,2020,20(6):194-198.
• [11] 尹东升，何怡，王琪.露天矿爆破飞石安全距离的推算[J].现代矿业，2014,30(9):23-26.YIN D S,HE Y,WANG Q.Calculation on the blasting flying stone safety distance in open-pit mine[J].Modern Mining,2014,30(9):23-26.
• [12] 贾达，陈星明，莫超，等.中小型露天矿山爆破飞石最远飞散距离预测研究[J].工业安全与环保，2021,47(3):30-33.JIA D,CHEN X M,MO C,et al.Study on the prediction of the maximum flying distance of blasting flying stones in small and medium-sized open-pit mines [J].Industrial Safety and Environmental Protection,2021,47(3):30-33.
• [13] MURLIDHAR B R,KUMAR D,ARMAGHANI D J,et al.A novel intelligent elm-bbo technique for predicting distance of mine blasting-induced flyrock[J].Natural Resources Research,2020,29:4 103-4 120.
• [14] 陈建宏，彭耀，邬书良.基于灰色Elman神经网络的爆破飞石距离预测研究[J].爆破，2015,32(1):151-156.CHEN J H,PENG Y,WU S L.Prediction of blasting flyrock distance based on elman neural network [J].Blasting,2015,32(1):151-156.
• [15] 刘庆，张光权，吴春平，等.基于BP神经网络模型的爆破飞石最大飞散距离预测研究[J].爆破，2013,30(1):114-118.LIU Q,ZHANG G Q,WU C P,et al.Research on maximum distance prediction of blast flyrock based on bp neural network[J].Blasting,2013,30(1):114-118.
• [16] FARADONBEH R S,ARMAGHANI D J,MONJEZI M,et al.Genetic programming and gene expression programming for flyrock assessment due to mine blasting[J].International Journal of Rock Mechanics & Mining Sciences,2016,88:254-264.
• [17] 张西良.岩体爆破环境效应预测的集成学习模型及工程应用[D].合肥：中国科学技术大学，2020:65-90.ZHANG X L.Ensemble learning model and engineering application of environmental effect prediction of rock mass blasting[D].Hefei:University of Science and Technology of China,2020:65-90.
• [18] ARMAGHANI D J,KOOPIALIPOOR M,BAHRI M,et al.A SVR-GWO technique to minimize flyrock distance resulting from blasting[J].Bulletin of Engineering Geology and the Environment,2020,79:4 369-4 385.
• [19] 何志昆，刘光斌，赵曦晶，等.高斯过程回归方法综述[J].控制与决策，2013,28(8):1 121-1 129,1 137.HE Z K,LIU G B,ZHAO X J,et al.Overview of Gaussian process regression[J].Control and Decision,2013,28(8):1 121-1 129,1 137.
• [20] LI Z Z,LI L,SHAO Z Y.Robust Gaussian process regression based on iterative trimming[J].Astronomy and Computing,2021,36:100483.
• [21] MENKE W,CREEL R.Gaussian process regression reviewed in the context of inverse theory[J].Surveys in Geophysics,2021,42:473-503.
• [22] 肖建，于龙，白裔峰.支持向量回归中核函数和超参数选择方法综述[J].西南交通大学学报，2008,43(3):297-303.XIAO J,YU L,BAI Y F.Survey of the selection of kernels and hyper-parameters in support vector regression[J].Journal of Southwest Jiaotong University,2008,43 (3):297-303.
• [23] LIU Y,WANG L,GU K X.A Support Vector Regression (SVR)-based method for dynamic load identification using heterogeneous responses under interval uncertainties[J].Applied Soft Computing Journal,2021,110:107599.
• [24] 李炳臻，刘克，顾佼佼，等.卷积神经网络研究综述[J].计算机时代，2021(4):8-12,17.LI B Z,LIU K,GU J J,et al.Review of the researches on convolutional neural networks[J].Computer Era,2021(4):8-12,17.
• [25] 张驰，郭媛，黎明.人工神经网络模型发展及应用综述[J].计算机工程与应用，2021,57(11):57-69.ZHANG C,GUO Y,LI M.Review of development and application of artificial neural network models[J].Computer Engineering and Applications,2021,57(11):57-69.
• [26] WANG G M,JIA Q S,ZHOU M C,et al.Artificial neural networks for water quality soft-sensing in wastewater treatment:a review[J].Artificial Intelligence Review,2022,55(1):565-587.