img

QQ群聊

img

官方微信

高级检索

黄金科学技术 ›› 2020, Vol. 28 ›› Issue (6): 920-929.doi: 10.11872/j.issn.1005-2518.2020.06.069

• 采选技术与矿山管理 • 上一篇    下一篇

基于机器学习的3种岩爆烈度分级预测模型对比研究

田睿1(),孟海东1(),陈世江1,王创业1,孙德宁2,石磊3   

  1. 1.内蒙古科技大学矿业研究院,内蒙古 包头 014010
    2.东北大学深部金属矿山安全开采教育部重点实验室,辽宁 沈阳 110819
    3.内蒙古自治区地质环境监测院,内蒙古 呼和浩特 010020
  • 收稿日期:2020-04-08 修回日期:2020-07-11 出版日期:2020-12-31 发布日期:2021-01-29
  • 通讯作者: 孟海东 E-mail:tianrui6251@126.com;haidongm@imust.cn
  • 作者简介:田睿(1988-),男,内蒙古四子王旗人,博士研究生,工程师,从事岩石力学与数据挖掘方面的研究工作。tianrui6251@126.com
  • 基金资助:
    国家自然科学基金项目“考虑三维岩体结构面各向异性特征的剪切强度研究”(51564038);“基于监测信息的露天矿边坡稳定性研究”(51464036);内蒙古自治区自然科学基金项目“厚煤层采动覆岩破断演化致灾机理研究”(2018MS05037);内蒙古自治区博士研究生科研创新资助项目“基于数据挖掘技术的岩爆预测研究”(B20171012702)

Comparative Study on Three Rockburst Prediction Models of Intensity Classi-fication Based on Machine Learning

Rui TIAN1(),Haidong MENG1(),Shijiang CHEN1,Chuangye WANG1,Dening SUN2,Lei SHI3   

  1. 1.Institute of Mining Engineering,Inner Mongolia University of Science and Technology,Baotou 014010,Inner Mongolia,China
    2.Key Laboratory of Ministry of Education on Safe Mining of Deep Metal Mines,Northeastern University,Shenyang 110819,Liaoning,China
    3.Inner Mongolia Institute of Geological Environmental Monitoring,Hohhot 010020,Inner Mongolia,China
  • Received:2020-04-08 Revised:2020-07-11 Online:2020-12-31 Published:2021-01-29
  • Contact: Haidong MENG E-mail:tianrui6251@126.com;haidongm@imust.cn

摘要:

岩爆是大型地下岩土和深部资源开采工程中必须要解决的关键科学问题之一。综合考虑岩爆的影响因素、特点以及内外因条件,选取洞壁围岩最大切向应力、岩石单轴抗压强度、岩石单轴抗拉强度和岩石弹性能量指数组成岩爆预测指标体系。运用文献调研法,建立了一个包含301组岩爆工程实例的数据库,并以此作为岩爆预测的样本数据。为准确可靠地预测岩爆灾害,基于机器学习技术,建立了RF-AHP-云模型、IGSO-SVM和DA-DNN 3种岩爆预测模型。通过对60组预测样本进行岩爆预测的工程实例分析,验证了3种模型的有效性和正确性。研究结果表明:DA-DNN、IGSO-SVM和RF-AHP-云模型的预测准确率分别为98.3%、90.0%和85.0%;DA-DNN模型理论通俗易懂,编码相对简单,容易实现;随着岩爆数据量的增加,DA-DNN模型应用前景更加广阔。

关键词: 岩爆预测, 机器学习, 随机森林, 云模型, 支持向量机, 深度神经网络

Abstract:

Rockburst is one of the key scientific problems that must be solved in large-scale underground geotechnical engineering and deep mineral resource mining.The safety of personnel and equipment on site was directly threatened by rockburst.Rockburst could be effectively avoided and controlled in time by scientific and accurate rockburst prediction of intensity classification.Through the analysis of six rockburst engineering examples,on the basis of the factors,characteristics and causes of rockburst,a rockburst prediction index system composed of four evaluation indices,i.e.,tunnel-wall surrounding rock’s maximum tangential stress,rock uniaxial compressive strength,rock uniaxial tensile strength,and rock elastic energy index was established.With reference to other rockburst intensity classification schemes,considering the intensity of rockburst occurrence and the main influencing factors,the rockburst intensity was divided into four levels:None rockburst(Ⅰ),slight rockburst(Ⅱ),intermediate rockburst(Ⅲ) and strong rockburst(Ⅳ).According to the selected rockburst evaluation index and rockburst intensity grade,a literature survey method was used to establish a database containing 301 groups of rockburst engineering examples,which would be used as the sample data for rockburst prediction.In order to accurately and reliably predicted rockburst disasters,machine learning technology was introduced.First,a random forest-based rockburst evaluation index importance analysis model was established,a new index weight calculation method of random forest-analytic hierarchy processs was proposed,and the rockburst prediction model based on the RF-AHP-cloud model was constructed.Then,the firefly algorithm based on good point set variable step strategy was introduced to optimize the penalty parameters and radial basis function parameters of the support vector machine,and the rockburst prediction model based on ⅠGSO-SVM was constructed.Finally,the Dropout method was used to regularize the model,and the improved Adam algorithm was used to update weight,and the rockburst prediction model based on DA-DNN was constructed.The effectiveness and correctness of the three models were validated by the prediction results of 60 groups of rockburst engineering examples.The research results show that:The DA-DNN,ⅠGSO-SVM,and RF-AHP-cloud model have prediction accuracy rates of 98.3%,90.0% and 85.0%.The core of rockburst intensity classification prediction based on cloud model is weight determination,and the RF-AHP weight calculation method proposed in this paper has a good effect.The data-driven ⅠGSO-SVM and DA-DNN models are based on rockburst engineering instance data.Through data mining,the rockburst intensity level can be effectively predicted,and higher prediction accuracy can be achieved by improvement.The theory of DA-DNN model is easy to understand,the coding is relatively simple and it is easy to implement.As various underground geotechnical engineering develops deeper,rockburst disasters occur frequently,the amount of rockburst data is increasing,and the DA-DNN model has a wider application prospect.

Key words: rockburst prediction, machine learning, random forest, cloud model, support vector machine, deep neural network

中图分类号: 

  • TU45

表1

岩爆工程实例数据库( 部分数据)"

序号工程名称σθσcσtWet岩爆等级
8瀑布沟水电站洞室[20]43.4123.06.05.0中级岩爆
18意大利Raibl矿井巷道[20]108.4140.08.05.5强烈岩爆
157括苍山隧道[21]13.9124.04.22.0无岩爆
203共和隧道[22]42.450.06.15.3轻微岩爆
???????
292美国Galena金矿[23]52.0175.07.05.2中级岩爆
301巴玉隧道[23]74.2190.08.97.1强烈岩爆

图1

各等级岩爆分布"

图2

岩爆指标重要性分数值"

表2

DA-DNN模型参数"

序号参数名称参数取值
1Dropout丢弃比率p=0.5
2初始学习率η=0.001
3动量系数λ=0.95
4一、二阶矩估计得指数衰减率β1=0.9β2=0.999
5用于数值稳定的常数δ=1e-08
6误差目标取值0.0001
7批大小取值Batch_size=10
8训练次数取值Epoch=60

表3

岩爆烈度分级预测样本预测结果"

样本序号工程名称DA-DNNIGSO-SVMRF-AHP-云模型FCM-RS-云模型实际岩爆等级
1天生桥二级水电站引水隧洞
2二滩水电站2号支洞
3龙羊峡水电站地下洞室
4鲁布革水电站地下洞室
5渔子溪水电站引水隧洞
6太平驿水电站地下洞室
7李家峡水电站地下洞室
8瀑布沟水电站地下洞室
9锦屏二级水电站引水隧洞
10拉西瓦水电站地下厂房
11挪威Sima水电站地下厂房
12挪威Heggura公路隧道
13挪威Sewage隧道
14瑞典Forsmark核电站冷却水隧洞
15瑞典Vietas水电站引水隧洞
16前苏联Rasvumchorr矿井巷
17日本关越隧道
18意大利Raibl铅硫化锌矿井巷
19秦岭隧道DyK77+176
20秦岭隧道DyK72+440
21秦岭隧道某段一
22秦岭隧道某段二
23括苍山隧道
24通渝隧道K21+720断面
25通渝隧道K21+212断面
26通渝隧道K21+740断面
27通渝隧道K21+680断面
28江边水电站引5+486
29江边水电站引7+366
30江边水电站引7+790
31江边水电站引7+806
32锦屏二级电站1+731
33锦屏二级电站3+390
34锦屏二级电站1+640
35锦屏二级电站3+000
36程潮铁矿K8
37程潮铁矿K9
38程潮铁矿K10
39程潮铁矿K11
40程潮铁矿K12
41程潮铁矿K13
42苍岭隧道K97+702~K98+152
43苍岭隧道K98+152~K98+637
44苍岭隧道K98+637~K99+638
45苍岭隧道K99+638~K100+892
46苍岭隧道K100+892~K101+386
47冬瓜山矿K1
48北洺河铁矿K1
49北洺河铁矿K2
50北洺河铁矿K3
51北洺河铁矿K4
52美国CAD-A矿
53美国CAD-B矿
54美国CAD-C矿
55苏联X矿山
56瑞士布鲁格水电站地下硐室
57乌兹别克斯坦卡姆奇克隧道
58美国加利纳矿
59重丘山岭某隧道
60中国巴玉隧道
1 冯夏庭,肖亚勋,丰光亮,等.岩爆孕育过程研究[J].岩石力学与工程学报,2019,38(4):649-673.
Feng Xiating,XiaoYaxun,Feng Guangliang,et al.Study on the development process of rockbursts[J].Chinese Journal of Rock Mechanics and Engineering,2019,38(4):649-673.
2 李夕兵,宫凤强,王少锋,等.深部硬岩矿山岩爆的动静组合加载力学机制与动力判据[J].岩石力学与工程学报,2019,38(4):708-723.
Li Xibing,Gong Fengqiang,Wang Shaofeng,et al.Coupled static-dynamic loading mechanical mechanism and dynamic criterion of rockburst in deep hard rock mines[J].Chinese Journal of Rock Mechanics and Engineering,2019,38(4):708-723.
3 李任豪,顾合龙,李夕兵,等.基于PSO-RBF神经网络模型的岩爆倾向性预测[J].黄金科学技术,2020,28(1):134-141.
Li Renhao,Gu Helong,Li Xibing,et al.A PSO-RBF neural network model for rockburst tendency prediction[J].Gold Science and Technology,2020,28(1):134-141.
4 王旷,李夕兵,马春德,等.基于改进的RS-TOPSIS模型的岩爆倾向性预测[J].黄金科学技术,2019,27(1):80-88.
Wang Kuang,Li Xibing,Ma Chunde,et al.Rockburst proneness prediction based on improved RS-TOPSIS model[J].Gold Science and Technology,2019,27(1):80-88.
5 田睿,孟海东,陈世江,等.基于深度神经网络的岩爆烈度分级预测研究[J].煤炭学报,2020..
Tian Rui,Meng Haidong,Chen Shijiang,et al.Prediction of intensity classification of rockburst based on deep neural network[J].Journal of China Coal Society,2020..
6 Wang C L,Wu A X,Lu H,et al.Predicting rockburst tendency based on fuzzy matter-element model[J].International Journal of Rock Mechanics & Mining Sciences,2015(75):224-232.
7 胡建华,尚俊龙,周科平.岩爆烈度预测的改进物元可拓模型与实例分析[J].中国有色金属学报,2013,23(2):495-502.
Hu Jianhua,Shang Junlong,Zhou Keping.Improved matter-element extension model and its application to prediction of rockburst intensity[J].The Chinese Journal of Nonferrous Metals,2013,23(2):495-502.
8 徐琛,刘晓丽,王恩志,等.基于组合权重—理想点法的应变型岩爆五因素预测分级[J].岩土工程学报,2017,39(12):2245-2252.
Xu Chen,Liu Xiaoli,Wang Enzhi,et al.Strain mode rockburst prediction and classification based on five-factors criterion and combined weight-ideal point method[J].Chinese Journal of Geotechnical Engineering,2017,39(12):2245-2252.
9 李绍红,王少阳,朱建东,等.基于权重融合和云模型的岩爆倾向性预测研究[J].岩土工程学报,2018,40(6):1075-1083.
Li Shaohong,Wang Shaoyang,Zhu Jiandong,et al.Prediction of rockburst tendency based on weighted fusion and improved cloud model[J].Chinese Journal of Geotechnical Engineering,2018,40(6):1075-1083.
10 Pu Y Y,Apel D B,Lingga B.Rockburst prediction in kimberlite with unsupervised learning method and support vector classifier[J].Tunnelling and Underground Space Technology,2019(90):12-18.
11 Wu S C,Wu Z G,Zhang C X.Rockburst prediction probability model based on case analysis[J].Tunnelling and Underground Space Technology,2019(93):1-15.
12 宫凤强,李夕兵,张伟,等.基于Bayes判别分析方法的地下工程岩爆发生及烈度分级预测[J].岩土力学,2010,31(增1):370-377.
Gong Fengqiang,Li Xibing,Zhang Wei,et al.Rockburst prediction of underground engineering based on Bayes discriminant analysis method[J].Rock and Soil Mechanics,2010,31(Supp.1):370-377.
13 李天斌,孟陆波,王兰生.高地应力隧道稳定性及岩爆、大变形灾害防治[M].北京:科学出版社,2016.
Li Tianbin,Meng Lubo,Wang Lansheng.High Geostress Tunnel Stability and Prevention of Rockburst and Large Deformation Disasters[M].Beijing:Science Press,2016.
14 周德培,洪开荣.太平驿隧洞岩爆特征及防治措施[J].岩石力学与工程学报,1995,14(2):171-178.
Zhou Depei,Hong Kairong.The rockburst features of Taipingyi tunnel and the prevention methods[J].Chinese Journal of Rock Mechanics and Engineering,1995,14(2):171-178.
15 谷明成,何发亮,陈成宗.秦岭隧道岩爆的研究[J].岩石力学与工程学报,2002,21(9):1324-1329.
Gu Mingcheng,He Faliang,Chen Chengzong.Study on rockburst in Qinling tunnel[J].Chinese Journal of Rock Mechanics and Engineering,2002,21(9):1324-1329.
16 严健,何川,汪波,等.雅鲁藏布江缝合带深埋长大隧道群岩爆孕育及特征[J].岩石力学与工程学报,2019,38(4):769-781.
Yan Jian,He Chuan,Wang Bo,et al.Inoculation and characters of rockbursts in extra-long and deep-lying tunnels located on YarlungZangbo suture[J].Chinese Journal of Rock Mechanics and Engineering,2019,38(4):769-781.
17 陈原望.阿舍勒铜矿深井开采岩爆现象研究及应对措施探索[J].新疆有色金属,2018(2):80-82.
Chen Yuanwang.Research on rockburst phenomenon in deep well mining of Ashele copper mine and exploration of its countermeasures[J].Xinjiang Nonferrous Metals,2018(2):80-82.
18 Russenes B F.Analysis of Rock Spalling for Tunnels in Steep Valley Sides(in Norwegian)[D].Trondheim:Norwegian Institute of Technology,1974.
19 Turchaninov I A,Markov G A,Gzovsky M V,et al.State of stress in the upper part of the Earth’s crust based on direct measurements in mines and on tectonophysicl and seismological studies[J].Physics of the Earth and Planetary Interiors,1972,6(4):229-234.
20 王元汉,李卧东,李启光,等.岩爆预测的模糊数学综合评判方法[J].岩石力学与工程学报,1998,17(5):493-501.
Wang Yuanhan,Li Wodong,Li Qiguang,et al.Method of fuzzy comprehensive evaluations for rockburst prediction[J].Chinese Journal of Rock Mechanics and Engineering,1998,17(5):493-501.
21 Zhou J,Li X B,Shi X Z.Long-term prediction model of rockburst in underground openings using heuristic algorithms and support vector machines[J].Safety Science,2012,50(4):629-644.
22 张波.基于岩体各向异性深埋公路隧道安全稳定性研究[D].武汉:中国科学院武汉岩土力学研究所,2007.
Zhang Bo.Study on Security and Stability of Deep Buried Highway Tunnel Based on Anisotropic Theory[D].Wuhan:Institute of Rock and Soil Mechanics,Chinese Aca-demy of Sciences,2007.
23 孙臣生.基于改进MATLAB-BP神经网络算法的隧道岩爆预测模型[J].重庆交通大学(自然科学版),2019,38(10):41-49.
Sun Chensheng.A prediction model of rockburst in tunnel based on the improved MATLAB-BP neural network[J].Journal of Chongqing Jiaotong University(Natural Science),2019,38(10):41-49.
24 李德毅,杜鹢.不确定性人工智能[M].北京:国防工业出版社,2014.
Li Deyi,Du Yi.Artificial Intelligence with Uncertainty[M].Beijing:National Defense Industry Press,2014.
25 Breiman L.Random forests[J].Machine Learning,2001,45(1):5-32.
26 鲁月.基于随机森林因素筛选的国产电影票房组合预测模型研究[D].南京:南京航天航空大学,2019.
Lu Yue.Research on Factors Screening Based on Random Forest and Domestic Movie Box-office Combined Prediction Model[D].Nanjing:Nanjing University of Aeronautics and Astronautics,2019.
27 冯夏庭,赵洪波.岩爆预测的支持向量机[J].东北大学学报(自然科学版),2002,23(1):57-59.
Feng Xiating,Zhao Hongbo.Prediction of rockburst using support vector machine[J].Journal of Northeastern University(Natural Science),2002,23(1):57-59.
28 Yang X S.Nature-inspired Metaheuristic Algorithms[M].Beckington:Luniver Press,2010.
29 李敬明.萤火虫群智能优化算法及其应用研究[D].合肥:合肥工业大学,2017.
Li Jingming.Research on Swarm Intelligent Optimization Algorithm of Glowworm and Its Application[D].Hefei:Hefei University of Technology,2017.
30 Lecun Y,Bengio Y,Hinton G E.Deep learning[J].Nature,2015,521(7553):436-444.
31 Goodfellow I J,Bengio Y,Courville A.Deep Learning[M].Cambridge:MIT Press,2016.
32 Srivastava N,Hinton G E,Krizhevsky A.Dropout:A simple way to prevent neural networks from overfitting[J].The Journal of Machine Learning Research,2014,15(1):1929-1958.
33 Kingma D,Adam B J.A method for stochastic optimization[C]//Proceedings of the 3rd International Conference for Learning Representations,2015:1-15.
34 张慧.深度学习中优化算法的研究与改进[D].北京:北京邮电大学,2017.
Zhang Hui.Research and Improvement of Optimization Algorithms in Deep Learning[D].Beijing:Beijing University of Posts and Telecommunications,2017.
35 郝杰,侍克斌,王显丽,等.基于模糊C-均值算法粗糙集理论的云模型在岩爆等级评价中的应用[J].岩土力学,2016,37(3):859-866.
Hao Jie,Shi Kebin,Wang Xianli,et al.Application of cloud model to rating of rockburst based on rough set of FCM algorithm[J].Rock and Soil Mechanics,2016,37(3):859-866.
[1] 谭吉玉,刘高常. 基于小波支持向量机模型的矿区生态安全评价方法研究[J]. 黄金科学技术, 2020, 28(6): 902-909.
[2] 王牧帆,罗周全,于琦. 基于 Stacking 模型的采空区稳定性预测[J]. 黄金科学技术, 2020, 28(6): 894-901.
[3] 廖智勤, 王李管, 何正祥. 基于EEMD和关联维数的矿山微震信号特征提取和分类[J]. 黄金科学技术, 2020, 28(4): 585-594.
[4] 许瑞, 侯奎奎, 王玺, 刘兴全, 李夕兵. 基于核主成分分析与SVM的岩爆烈度组合预测模型[J]. 黄金科学技术, 2020, 28(4): 575-584.
[5] 李彤彤, 王玺, 刘焕新, 侯奎奎, 李夕兵. 基于组合赋权的T-FME岩爆倾向性预测模型研究及应用[J]. 黄金科学技术, 2020, 28(4): 565-574.
[6] 周科平, 侯霄峰, 林允. 基于综合决策云模型的围岩稳定性分级方法研究[J]. 黄金科学技术, 2020, 28(3): 372-379.
[7] 戚伟,李威,李振阳,赵国彦. 基于CRITIC-CW法的地下矿岩体质量评价[J]. 黄金科学技术, 2020, 28(2): 264-270.
[8] 李任豪,顾合龙,李夕兵,侯奎奎,朱明德,王玺. 基于PSO-RBF神经网络模型的岩爆倾向性预测[J]. 黄金科学技术, 2020, 28(1): 134-141.
[9] 韩超群,陈建宏,周智勇,杨珊. 基于主成分分析—支持向量机模型的矿岩可爆性等级预测研究[J]. 黄金科学技术, 2019, 27(6): 879-887.
[10] 李科明,刘志祥,兰明. 滨海金矿涌水危险评价及涌水量混沌预测研究[J]. 黄金科学技术, 2019, 27(4): 539-547.
[11] 黄仁东,刘赞赞,闫泽正. 基于有限云模型的深基坑安全性研究[J]. 黄金科学技术, 2019, 27(1): 72-79.
[12] 王旷,李夕兵,马春德,顾合龙. 基于改进的RS-TOPSIS模型的岩爆倾向性预测[J]. 黄金科学技术, 2019, 27(1): 80-88.
[13] 刘强,李夕兵,梁伟章. 岩体质量分类的PCA-RF模型及应用[J]. 黄金科学技术, 2018, 26(1): 49-55.
[14] 张钦礼,王兢*,王新民. 基于核主成分分析与PSO-SVM的充填管道失效风险性分级评价模型[J]. 黄金科学技术, 2017, 25(3): 70-76.
[15] 饶运章,李雪珍. 基于实际冲击能量指数(W)的岩爆预测技术研究[J]. 黄金科学技术, 2015, 23(4): 63-67.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 闫杰, 覃泽礼, 谢文兵, 蔡邦永. 青海南戈滩—乌龙滩地区多金属地质特征与找矿潜力[J]. J4, 2010, 18(4): 22 -26 .
[2] 宋贺民, 冯喜利, 丁宪华. 太行山北段交界口矿区地质地球化学特征及找矿方向[J]. J4, 2010, 18(3): 54 -58 .
[3] 李淑芳, 于永安, 朝银银, 王美娟, 张岱, 刘君, 孙亮亮. 在辽东成矿带找寻层控型金矿床靶区[J]. J4, 2010, 18(3): 59 -62 .
[4] 胡琴霞, 李建忠, 喻光明, 谢艳芳, 张圣潇. 白龙江成矿带金矿点初探[J]. J4, 2010, 18(3): 51 -53 .
[5] 崔廷军, 逯克思, 庄勇, 傅星. 青海省柴达木盆地南缘金成矿带特征及成矿规律浅析[J]. J4, 2010, 18(3): 63 -67 .
[6] 杨明荣, 牟长贤. 原子荧光法测定化探样品中砷和锑的不确定度评定[J]. J4, 2010, 18(3): 68 -71 .
[7] 苏建华, 陆树林. 从高酸低浓度尾液中萃取金的试验[J]. J4, 2010, 18(3): 72 -75 .
[8] 王大平, 宋丙剑, 韦库明. 大功率激电测量在辽宁北水泉寻找隐伏矿床的应用[J]. J4, 2010, 18(3): 76 -78 .
[9] 刘胜光, 高海峰, 黄锁英. 电子手薄在山东焦家金矿地质专业中的应用[J]. J4, 2010, 18(3): 79 -82 .
[10] 刘新会,刘家军,陈彩华. 西秦岭寨上特大型金矿床硫盐矿物特征及其成因意义[J]. J4, 2010, 18(4): 6 -11 .