img

QQ群聊

img

官方微信

高级检索

黄金科学技术 ›› 2019, Vol. 27 ›› Issue (1): 63-71.doi: 10.11872/j.issn.1005-2518.2019.01.063

• • 上一篇    下一篇

基于GSO-GPR算法的岩层移动角预测模型及其应用

赵国彦,张海云*(),刘建,陈英   

  1. 1. 中南大学资源与安全工程学院,湖南 长沙 410083
  • 收稿日期:2017-09-08 修回日期:2017-12-29 出版日期:2019-02-28 发布日期:2019-03-19
  • 通讯作者: 张海云 E-mail:510213771@qq.com
  • 作者简介:赵国彦(1963-),男,湖南益阳人,教授,从事采矿与岩石力学研究工作。gy_zhao@263.net|张海云(1992-),男,湖南怀化人,硕士研究生,从事采矿与岩石力学研究工作。510213771@qq.com
  • 基金资助:
    国家自然科学基金项目“深井开采岩石孔洞群能量演化及应力调控方法研究”(编号:51774321)资助

GSO-GPR Model for Strata Displacement Angle Predicting and Its Application

Guoyan ZHAO,Haiyun ZHANG*(),Jian LIU,Ying CHEN   

  1. 1. School of Resources and Safety Engineering,Central South University,Changsha 410083,Hunan,China
  • Received:2017-09-08 Revised:2017-12-29 Online:2019-02-28 Published:2019-03-19
  • Contact: Haiyun ZHANG E-mail:510213771@qq.com

摘要:

为快速准确获取金属矿地下开采岩层移动角,提出基于群搜索优化(GSO)算法的改进高斯过程回归(GPR)理论。以矿体上下盘围岩性质、上下盘围岩稳固程度、地下水情况、矿体走向长度、矿体倾角、开采厚度及深度9个影响因素作为判别指标,结合35组实测数据建立金属矿充填开采岩层移动角学习预测模型。将该模型应用于三山岛金矿岩层移动角预测,利用UDEC数值模拟结果进行对比验证,同时分析三山岛金矿海下开采对上盘竖井的影响。研究结果表明:(1)GSO-GPR预测模型对地下开采岩层移动角的预测效果良好,预测精度在5%以内;(2)三山岛金矿上、下盘岩层移动角分别为72°和68°;(3)当前矿山开采未对竖井造成影响,但随着开采深入至-658 m水平,竖井将进入塌陷范围。

关键词: 金属矿, 地下开采, 岩层移动角, 群搜索优化, 高斯过程回归, UDEC

Abstract:

The strata displacement angle of underground metal mine is the key parameter for analyzing rock movement caused by underground mining.It is usually used in the design of security pillars, the delineation of dangerous moving boundaries, and the delineation of surface protective buildings.Therefore, to quickly and accurately obtain the strata displacement angle of underground metal mine is of great significance for the safe and efficient mining of underground metal mines.The Gaussian Process (GP) is a new machine learning technology that was developed on the basis of strict statistical foundation.It has outstanding advantages in dealing with complex classification and regression problems such as high dimensionality, small sample, and nonlinear.However, the optimization effect of its performance parameters has the disadvantages of strong dependence on initial value, difficulty in determining the number of iterations, and local optimization.Group Search Optimizer (GSO) algorithm draws on the behavior of group behavior and has strong optimization search ability.To quickly and accurately obtain the strata displacement angle of underground metal mine, the GSO was chosen to take the place of conjugate gradient method to search for optimal hyper parameters, therefore, an improved Gaussian Process Regression (GPR) theory based on the Group Search Optimization (GSO) algorithm was proposed.According to the actual situation of underground mining, the influence factors selected by relevant scholars and relevant national standards, nine influence factors which including characteristics and stability of surrounding rock on upper-wall and foot-wall, geological structure, underground water, ore-body length along its trend, ore-body dip angle, mining thickness and depth were chosen as the evaluation indexes. Combining with 35 groups of measured data to establish, the learning model was established for predicting displacement angle of strata in metal mine adopting backfilling methods. Sanshandao gold mine is the only large-scale submarine gold mine in the world.The range of strata displacement and deformation gradually expands with the deepening of mining.It is likely to affect the stability of the coastal shaft in the later stage.The improved Gaussian Process Regression (GPR) theory model was then applied to predict the strata displacement angle of Sanshandao gold mine, and the results was compared to the simulation results by UDEC.The FLAC software was used to establish the underground mining geometric model.The UDEC software was used to simulate the rock movement caused by submarine mining, and then the strata displacement angle of the upper rock stratum of the Sanshandao gold mine was calculated and verified.Meanwhile, the influence of mining on the upper-wall shaft was analyzed.The results show that:(1) The GSO-GPR model has a significant effect on the prediction of strata displacement angle of underground mines with the prediction accuracy within 5%;(2) The strata displacement angles of upper-wall and foot-wall of Sanshandao gold mine are 72° and 68° respectively, through the UDEC numerical simulation, the law of rock stratum subsidence in the mining is analyzed, and the moving angle of the upper plate is stable at around 72° after the mining in the -600 m level. (3)Applying the strata displacement angle of the upper rock to the division of the subsidence range,the current mine mining has no effect on the shaft, but as the mining goes deeper, the shaft will fall into the collapse range when mining the level of -658 m.

Key words: metal mine, underground mining, strata displacement angle, Group Search Optimization (GSO), Gaussian Process Regression (GPR), UDEC

中图分类号: 

  • TD325

表1

充填采矿法矿山岩层移动资料统计"

序号普氏系数稳固程度地下水情况矿体倾角/(°)开采厚度/m矿体走向长度/m开采深度/m移动角/(°)
上盘下盘上盘下盘上盘下盘
10.500.570.670.670.000.470.150.010.166368
20.830.711.000.331.001.000.360.091.008080
30.000.290.000.500.000.080.060.030.005463
40.670.431.001.000.000.860.810.200.346058
50.330.571.000.670.330.860.470.120.135560
60.830.140.000.330.330.390.130.270.276050
70.670.000.331.000.670.861.000.130.175550
80.670.570.000.330.670.940.250.130.297070
90.500.710.330.330.000.390.530.050.245555
100.670.431.001.001.000.280.171.000.217672
110.500.570.000.330.670.550.400.570.117075
120.670.710.670.670.670.000.230.000.436570
130.500.430.330.331.000.780.810.140.636570
140.330.290.330.330.670.581.320.160.377070
150.000.290.000.000.330.470.550.320.455565
160.330.710.330.670.670.700.170.590.425660
170.670.431.001.000.670.700.000.210.016260
180.670.291.000.670.330.860.340.210.017065
190.500.290.500.500.670.780.230.250.417065
200.830.140.500.501.000.780.110.350.267565
210.670.290.500.500.670.550.060.450.587065
221.000.141.001.001.000.700.170.240.027880
230.831.000.500.501.000.700.210.210.047875
240.500.860.330.331.000.470.210.260.027674
250.670.290.500.500.670.700.130.270.056866
260.830.431.001.001.000.670.230.480.047980
270.501.000.500.501.000.310.190.150.037879
280.330.710.330.330.670.940.130.370.077577
290.670.571.001.001.000.830.150.490.077075
300.830.710.330.330.330.310.320.440.026970
31*0.670.571.001.000.670.860.130.510.077575
32*0.830.861.001.001.000.780.170.530.056260
33*0.670.860.670.670.670.860.150.150.007475
34*0.830.710.500.500.000.830.170.420.067272
35*0.670.570.670.670.000.700.090.490.037879

表2

岩层移动角预测结果对比"

序号上盘移动角/(°)下盘移动角/(°)
实际值GPR预测值GPR误差/%GSO-GPR预测值GSO-GPR误差/%实际值

GPR

预测值

GPR误差/%

GSO-GPR

预测值

GSO-GPR误差/%
31*75698.00741.3375706.67741.33
32*627012.90603.23607423.33623.33
33*74731.35731.3575741.33741.33
34*72702.78711.3872702.78702.78
35*78736.41771.2879746.33763.80

图1

55勘探线矿体剖面示意图"

表3

回采-240 m中段测点位移变化(mm)"

监测日期位移变化
测点1测点2测点3
4月11日0.00.00.0
4月24日18.614.011.6
5月4日32.022.020.8
5月9日36.028.025.0
5月14日41.335.031.0

表4

三山岛金矿岩层移动角预测结果"

普氏系数稳固程度地下水影响矿体倾角/(°)开采厚度/m矿体走向长度/m开采深度/mGSO-GPR预测结果/(°)
上盘下盘上盘下盘上盘下盘
98中等稳固中等稳固严重46209006007268

表5

矿区矿岩物理力学参数"

岩性密度/(kg·m-3弹性模量/GPa泊松比抗拉强度/MPa黏聚力/MPa内摩擦角/(°)单轴抗压强度/MPa
上盘变辉长岩2 70613.440.204.9211.4430.6080.87
矿体黄铁绢英花岗岩2 70915.020.198.5421.5032.60102.95
下盘二长花岗岩2 63517.100.248.2242.8036.9472.07
充填体2 1000.230.190.171.7138.701.71

图2

开挖阶段沉陷范围变化情况"

图3

竖井变形量"

图4

矿床后续开采对竖井稳定性分析"

表6

开挖阶段地表倾斜率、水平变形率"

开挖阶段地表倾斜率/(mm?m-1水平变形率/(mm?m-1开挖阶段地表倾斜率/(mm?m-1水平倾斜率/(mm?m-1
-240 m0.0080.013-440 m0.2670.546
-280 m0.3020.055-480 m0.3380.676
-320 m0.7960.131-520 m0.4230.789
-360 m0.1370.247-560 m0.5251.288
-400 m0.2160.433-600 m0.5991.601
1 吴浩,赵国彦,马少维,等.滨海基岩矿床开采防水矿岩柱高度的确定[J].中国地质灾害与防治学报,2014,25(1):44-50.
WuHao,ZhaoGuoyan,MaShaowei,et al.Design on the size of waterproof pillar(rock) in subsea bedrock mining [J].The Chinese Journal of Geological Hazard and Control, 2014,25(1): 44-50.
2 刘钦,岳严良,李威.三山岛金矿海底开采对周边建筑安全的影响评价[J].黄金,2009,30(11):29-32.
LiuQin,YueYanliang,LiWei.Influence evaluation of the undersea mining to the nearby buildings safety in Sanshandao gold mine[J].Gold,2009,30(11):29-32.
3 李猛,张吉雄,缪协兴,等.固体充填体压实特征下岩层移动规律研究[J].中国矿业大学学报,2014,43(6):969-973,980.
LiMeng,ZhangJixiong,MiaoXiexing,et al.Strata movement under compaction of solid backfill body[J].Journal of China University of Mining and Technology,2014,43(6):969-973,980.
4 栾元重,李静涛,刘娜,等.重复开采上覆岩体与地移动规律研究[[J].采矿与安全工程学报,2012, 29(1): 90-94.
LuanYuanzhong,LiJingtao,LiuNa,et al. Research on overlying strata and surface movement rule in repeated mining[J]. Journal of Mining and Safety Engineering, 2012, 29(1): 90-94.
5 贺跃光.工程开挖引起的地表移动与变形模型及监测技术研究[D].长沙:中南大学,2003.
HeYueguang.Modeling and Monitoring of Ground Surface Movements Due to Excavation[D].Changsha:Central South University,2003.
6 孔素丽,庞庆刚.厚冲积层大采深条件下的地表岩层移动规律探讨[J].金属矿山,2015,44(5):201-204.
KongSuli, PangQinggang. Discussion on ground movement and deformation of the thick unconsolidated layers under the great mining[J].Metal Mine,2015,44(5):201-204.
7 GhabraieB,RenG,SmithJ. Application of 3D laser scanner optical transducers and digital image processing techniques in physical modelling of mining-related strata movement [J].International Journal of Rock Mechanics and Mining Sciences,2015,80:219-230.
8 《采矿设计手册》编委会.采矿设计手册[M].北京:中国建筑工业出版社,1987.
The Editorial Committee of Mining Design Handbook. Mining Design Handbook[M]. Beijing:China Building Industry Press, 1987.
9 李夕兵,刘志祥,彭康,等.金属矿滨海基岩开采岩石力学理论与实践[J].岩石力学与工程学报,2010,29(10):1945-1953.
LiXibing, LiuZhixiang, PengKang, et al.Theory and practice of rock mechanics related to exploitation of undersea metal mine[J].Chinese Journal of Rock Mechanics and Engineering,2010,29(10):1945-1953.
10 熊志化,张继承,邵惠鹤.基于高斯过程的软测量建模[J].系统仿真学报,2005,17(4):793-794,800.
XiongZhihua, ZhangJicheng, ShaoHuihe.GP-basedsoft sensor moderling[J].Journal of System Simulation,2005,17(4):793-794, 800.
11 苏国韶,燕柳斌,张小飞,等.基坑位移时间序列预测的高斯过程方法[J].广西大学学报(自然科学版),2007,32(2):223-226.
SuGuoshao,YanLiubin,ZhangXiaofei,et al. Time series prediction of foundation pit displacement using Gaussian process method[J].Journal of Guangxi University (Natural Science Edition),2007,32(2):223-226.
12 HeS,WuQ H. A novel group search optunizer inspired by animal behavioral ecology[C]//2006 IFFF Congress Evolutionary Computation. Vancouver:IEEE,2006:1272-1278.
13 刘钦,刘志祥,李地元,等.金属矿开采岩层移动角预测知识库模型及其工程应用[J].中南大学学报(自然科学版), 2011,42(8):2446-2452.
LiuQin,LiuZhixiang,LiDiyuan,et al. Knowledge bank model to predict motion angle of terrane in metal deposit and its application in engineering[J].Journal of Central South University(Science and Technology),2011,42(8):2446-2452.
14 高栗,李夕兵,张楚璇.地下金属矿山岩层移动角选取的进化支持向量机模型及工程应用[J].采矿与安全工程学报, 2014,31(5):795-802.
GaoLi,LiXibing,ZhangChuxuan.Nonlinear SVM with GA in determination of the motion angle of terrene in underground metal mine and its application in engineering[J].Journal of Mining and Safety Engineering,2014,31(5):795-802.
15 王强,郭广礼.基于GM(1,1)模型的岩层移动预测[J].金属矿山,2010,39(2):35-37.
WangQiang, GuoGuangli. Prediction of strata movement based on GM (1,1) model [J] .Metal Mine,2010,39(2):35-37.
16 曹帅,杜翠凤,母昌平,等.崩落法转充填法采矿地表移动二维离散元程序数值模拟及其规律验证[J].岩土力学,2015,36(6):1737-1743.
CaoShuai,DuCuifeng,MuChangping,et al. UDEC-based modelling of mining surface movement due to transforming from block caving to sublevel filling and its law verification[J].Rock and Soil Mechanics,2015,36(6):1737-1743.
17 SalmiE F, HosseinzadehS.Slope stability assessment using both empirical and numerical methods: A case study[J].Bulletin of Engineering Geology and the Environment, 2014,74(1):1-13.
[1] 张宝林,苗雅娜,苏艳平,李会中. “地物化三场异常耦合理论”及其在隐伏金多金属矿床定位预测中的应用[J]. 黄金科学技术, 2018, 26(4): 431-442.
[2] 陈静,胡继春,逯永卓,卢世银,王树林,徐贝贝. 东昆仑小灶火地区钼矿化正长花岗岩年代学、地球化学特征及其地质意义[J]. 黄金科学技术, 2018, 26(4): 465-472.
[3] 张琪彬, 张朋, 徐忠华, 刘向东, 张亮亮, 王斌, 王珊珊. 山东牟平阎家疃金矿床地质特征及成因探讨[J]. 黄金科学技术, 2018, 26(3): 279-288.
[4] 卢富然, 陈建宏. 基于AHP和熵权TOPSIS模型的岩爆预测方法[J]. 黄金科学技术, 2018, 26(3): 365-371.
[5] 胡华瑞, 李旭东, 陈庆发, 高飞红. 金属矿床地下采矿方法分类表的修订[J]. 黄金科学技术, 2018, 26(3): 387-394.
[6] 雷阿丽, 吴彩斌, 江领培. 某低品位伴生银铅锌多金属矿选矿工艺试验研究[J]. 黄金科学技术, 2018, 26(2): 212-218.
[7] 张文伟, 底青云, 雷达, 马凤山. 物探新方法-多通道瞬变电磁法在金属矿勘探中的应用[J]. 黄金科学技术, 2018, 26(1): 1-8.
[8] 郑慕婷,张术根,贺忠春. 湖南康家湾金银多金属矿床金银赋存状态及其与成矿演化的关系[J]. 黄金科学技术, 2017, 25(6): 31-42.
[9] 丁剑锋. 某金矿矿仓治理研究[J]. 黄金科学技术, 2017, 25(4): 52-57.
[10] 徐忠华,王福江,周明岭,白宜娜,赵成乐,胡秉谦. 胶东磨山金矿床主要金属矿物的矿物学特征及矿床成因研究[J]. 黄金科学技术, 2017, 25(3): 28-37.
[11] 樊志勇,邱慧远,付旭,王可祥,胡格吉乐吐. 内蒙古维拉斯托大型斑岩型锡多金属找矿勘查及启示[J]. 黄金科学技术, 2017, 25(1): 9-17.
[12] 李惠,禹斌,马久菊,李德亮,孙凤舟,李永才,阮怡箫,魏江,赵佳祥,王俊,王一大,李上,魏子鑫. 构造叠加晕找盲矿法的先进性及典型案例[J]. 黄金科学技术, 2016, 24(6): 15-23.
[13] 薛兰花,史老虎. 内蒙古多伦义盛店铀银多金属矿地质特征及控矿因素分析[J]. 黄金科学技术, 2016, 24(3): 21-28.
[14] 杨宝荣,马忠贤,熊生云 . 青海都兰哈西哇金多金属矿床有用矿物赋存状态研究[J]. 黄金科学技术, 2016, 24(3): 52-57.
[15] 王晓敏. 黑龙江十四工段地区金多金属矿找矿前景分析[J]. 黄金科学技术, 2016, 24(1): 53-58.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!