img

QQ群聊

img

官方微信

高级检索

黄金科学技术 ›› 2020, Vol. 28 ›› Issue (1): 134-141.doi: 10.11872/j.issn.1005-2518.2020.01.053

• 采选技术与矿山管理 • 上一篇    下一篇

基于PSO-RBF神经网络模型的岩爆倾向性预测

李任豪1(),顾合龙1,李夕兵1,侯奎奎2,朱明德2,王玺2   

  1. 1.中南大学资源与安全工程学院,湖南 长沙 410083
    2.山东黄金集团有限公司深井开采实验室,山东 烟台 261442
  • 收稿日期:2019-05-22 修回日期:2019-11-04 出版日期:2020-02-29 发布日期:2020-02-26
  • 作者简介:李任豪(1995-),男,湖南双峰人,硕士研究生,从事安全理论与深部矿山安全研究工作。scnhao@csu.edu.cn
  • 基金资助:
    国家自然科学基金重点项目“深部资源开采诱发岩体动力灾害机理与防控方法研究”(41630642)

A PSO-RBF Neural Network Model for Rockburst Tendency Prediction

Renhao LI1(),Helong GU1,Xibing LI1,Kuikui HOU2,Deming ZHU2,Xi WANG2   

  1. 1.School of Resource and Safety Engineering,Central South University,Changsha 410083,Hunan,China
    2.Deep Mining Laboratory Branch of Shandong Gold Group Co. ,Ltd. ,Laizhou 261442,Shandong,China
  • Received:2019-05-22 Revised:2019-11-04 Online:2020-02-29 Published:2020-02-26

摘要:

鉴于岩爆机理的复杂性以及岩爆发生前后信号提取困难的现状,对高应力区进行岩爆倾向性预测研究具有现实意义。为提高岩爆预测的准确性,基于岩爆预测多维非线性的特点,选取4个影响岩爆发生的核心指标作为判决依据,结合粒子群优化算法(PSO)与径向基神经网络(RBF)建立了PSO-RBF神经网络岩爆预测模型。采用试错法确定隐含层节点数后,进一步利用国内外典型工程数据对模型参数隐含层基函数中心ci,隐含层节点宽度σi以及隐含层与输出层间权重因子w进行学习优化以获取最优参数,并将所建立的模型应用于实际工程的岩爆倾向性预测。结果表明:利用该模型预测的岩爆等级与实际岩爆情况基本相符,相对误差率为10%,精度较以往预测方法有显著提高。

关键词: 岩石力学, 岩爆预测, 岩爆倾向性, RBF神经网络, 粒子群优化, 智能优化

Abstract:

Rockburst is one of the typical dynamic disasters in the field of underground engineering.The forecast of rockburst tendency in high stress area is of great practical significance.Due to the complexity of rockburst mechanism,the existing prediction models were difficult to reflect the multi-dimensional nonlinear characteristics of rockburst,which result in the low rockburst tendency prediction accuracy.In order to forecast rockburst tendency more accurately, a new rockburst tendency forecast model was proposed by combining particle swarm optimization (PSO) with radial basis function neural network (RBF).After determining the number of the hidden layer nodes by trial-by-error method,the parameters of RBF neural network including the center of basic function,width of the hidden layer node and the output weights formed a multi-dimensional vector,and were optimized as population particle of the PSO algorithm for the purpose of getting the optimal solution within the scope of global solvable space.Further,this paper referenced domestic and foreign related literature and choose four major rockburst tendency indicators,including the uniaxial compressive strength,the rock stress index,the rock brittleness index and the elastic energy index.25 typical practical rockburst engineering cases were took as the learning samples to train the PSO-RBF neural network model parameters.Finally,the established model of PSO-RBF was applied to rockburst tendency prediction of practical engineering.The results show it is approved that the prediction results of the proposed model in this paper are approximately consistent with the actual rockburst status.The relative error rate of PSO-RBF prediction model is 10%,and the accurate is significantly improved than prevenient prediction method.The PSO-RBF neural network rockburst tendency prediction model has a certain practicality and could provide effective guidance for similar projects.

Key words: rock mechanics, rockburst prediction, rockburst tendency, RBF neural network, particle swarm optimization algorithm, intelligent optimization

中图分类号: 

  • TU-45

图1

RBF神经网络拓扑结构"

表1

岩爆倾向性指标分级判据"

岩爆分级σcσθ/σcσc?/σtWeq
Ⅰ(无岩爆)<80.0<0.3>40.0<2.0
Ⅱ(弱岩爆)80.0~120.00.3~0.526.7~40.02.0~4.0
Ⅲ(中岩爆)120.0~180.00.5~0.714.5~26.74.0~6.0
Ⅳ(强岩爆)>180.0>0.7<14.5>6.0

图2

PSO-RBF神经网络岩爆预测模型"

表2

国内外工程岩爆数据"

样本序号岩爆指标实际岩爆等级
σcσθ?/σcσc?/σtWeq
11700.5315.049.00
21200.8218.463.80
31400.7717.505.50
4200.086.671.39
51200.3724.005.10
6200.196.671.39
71200.6124.005.10
81800.4221.695.00
91400.7717.505.50
101150.1023.005.70
111760.3124.119.30
121150.5576.675.70
131650.3817.559.00
141320.4313.987.44
151280.5514.666.43
161900.4711.093.97
171700.539.923.97
18830.3712.773.20
192260.4013.147.30
20540.634.463.17
212370.4413.426.38
221570.5813.26.30
231480.4517.55.10
241320.3920.94.60
251070.2041.01.70

表3

岩爆倾向性预测结果"

样本序号岩爆指标输出特征值PSO-RBF预测等级实际岩爆等级RBF预测等级Hoek岩爆判据
σcσθ?/σcσc?/σtWeq
11640.642.808.414.1671Ⅲ*Ⅲ~Ⅳ
21460.586.225.132.6765Ⅱ~Ⅲ
31320.3021.394.220.9672
41490.556.095.603.2167
51390.414.85.382.0910
61410.4310.764.871.9851Ⅲ*
71520.573.717.263.7762Ⅳ*
81350.3816.924.081.1662Ⅱ*
91610.692.977.093.0102Ⅳ*
101300.3129.863.961.1537
1 许迎年,徐文胜,王元汉,等.岩爆模拟试验及岩爆机理研究[J].岩石力学与工程学报,2002,21(10):1462-1466.
Xu Yingnian,Xu Wensheng,Wang Yuanhan,et al.Simulation testing and mechanism studies on rockburst[J].Chinese Journal of Rock Mechanics and Engineering,2002,21(10):1462-1466.
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 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.
Lu Furan,Chen Jianhong.Rockburst prediction method based on AHP and entropy weight TOPSIS model[J].Gold Science and Technology,2018,26(3):365-371.
4 李夕兵.岩石动力学基础与应用[M].北京:科学出版社,2014.
Li Xibing.Rock Dynamics Fundamentals and Application[M].Beijing:Science Press,2014.
5 张镜剑,傅冰骏.岩爆及其判据和防治[J].岩石力学与工程学报,2008,27(10):2034-2042.
Zhang Jingjian,Fu Bingjun.Rockburst and its criteria and control[J].Chinese Journal of Rock Mechanics and Engineering,2008,27(10):2034-2042.
6 吴昊,陈炳瑞,池秀文,等.基于区域性微震活动的深部采场稳定性分析[J].黄金科学技术,2018,26(3):325-333.
Wu Hao,Chen Bingrui,Chi Xiuwen,et al.Stability analysis of deep stope based on regional microseismic activity[J].Gold Science and Technology,2018,26(3):325-333.
7 Dou L,Chen T,Gong S,et al.Rockburst hazard determination by using computed tomography technology in deep workface[C]//The First International Symposium on Mine Safety Science & Engineering.Beijing:Chinese Academy of Safety Science and Technology,2012:1205-1212.
8 李长洪,张立新,张磊,等.灰色突变理论及声发射在岩爆预测中的应用[J].中国矿业,2008,17(8):87-90.
Li Changhong,Zhang Lixin,Zhang Lei,et al.Application of grey catastrophe theory and acoustic emission in rock burst prediction[J].China Mining Magazine,2008,17(8):87-90.
9 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.
10 史秀志,周健,董蕾,等.未确知测度模型在岩爆烈度分级预测中的应用[J].岩石力学与工程学报,2010,29(增1):2720-2726.
Shi Xiuzhi,Zhou Jian,Dong Lei,et al.Application of unascertained measurement model to prediction of classification of rockburst intensity[J].Chinese Journal of Rock Mechanics and Engineering,2010,29(Supp.1):2720-2726.
11 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.Rock-burst proneness prediction based on improved RS-TOPSIS model[J].Gold Science and Technology,2019,27(1):80-88.
12 Dong L J,Li X B,Peng K.Prediction of rockburst classification using Random Forest[J].Transactions of Nonferrous Metals Society of China,2013,23(2):472-477.
13 张德永,王玉洲,张志豪.RBF神经网络在岩爆预测中的应用[J].土工基础,2013,27(5):31-33,59.
Zhang Deyong,Wang Yuzhou,Zhang Zhihao.Application of RBF neural network in rockburst prediction[J].Soil Engineering and Foundation,2013,27(5):31-33,59.
14 李夕兵,朱玮,刘伟军,等.基于主成分分析法与RBF神经网络的岩体可爆性研究[J].黄金科学技术,2015,23(6):58-63.
Li Xibing,Zhu Wei,Liu Weijun,et al.Research on rock mass blastability based on principal component analysis and RBF neural network[J].Gold Science and Technology,2015,23(6):58-63.
15 李爱国,覃征,鲍复民,等.粒子群优化算法[J].计算机工程与应用,2002,38(21):1-3,17.
Li Aiguo,Qin Zheng,Bao Fumin,et al.Particle swarm optimization algorithm[J].Computer Engineering and Applications,2002,38(21):1-3,17.
16 谢旭,陈芸芝.基于PSO-RBF神经网络模型反演闽江下游水体悬浮物浓度[J].遥感技术与应用,2018,33(5):900-907.
Xie Xu,Chen Yunzhi.Retrieval of total suspended matter in the lower of Minjiang River based on PSO-RBF[J].Remote Sensing Technology and Application,2018,33(5):900-907.
17 杨金林,李夕兵,周子龙,等.基于粗糙集理论的岩爆预测模糊综合评价[J].金属矿山,2010,39(6):26-29.
Yang Jinlin,Li Xibing,Zhou Zilong,et al.A fuzzy assessment method of rockburst prediction based on rough set theory[J].Metal Mine,2010,39(6):26-29.
18 赵洪波.岩爆分类的支持向量机方法[J].岩土力学,2005,26(4):642-644.
Zhao Hongbo.Classification of rockburst using support vector machine[J].Rock and Soil Mechanics,2005,26(4):642-644.
19 周科平,雷涛,胡建华.深部金属矿山RS-TOPSIS岩爆预测模型及其应用[J].岩石力学与工程学报,2013,32(增2):3705-3711.
Zhou Keping,Lei Tao,Hu Jianhua.RS-TOPSIS model of rockburst prediction in deep metal mines and its application[J].Chinese Journal of Rock Mechanics and Engineering,2013,32(Supp.2):3705-3711.
20 张乐文,张德永,李术才,等.基于粗糙集理论的遗传-神经网络在岩爆预测中的应用[J].岩土力学,2012(增1):270-276.
Zhang Lewen,Zhang Deyong,Li Shucai,et al.Application of RBF neural network to rockburst prediction based on rough set theory[J].Rock and Soil Mechanics,2012(Supp.1):270-276.
21 常兴兵,张方安,唐彦杰.江边水电站引水隧洞岩爆特征及防治措施[J].西北水电,2010(2):57-59.
Chang Xingbing,Zhang Fang’an,Tang Yanjie.Rockburst characteristics of head race tunnel for Jiangbian hydropower project and countermeasures[J].Northwest Hydropower,2010(2):57-59.
[1] 卜斤革, 陈建宏. 基于粒子群算法优化BP神经网络的溶浸开采浸出率预测[J]. 黄金科学技术, 2020, 28(1): 82-89.
[2] 孙冰,罗瑜,谢杰辉,曾晟. N型组合节理类岩体单轴压缩破坏试验[J]. 黄金科学技术, 2019, 27(4): 548-556.
[3] 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.
[4] 杨仕教,王志会. 上覆公路浅埋采空区群稳定性数值模拟[J]. 黄金科学技术, 2019, 27(4): 505-512.
[5] 冯春迪,黄仁东. 红砂岩中矿物颗粒的塑性应变分析[J]. 黄金科学技术, 2019, 27(4): 557-564.
[6] 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.
[7] 肖伟晶,陈辰,李永欣,王晓军,曹世荣,韩建文. 分级加载条件下深部灰岩蠕变试验及模型[J]. 黄金科学技术, 2017, 25(2): 76-82.
[8] 李夕兵,朱玮,刘伟军,张德明. 基于主成分分析法与RBF神经网络的岩体可爆性研究[J]. 黄金科学技术, 2015, 23(6): 58-63.
[9] 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.
[10] 郭广军,刘明君,徐咏彬,程蔚,叶延龄,郑小礼,高海峰,赵荣欣. 山东焦家金矿床工程岩体稳定性分类研究[J]. J4, 2012, 20(4): 71-75.
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] 陈学俊. 青海直亥买休玛金矿床矿体特征与找矿前景分析[J]. J4, 2010, 18(4): 50 -53 .
[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] 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 .
[9] 黄俊,吴家富,鲁如魁 ,夏立元. 内蒙古兵图金矿成因探讨及找矿方向[J]. J4, 2010, 18(4): 1 -5 .
[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 .