img

QQ群聊

img

官方微信

高级检索

黄金科学技术 ›› 2022, Vol. 30 ›› Issue (3): 404-413.doi: 10.11872/j.issn.1005-2518.2022.03.037

• 采选技术与矿山管理 • 上一篇    

基于正态隶属度—属性区间识别模型的岩爆倾向等级预测

贡力1,2(),陆丽丽1(),靳春玲1,梁栋3,周汉国3,谢平3   

  1. 1.兰州交通大学土木工程学院,甘肃 兰州 730070
    2.兰州交通大学调水工程及输水安全研究所,甘肃 兰州 730070
    3.中国中铁科学研究院有限公司,四川 成都 610000
  • 收稿日期:2021-03-05 修回日期:2021-08-29 出版日期:2022-06-30 发布日期:2022-09-14
  • 通讯作者: 陆丽丽 E-mail:gongl@mail.lzjtu.cn;lullin@qq.com
  • 作者简介:贡力(1977-),男,江苏丹阳人,教授,博士生导师,从事深埋隧道及输水工程方面的研究工作。gongl@mail.lzjtu.cn
  • 基金资助:
    国家自然科学基金项目“西北盐渍干寒地区多因素耦合作用下长距离明渠的劣化机理研究”(51969011);甘肃省科技计划资助项目“ 黄河流域突发水污染应急调控关键技术与应用”(20JR10RA274)

Propensity Grade Prediction of Rockburst Based on Normal Membership-Attribute Interval Recognition Model

Li GONG1,2(),Lili LU1(),Chunling JIN1,Dong LIANG3,Hanguo ZHOU3,Ping XIE3   

  1. 1.College of Civil Engineering, Lanzhou Jiaotong University, Lanzhou 730070, Gansu, China
    2.Institute of Water Diversion Engineering and Water Security, Lanzhou Jiaotong University, Lanzhou 730070, Gansu, China
    3.China Railway Academy Co. , Ltd. , Chengdu 610000, Sichuan, China
  • Received:2021-03-05 Revised:2021-08-29 Online:2022-06-30 Published:2022-09-14
  • Contact: Lili LU E-mail:gongl@mail.lzjtu.cn;lullin@qq.com

摘要:

岩爆是地下工程开挖面临的关键问题之一,为了准确预测深埋隧洞中岩爆烈度倾向等级,提出了正态隶属度—属性区间识别模型的岩爆预测方法。针对岩爆倾向等级属于典型的多属性有序分割类问题,构建了属性区间识别模型,并将岩爆倾向等级划分为4个等级进行预测。根据岩爆发生的成因和机理,选取应力系数、脆性系数、弹性应变指数和岩石完整性系数作为预测指标,考虑各指标之间、指标与标准等级之间的交互关系,采用正态隶属度函数和Jousselme距离计算评价指标权重。结合13个深埋隧洞工程对该预测模型进行准确性测试,并以双江口水电站SPD9厂房为例进行工程实例验证,该模型预测结果与实际相吻合,证明该模型用于具体工程实践中是可行且有效的,研究结果可为类似深埋隧洞岩爆倾向等级预测提供新的思路。

关键词: 深埋隧洞, 岩爆倾向等级, 岩爆预测, 正态隶属度函数, 属性区间识别模型, 均化系数

Abstract:

Rockburst is one of the key problems in underground engineering excavation,in order to accurately predict the grade of rockburst propensity in deep-buried tunnels,a rockburst prediction method based on the normal membership degree-attribute interval recognition model was proposed.Due to the rockburst propensity is a typical multi-attribute orderly segmentation problem,the attribute interval recognition model was constructed to divide the rockburst propensity into four grades for prediction.The occurrence of rockburst is affected by engineering geology,and the geological parameter is usually an interval value.The attribute interval recognition model can be better applied to the problem that each grade index value is an interval value.According to the mechanism of rockburst,the stress coefficient,brittleness coefficient,elastic strain index and rock integrity coefficient were selected as predictive indicators,considering the interaction between the indicators and the standard grade,the normal membership function and Jousselme distance were used to calculate the weight of the index.The method had different weights for the measured values of different indexes under the same index system,which can avoid the drawback that the traditional method didn’t consider the interaction relationship between the indexes,and improve the robustness of the model.The accuracy of the prediction model was tested with 13 deep-buried tunnel projects.Since the value of the averaging coefficient had a greater impact on the prediction accuracy of the model,in order to obtain the optimal value of the averaging coefficient,the step size was 0.1 and selected within the interval [0.05,0.95].The analysis shows that when the averaging coefficient is 0.65,the prediction accuracy of the model is the highest,which is 92.31%.The left bank of SPD9 in the Huangjiangkou hydropower project was used to verify the model.The prediction results are consistent with the actual rockburst propensity grade.The prediction results prove that the model is feasible and effective in specific engineering practice,and it can provide new ideas for predicting the rockburst propensity grade in similar deep-buried tunnels.

Key words: deep-buried tunnels, rockburst propensity grade, rockburst prediction, normal membership function, attribute interval recognition model, averaging coefficient

中图分类号: 

  • TD45

表1

岩爆倾向等级的特征描述"

岩爆倾向等级分级特征描述
无岩爆(Ⅰ级)表层围岩没有出现爆炸脱落、剥离等现象,对施工基本无影响
弱岩爆(Ⅱ级)表层围岩出现爆裂脱落、剥离等现象,并且内部不时出现轻微噼啪、撕裂声,对施工影响较小
中等岩爆(Ⅲ级)围岩爆裂脱落、剥离现象较严重,出现少量弹射、偶尔抛射现象,时常发出尖锐爆裂声音,破坏范围明显,对施工有一定影响
强岩爆(Ⅳ级)围岩大片爆裂脱落,出现强烈弹射现象,持续发出尖锐爆裂声音,围岩急剧变形,严重影响施工

表2

典型深埋隧洞原始数据"

深埋隧洞编号工程名称评价指标实测值文献来源
σθcσctWetkv
1天生桥二级水电站引水隧洞0.3024.06.600.73陈祥等(2009)、张彪等(2017)
2瀑布沟地下水电站地下洞室0.3324.65.000.80徐琛等(2017)
3二滩水电站2#支洞0.4129.77.300.64殷欣等(2020)、张彪等(2017)
4鲁布革水电站引水隧洞0.2327.87.800.69陈祥等(2009)、张彪等(2017)
5李家峡水电站地下洞室0.1023.05.700.34张研等(2011)、殷欣等(2020)
6鱼子溪水电站引水隧洞0.5314.89.000.71陈祥等(2009)、张彪等(2017)
7Vietas水电站引水隧洞0.4426.75.500.73殷欣等(2020)
8太平驿水电站引水隧洞0.3817.69.000.75陈祥等(2009)、张研等(2011)
9锦屏一级水电站引水隧洞0.6712.03.500.53徐琛等(2017)
10猴子岩水电站引水隧洞0.5428.54.710.55贾哲强等(2016)
11锦屏二级水电站引水隧洞0.8218.53.800.80陈祥等(2009)、张彪等(2017)
12龙羊峡水电站地下洞室0.1131.27.400.42刘冉等(2019)、殷欣等(2020)
13挪威Sima水电站地下厂房0.2721.75.000.81李鹏程等(2019)

表3

指标概率分配表"

评价指标岩爆倾向等级基本概率分配
Ⅰ级Ⅱ级Ⅲ级Ⅳ级
σθ /σc0.50000.50000.00000.0000
σc /σt0.00000.19300.80700.0000
Wet0.00000.00000.00001.0000
kv0.00000.00000.78000.2200

表4

各指标间距离"

评价指标σθ /σcσc /σtWetkv
σθ /σc0.00000.70550.86600.7605
σc /σt0.70550.00000.91880.2078
Wet0.86600.91880.00000.7800
kv0.76050.20780.78000.0000

表5

深埋隧洞指标权重值"

深埋隧洞编号工程名称指标权重值
σθ /σcσc /σtWetkv
1天生桥二级水电站引水隧洞0.18960.33150.12350.3554
2瀑布沟地下水电站地下洞室0.16930.25340.32060.2567
3二滩水电站2#支洞0.29400.34510.04090.3200
4鲁布革水电站引水隧洞0.15810.44690.10480.2902
5李家峡水电站地下洞室0.44010.07150.03100.4574
6鱼子溪水电站引水隧洞0.28780.32650.12060.2651
7Vietas水电站引水隧洞0.22770.35220.14940.2707
8太平驿水电站引水隧洞0.05240.34390.26200.3417
9锦屏一级水电站引水隧洞0.28110.23350.28370.2017
10猴子岩水电站引水隧洞0.28770.26220.25010.2000
11锦屏二级水电站引水隧洞0.21070.27910.21790.2923
12龙羊峡水电站地下洞室0.36640.11530.04560.4726
13挪威Sima水电站地下厂房0.14870.21040.37210.2688

图1

正确预测岩爆个数与ε值的关系"

表6

岩爆预测评价等级"

深埋隧洞编号综合属性测度本文预测结果实际级别
μ1μ2μ3μ4
10.06640.31620.28360.3338
20.04750..22490.31620.4113
30.10910.46470.38530.0409
40.11450.40750.29770.1803Ⅰ或Ⅱ
50.57420.23660.17450.0147
60.00230.23900.50670.2520
70.25280.24730.21480.2551
80.01650.08840.33250.5626Ⅳ(误判)400多例,等级不定
90.09010.33670.46540.1078
100.09350.38700.35090.1686Ⅱ或Ⅲ
110.00000.12090.39370.4854Ⅲ或Ⅳ
120.54780.27450.13720.0404
130.02860.15730.34470.4693Ⅲ或Ⅳ

表7

SPD9洞室指标原始数据及指标权重值"

桩号评价指标实测值指标权重值
σθ /σcσc /σtWetkvσθ /σcσc /σtWetkv
0+1230.5010.25.00.700.25100.19280.32930.2269
0+2000.629.45.50.750.12610.28780.29310.2931
0+3010.5710.245.00.700.28890.15420.28890.2681
0+4061.0910.565.50.750.25820.27480.27480.1923
0+5700.5610.614.50.700.30460.08170.31340.3003

表8

SPD9洞室岩爆预测评价等级"

桩号综合属性测度本文预测结果实际级别
μ1μ2μ3μ4
0+1230.00000.12760.48000.3924
0+2000.00000.01770.54190.4404
0+3010.00000.11260.46330.4241
0+4060.00000.00000.26150.7385
0+5700.00000.14800.45240.3996
Adoko A C, Gokceoglu C, Wu L,et al,2013.Knowledge-based and data-driven fuzzy modeling for rockburst prediction[J].International Journal of Rock Mechanics and Mining Sciences,61:86-95.
Chen Xiang, Sun Jinzhong, Zhang Jiekun,et al,2009.Judgment indexes and classification criteria of rock-burst with the extension judgment method[J].China Civil Engineering Journal,42(9):82-88.
Dong L J, Li X B, Peng K,2013.Prediction of rockburst classification using random forest[J].Transactions of Nonferrous Metals Society of China,23(2):472-477.
Jia Zheqiang, Zhang Ru, Zhang Yanfei,et al,2016.Integrated prediction for rockburst of underground powerhouse of Houziyan hydropower station[J].Chinese Journal of Geotechnical Engineering,38(Supp.2):110-116.
Kidybinski A,1981.Bursting liability indices of coal[J].International Journal of Rock Mechanics and Mining Sciences,18(4):295-304.
Li Hang,2020.Research on Tunnel Rockburst Prediction Method Based on Combination Weight Ideal Point Method-Database[D].Beijing:China University of Geosciences (Beijing).
Li Pengcheng, Ye Yicheng, Wang Qihu,et al,2019.Grey evaluation rockburst prediction model based on normal whitening weight function[J].Industrial Minerals & Processing,48(5):16-22,26.
Li Renhao, Gu Helong, Li Xibing,et al,2020.A PSO-RBF neural network model for rockburst tendency prediction[J].Gold Science and Technology,28(1):134-141.
Lin Dayong, Lei Mingfeng, Cao Haorong,et al,2018.Study on construction risk of shield tunnel under-passing existing railway by fuzzy comprehensive evaluation[J].Journal of Railway Science and Engineering,15(5):1347-1355.
Liu Ran, Ye Yicheng, Zhang Guangquan,et al,2019.Grading prediction model of rockburst based on rough set-multidiensional normal cloud[J].Metal Mine,(3):48-55.
Liu Xiaoyue, Yang Wei, Zhang Xuemei,2021.Rockburst prediction of multi-dimensional cloud model based on improved hierarchical analytic method and critic method[J].Journal of Hunan University(Natural Sciences),48(2):118-124.
Pei Qitao, Li Haibo, Liu Yaqun,et al,2013.Rockburst prediction based on a modified grey[J].Chinese Journal of Rock Mechanics and Engineering,32(10):2088-2093.
Russenes B F,1974.Analysis of Rock Spalling for Tunnels in Steep Valley Sides[D].Trondheim:Norwegian Institute of Technology.
Shen Y N, Zhang J B,2019.Equipment management performan-ce assessment based on cloud model and evidence theory[J].Systems Engineering and Electronics,41(5):1049-1055.
Sun Chensheng,2019.A prediction model of rock burst in tunnel based on the improved MATLAB-BP neural network[J].Journalof Chongqing Jiaotong University(Natural Science),38(10):41-49.
Tian Rui, Meng Haidong, Chen Shijiang,et al,2020.Prediction of intensity classification of rockburst based on deep neural network[J].Journal of China Coal Society,45(Supp.1):191-201.
Wang M W, Liu Q Y, Wang X,et al,2020.Prediction of rockburst based on multidimensional connection cloud model and set pair analysis[J].International Journal of Geomechanics,20(1).DOI:10.1061/(ASCE)GM.1943-5622.0001546 .
doi: 10.1061/(ASCE)GM.1943-5622.0001546
Wang Yingchao, Jing Hongwen, Ji Xianwei,et al,2014.Model for classification and prediction of rock burst intensity in a deep underground engineering with rough set and efficacy coefficient method[J].Journal of Central South University(Science and Technology),45(6):1992-1997.
Wang Yingchao, Jing Hongwen, Zhang Qiang,et al,2015.A normal cloud model-based study of grading prediction of rockburst intensity in deep underground engineering[J].Rock and Soil Mechanics,36(4):1189-1194.
Wang Yuanhan, Li Wodong, Li Qiguang,et al,1998.Method of fuzzy comprehensive evaluations for rockburst prediction[J].Chinese Journal of Rock Mechanics and Engineering,(5):15-23.
Xu Chen, Liu Xiaoli, Wang Enzhi,et al,2017.Prediction and classification of strain mode rockburst based on five-factor crierion and combined weight-ideal point method[J].Chinese Journal of Geotechnical Engineering,39(12):2245-2252.
Yin Xin, Liu Quansheng, Wang Xinyu,et al,2020.Prediction model of rockburst intensity classification based on combined weighting and attribute interval recognition theory[J].Journal of China Coal Society,45(11):3772-3780.
Zhang Biao, Dai Xingguo,2017.rockburst intensity grade based on index distance and uncertainty measure[J].Rock and Soil Mechanics,38(Supp.2):257-265.
Zhang Guangcun, Gao Qian, Du Juqiang,et al,2013.Rockburst criterion based on artificial neural networks and nonlinear regression[J].Journal of Central South University(Science and Technology),44(7):2977-2981.
Zhang Jingjian, Fu Bingjun,2008.Rock burst and its criteria and control[J].Chinese Journal of Rock Mechanics and Engineering,27(10):2034-2042.
Zhang Lewen, Zhang Deyong, Qiu Daohong,2010.Application of extension evaluation based on rough set in rockburst prediction [J] .Coal Coal Journal,35(9):1461-1465.
ZhangYan, Su Guoshao, Yan Liubin,2011.Method of identifying rockburst grades based on Gaussian process machine learning[J].Chinese Journal of Underground Space and Engineering,7(2):392-397.
Zou Qiang, Zhou Jianzhong, Yang Xiaoling,et al,2011.A comprehensive assessment model for severity degree of dam failure impact based on attribute interval recognition theory[J].Journal of Sichuan University (Engineering Science Edition),43(2):45-50.
陈祥,孙进忠,张杰坤,等,2009.岩爆的判别指标和分级标准及可拓综合判别方法[J].土木工程学报,42(9):82-88.
贾哲强,张茹,张艳飞,等,2016.猴子岩水电站地下厂房岩爆综合预测研究[J].岩土工程学报,38(增2):110-116.
李航,2020.基于组合权重理想点法—数据库的隧洞岩爆预测方法研究[D].北京:中国地质大学(北京).
李鹏程,叶义成,王其虎,等,2019.基于正态白化权函数的灰评估岩爆预测模型[J].化工矿物与加工,48(5):16-22,26.
李任豪,顾合龙,李夕兵,等,2020.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,28(1):134-141.
林大涌,雷明锋,曹豪荣,等,2018.盾构下穿运营铁路施工风险模糊综合评价方法研究[J].铁道科学与工程学报,15(5):1347-1355.
刘冉,叶义成,张光权,等,2019.岩爆分级预测的粗糙集—多维正态云模型[J].金属矿山,(3):48-55.
刘晓悦,杨伟,张雪梅,2021.基于改进层次法与CRITIC法的多维云模型岩爆预测[J].湖南大学学报(自然科学版),48(2):118-124.
裴启涛,李海波,刘亚群,等,2013.基于改进的灰评估模型在岩爆中的预测研究[J].岩石力学与工程学报,32(10):2088-2093.
孙臣生,2019.基于改进MATLAB-BP神经网络算法的隧道岩爆预测模型[J].重庆交通大学学报(自然科学版),38(10):41-49.
田睿,孟海东,陈世江,等,2020.基于深度神经网络的岩爆烈度分级预测研究[J].煤炭学报,45(增1):191-201.
王迎超,靖洪文,吉咸伟,等,2014.深埋地下工程岩爆烈度分级预测的RS-功效系数模型[J].中南大学学报(自然科学版),45(6):1992-1997.
王迎超,靖洪文,张强,等,2015.基于正态云模型的深埋地下工程岩爆烈度分级预测研究[J].岩土力学,36(4):1189-1194.
王元汉,李卧东,李启光,等,1998.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,(5):15-23.
徐琛,刘晓丽,王恩志,等,2017.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,39(12):2245-2252.
殷欣,刘泉声,王心语,等,2020.基于组合赋权和属性区间识别理论的岩爆烈度分级预测模型[J].煤炭学报,45(11):3772-3780.
张彪,戴兴国,2017.基于指标距离与不确定度量的岩爆云模型预测研究[J].岩土力学,38(增2):257-265.
张光存,高谦,杜聚强,等,2013.基于人工神经网络及非线性回归的岩爆判据[J].中南大学学报(自然科学版),44(7):2977-2981.
张镜剑,傅冰骏,2008.岩爆及其判据和防治[J].岩石力学与工程学报,27(10):2034-2042.
张乐文,张德永,邱道宏,2010.基于粗糙集的可拓评判在岩爆预测中的应用[J].煤炭学报,35(9):1461-1465.
张研,苏国韶,燕柳斌,2011.基于高斯过程机器学习的岩爆等级识别方法[J].地下空间与工程学报,7(2):392-397.
邹强,周建中,杨小玲,等,2011.属性区间识别模型在溃坝后果综合评价中的应用[J].四川大学学报(工程科学版),43(2):45-50.
[1] 田睿,孟海东,陈世江,王创业,孙德宁,石磊. 基于机器学习的3种岩爆烈度分级预测模型对比研究[J]. 黄金科学技术, 2020, 28(6): 920-929.
[2] 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.
[3] 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.
[4] 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.
[5] 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   
No Suggested Reading articles found!