基于高斯混合模型的采煤工作面冲击危险性评价

崔峰, 李宜霏, 贾冲, 陆长亮, 何仕凤, 张随林, 田梦琪

崔峰,李宜霏,贾冲,等. 基于高斯混合模型的采煤工作面冲击危险性评价[J]. 煤田地质与勘探,2024,52(10):85−96. DOI: 10.12363/issn.1001-1986.24.01.0072
引用本文: 崔峰,李宜霏,贾冲,等. 基于高斯混合模型的采煤工作面冲击危险性评价[J]. 煤田地质与勘探,2024,52(10):85−96. DOI: 10.12363/issn.1001-1986.24.01.0072
CUI Feng,LI Yifei,JIA Chong,et al. Rock burst hazard evaluation of coal mining face based on a Gaussian mixture model[J]. Coal Geology & Exploration,2024,52(10):85−96. DOI: 10.12363/issn.1001-1986.24.01.0072
Citation: CUI Feng,LI Yifei,JIA Chong,et al. Rock burst hazard evaluation of coal mining face based on a Gaussian mixture model[J]. Coal Geology & Exploration,2024,52(10):85−96. DOI: 10.12363/issn.1001-1986.24.01.0072

 

基于高斯混合模型的采煤工作面冲击危险性评价

基金项目: 国家自然科学基金项目(52422404、51874231);陕西省创新能力支撑计划项目(2020KJXX-006)
详细信息
    作者简介:

    崔峰,1986年生,男,河南新乡人,博士,教授。 E-mail:cuifeng9418@163.com

  • 中图分类号: TD324

Rock burst hazard evaluation of coal mining face based on a Gaussian mixture model

  • 摘要:
    目的 

    深入了解声发射或微震能量分布所蕴含的概率学信息,对于工作面回采过程中的冲击危险性评价具有重要意义。

    方法 

    以陕西大佛寺煤矿4号煤层40111工作面作为工程背景,运用物理相似模拟实验、理论分析、现场监测等相关方法进行分析,研究了声发射监测数据在回采过程中的演化规律,阐明了声发射能量概率分布呈现波动性的物理意义,提出了基于高斯混合模型(Gaussian minture model,GMM)及置信区间的冲击危险性评价指标模型,并由现场微震数据进行验证。

    结果和结论 

    结果表明:回采过程中上覆岩层周期性垮落并伴随声发射能量的集中释放。总能量的概率密度函数呈现多自由度的非对称分布,通过对比残差平方和等多项拟合效果指标,确定高斯混合模型为最佳拟合模型。基于EM(expectation maximization)算法的GMM聚类分析,将声发射事件总能量分布划分为两类:高频低能型和低频高能型,其中低频高能型与冲击事件的突发性和高能量破坏特征一致。依据概率−能量梯度变化特征,对工作面开采过程中冲击危险性进行了评估。研究成果为采煤工作面冲击危险性评价提供了概率学上的创新思路,具有在冲击地压监测预警及后续防治中的潜在应用价值。

    Abstract:
    Objective 

    Deep insights into the probabilistic information contained in the energy distribution of acoustic emission (AE) or microseismic events are significant for the rock burst hazard evaluation of coal mining face.

    Methods 

    This study investigated No.40111 mining face of the No.4 coal seam at the Dafosi Coal Mine in Shaanxi Province. Using physical simulation experiments with similar materials, theoretical analysis, and on-site monitoring, this study investigated the evolutionary patterns of AE monitoring data during coal mining and illustrated the physical meaning of fluctuations in the probability distribution of AE energy. Accordingly, this study proposed an index model for the rock burst hazard evaluation based on a Gaussian mixture model (GMM) and confidence intervals and validated the proposed model based on field microseismic data.

    Results and Conclusions 

    The results indicate that the overlying strata collapsed periodically during mining, with the collapse being accompanied by intensive release of AE energy. The probability density function (PDF) of the total energy exhibited a multi-degree-of-freedom asymmetric distribution. The comparison of multiple indices of fitting effects, such as the residual sum of squares, reveals that the GMM is the optimal fitting model. As indicated by the GMM clustering analysis based on the expectation-maximization (EM) algorithm, the total energy distribution of AE events can be categorized into two types, namely the high-frequency/low-energy and low-frequency/high-energy AE signals, with the latter type consistent with the sudden occurrence and high-energy destruction of rock burst events. This study conducted a rock burst hazard evaluation of the mining face based on the probability-energy gradient variations, providing a novel probabilistic approach for the rock burst hazard evaluation of coal mining face. The new assessment method based on probabilistic information has the potential to be applied in the monitoring, early warning, and subsequent prevention of rock bursts.

  • 图  1   工作面布置

    Fig.  1   Layout of the mining face

    图  2   地层柱状图及岩层模拟材料配比

    Fig.  2   Stratigraphic column and ratio of materials for rock layer simulation

    图  3   物理相似材料模拟实验

    Fig.  3   Physical simulation experiment for similar materials

    图  4   40111工作面回采全过程声发射特征

    Fig.  4   AE characteristics during the mining of the No.40111 mining face

    图  5   40111工作面第一次周期来压能量随时间变化

    Fig.  5   Time-varying energy during the first periodic weighting of the No.40111 mining face

    图  6   40111工作面声发射能量概率分布规律

    Fig.  6   Probability distribution pattern of the total energy of AE events in the No.40111 mining face

    图  7   单一分布函数拟合效果对比

    Fig.  7   Comparison of fitting effects of single distribution functions

    图  8   5阶高斯分布模型拟合曲线

    Fig.  8   Fitted curve of the fifth-order Gaussian distribution model

    图  9   GMM聚类算法流程

    Fig.  9   Flowchart of the GMM clustering algorithm

    图  10   回采全过程声发射总能量概率密度分布特征

    Fig.  10   Probability density distribution of the total energy of AE events during mining

    图  11   基于声发射事件总能量的冲击危险性评价

    Fig.  11   Rock burst risk assessment based on the total energy of AE events

    图  12   基于现场微震事件能量的冲击危险性评价

    Fig.  12   Rock burst risk assessment based on the energy of field microseismic events

    表  1   工作面参数

    Table  1   Parameters of the mining face

    煤层 工作面名称 走向长/m 斜长/m 采高/m
    4上 41106 1810 190 3.0
    4号 40111 1860 220 11.5
    下载: 导出CSV

    表  2   声发射监测设定参数

    Table  2   Parameters of AE monitoring

    参数 参数值
    采集频率/MHz 10
    参数间隔/μs 2 000
    峰值间隔/μs 1000
    波形门阀/dB 45
    参数门阀/dB 40
    滤波频率/kHz 20~100
    下载: 导出CSV

    表  3   典型单一分布的拟合效果指标值

    Table  3   Fitting effect index values of the typical single distribution

    分布类型 ESS/10−9 ERMS/10−6 R Ra
    威布尔分布 2.66 5.16 0.45 0.44
    t分布 1.49 3.86 0.69 0.69
    广义极值分布 1.33 3.64 0.73 0.72
    正态分布 2.85 5.34 0.41 0.41
    下载: 导出CSV

    表  4   5阶高斯混合模型的参数值

    Table  4   Parameter values of the fifth-order Gaussian mixture model

    阶数 ai/10−6 bi ci
    1 1.831 −1.0510 0.1570
    2 3.436 −0.9350 0.1787
    3 7.856 −1.1460 0.2105
    4 0.339 0.7118 0.1311
    5 6.229 0.6419 1.0400
    下载: 导出CSV

    表  5   2阶与5阶高斯混合模型的拟合效果指标值

    Table  5   Fitting effect index values of the 2-component and 5-component Gaussian mixture models

    模型 ESS/10−10 ERMS/10−6 R Ra
    2阶 8.91 3.13 0.79 0.77
    5阶 4.49 2.29 0.90 0.90
    下载: 导出CSV

    表  6   二维高斯混合模型的参数

    Table  6   Parameters of the two-dimensional Gaussian mixture model

    类别 ${\textit{π}} $ $ {\text{μ}} $/104 $ {\boldsymbol{\varSigma}} $/108
    1 0.7374 $ \left[ {\begin{array}{*{20}{c}} {0.153\;3} \\ {3.126\;1} \end{array}} \right] $ $ \left[ {\begin{array}{*{20}{c}} {0.000\;1}&{0.004\;7} \\ {0.004\;7}&{1.354\;6} \end{array}} \right] $
    2 0.2626 $ \left[ {\begin{array}{*{20}{c}} {0.140\;7} \\ {6.884\;9} \end{array}} \right] $ $ \left[ {\begin{array}{*{20}{c}} {0}&{ - 0.002\;7} \\ { - 0.002\;7}&{7.388\;1} \end{array}} \right] $
    下载: 导出CSV

    表  7   二维高斯混合模型的参数

    Table  7   Parameters of the two-dimensional Gaussian mixture model

    类别 $ \textit{π} $ ${\text{μ}} $/103 $ {\boldsymbol{\varSigma}} $/105
    1 0.9686 $ \left[ {\begin{array}{*{20}{c}} {0.860\;1} \\ {1.126\;7} \end{array}} \right] $ $ \left[ {\begin{array}{*{20}{c}} {0.287\;8}&{0.371\;3} \\ {0.371\;3}&{3.879\;2} \end{array}} \right] $
    2 0.0314 $ \left[ {\begin{array}{*{20}{c}} {1.184\;2} \\ {3.555\;5} \end{array}} \right] $ $ \left[ {\begin{array}{*{20}{c}} {0.097\;2}&{ - 0.172\;7} \\ { - 0.172\;7}&{9.316\;1} \end{array}} \right] $
    下载: 导出CSV
  • [1] 窦林名,田鑫元,曹安业,等. 我国煤矿冲击地压防治现状与难题[J]. 煤炭学报,2022,47(1):152−171.

    DOU Linming,TIAN Xinyuan,CAO Anye,et al. Present situation and problems of coal mine rock burst prevention and control in China[J]. Journal of China Coal Society,2022,47(1):152−171.

    [2] 潘一山,肖永惠,罗浩,等. 冲击地压矿井安全性研究[J]. 煤炭学报,2023,48(5):1846−1860.

    PAN Yishan,XIAO Yonghui,LUO Hao,et al. Study on safety of rockburst mine[J]. Journal of China Coal Society,2023,48(5):1846−1860.

    [3] 崔峰,张廷辉,来兴平,等. 冲击地压矿井科学产能确定初步构想[J]. 采矿与安全工程学报,2023,40(1):48−59.

    CUI Feng,ZHANG Tinghui,LAI Xingping,et al. Preliminary conception of scientific productivity determination in rock burst mines[J]. Journal of Mining & Safety Engineering,2023,40(1):48−59.

    [4] 齐庆新,李海涛,李晓鹏. 煤矿冲击危险性的定性与定量评价研究[J]. 煤炭科学技术,2021,49(4):12−19.

    QI Qingxin,LI Haitao,LI Xiaopeng. Qualitative and quantitative evaluation of impact risk in underground mine[J]. Coal Science and Technology,2021,49(4):12−19.

    [5] 姜福兴,冯宇,刘晔. 采场回采前冲击危险性动态评估方法研究[J]. 岩石力学与工程学报,2014,33(10):2101−2106.

    JIANG Fuxing,FENG Yu,LIU Ye. Dynamic evaluation method for rockburst risk before stopping[J]. Chinese Journal of Rock Mechanics and Engineering,2014,33(10):2101−2106.

    [6] 雷毅. 冲击危险性评价模型的建立及应用研究[D]. 北京:煤炭科学研究总院,2005:1–73.

    LEI Yi. Study on establishment and application of hazard evaluation model for rock-burst[D]. Beijing:China Coal Research Institute,2005:1–73.

    [7]

    CAI Wu,DOU Linming,SI Guangyao,et al. Fault-induced coal burst mechanism under mining-induced static and dynamic stresses[J]. Engineering,2021,7(5):687−700. DOI: 10.1016/j.eng.2020.03.017

    [8] 兰天伟,张志佳,袁永年,等. 矿井地质动力环境评价方法与冲击地压矿井类型划分研究[J]. 煤田地质与勘探,2023,51(2):104−113. DOI: 10.12363/issn.1001-1986.22.12.0913

    LAN Tianwei,ZHANG Zhijia,YUAN Yongnian,et al. An evaluation method for geological dynamic environments of mines and the classification of mines subjected to rock bursts[J]. Coal Geology & Exploration,2023,51(2):104−113. DOI: 10.12363/issn.1001-1986.22.12.0913

    [9] 陈结,高靖宽,蒲源源,等. 冲击地压预测预警的机器学习方法[J]. 采矿与岩层控制工程学报,2021,3(1):53−64.

    CHEN Jie,GAO Jingkuan,PU Yuanyuan,et al. Machine learning method for predicting and warning of rockbursts[J]. Journal of Mining and Strata Control Engineering,2021,3(1):53−64.

    [10] 曹安业,刘耀琪,杨旭,等. 物理指标与数据特征融合驱动的冲击地压时序预测方法[J]. 煤炭学报,2023,48(10):3659−3673.

    CAO Anye,LIU Yaoqi,YANG Xu,et al. Physical index and data fusion-driven method for coal burst prediction in time sequence[J]. Journal of China Coal Society,2023,48(10):3659−3673.

    [11] 姚辉,尹慧超,梁满玉,等. 机器学习方法在矿井水防治理论体系研究中的应用思考[J]. 煤田地质与勘探,2024,52(5):107−117. DOI: 10.12363/issn.1001-1986.23.10.0641

    YAO Hui,YIN Huichao,LIANG Manyu,et al. Some reflections on the application of machine learning to research into the theoretical system of mine water prevention and control[J]. Coal Geology & Exploration,2024,52(5):107−117. DOI: 10.12363/issn.1001-1986.23.10.0641

    [12] 潘俊锋,冯美华,卢振龙,等. 煤矿冲击地压综合监测预警平台研究及应用[J]. 煤炭科学技术,2021,49(6):32−41.

    PAN Junfeng,FENG Meihua,LU Zhenlong,et al. Research and application of comprehensive monitoring and early warning platform for coal mine rock burst[J]. Coal Science and Technology,2021,49(6):32−41.

    [13]

    ZHAO Hongbo,CHEN Bingrui,ZHU Changxing. Decision tree model for rockburst prediction based on microseismic monitoring[J]. Advances in Civil Engineering,2021,2021:8818052.

    [14]

    LI Yongsong,ZHOU Chao. Rockburst inducement mechanism and its prediction based on microseismic monitoring[J]. Geofluids,2021,2021:4028872.

    [15] 夏永学,冯美华,李浩荡. 冲击地压地球物理监测方法研究[J]. 煤炭科学技术,2018,46(12):54–60.

    XIA Yongxue,FENG Meihua,LI Haodang. Study on rock burst geophysical monitoring method. Coal Science and Technology[J]. 2018,46(12):54–60.

    [16] 崔峰,何仕凤,来兴平,等. 基于相空间重构与深度学习的冲击地压矿井时间序列b值趋势[J]. 煤炭学报,2023,48(5):2022−2034.

    CUI Feng,HE Shifeng,LAI Xingping,et al. Trend of time sequence b value of rock burst mine based on phase space reconstruc-tion and deep learning[J]. Journal of China Coal Society,2023,48(5):2022−2034.

    [17] 李庶林,周梦婧,高真平,等. 增量循环加卸载下岩石峰值强度前声发射特性试验研究[J]. 岩石力学与工程学报,2019,38(4):724−735.

    LI Shulin,ZHOU Mengjing,GAO Zhenping,et al. Experimental study on acoustic emission characteristics before the peak strength of rocks under incrementally cyclic loading-unloading methods[J]. Chinese Journal of Rock Mechanics and Engineering,2019,38(4):724−735.

    [18] 石显鑫,蔡栓荣,冯宏,等. 利用声发射技术预测预报煤与瓦斯突出[J]. 煤田地质与勘探,1998,26(3):60−65.

    SHI Xianxin,CAI Shuanrong,FENG Hong,et al. The prediction of coal and gas outburst using the acoustic emission technique[J]. Coal Geology & Exploration,1998,26(3):60−65.

    [19] 谭云亮,张明,徐强,等. 坚硬顶板型冲击地压发生机理及监测预警研究[J]. 煤炭科学技术,2019,47(1):166−172.

    TAN Yunliang,ZHANG Ming,XU Qiang,et al. Study on occurrence mechanism and monitoring and early warning of rock burst caused by hard roof[J]. Coal Science and Technology,2019,47(1):166−172.

    [20] 谭云亮,周辉,韩宪军,等. 冲击地压声发射前兆模式初步研究[J]. 岩石力学与工程学报,2000,19(4):425−428. DOI: 10.3321/j.issn:1000-6915.2000.04.006

    TAN Yunliang,ZHOU Hui,HAN Xianjun,et al. Analysis on acoustic emission pattern for rock burst[J]. Chinese Journal of Rock Mechanics and Engineering,2000,19(4):425−428. DOI: 10.3321/j.issn:1000-6915.2000.04.006

    [21]

    LONG Guangyu,WANG Hong,HU Ke,et al. Probability prediction method for rockburst intensity based on rough set and multidimensional cloud model uncertainty reasoning[J]. Environmental Earth Sciences,2024,83(2):84. DOI: 10.1007/s12665-023-11403-2

    [22]

    LI Qingwen,XIANG Ben. Rockburst prediction on the superimposed effect of excavation accumulation energy and blasting vibration energy in deep roadway[J]. Shock and Vibration,2021,2021:6644590.

    [23] 王佳信,周宗红,李克钢,等. 一种基于R型因子分析和概率神经网络的冲击地压危险性等级评价模型[J]. 振动与冲击,2019,38(2):192−203.

    WANG Jiaxin,ZHOU Zonghong,LI Kegang,et al. Evaluation model for the risk grade of rock burst based on the R-type factor analysis and a probabilistic neural network[J]. Journal of Vibration and Shock,2019,38(2):192−203.

    [24] 缪华祥,姜福兴,宋雪娟,等. 矿山微地震活动特征的概率分析方法研究[J]. 采矿与安全工程学报,2012,29(5):685−693.

    MIAO Huaxiang,JIANG Fuxing,SONG Xuejuan,et al. Probability analysis of microseismic activity in underground mining[J]. Journal of Mining & Safety Engineering,2012,29(5):685−693.

    [25] 李建勋,于兴凯. 概率密度函数信息融合概述[J]. 航空兵器,2023,30(3):1−10. DOI: 10.12132/ISSN.1673-5048.2022.0205

    LI Jianxun,YU Xingkai. Survey on information fusion of probability density functions[J]. Aero Weaponry,2023,30(3):1−10. DOI: 10.12132/ISSN.1673-5048.2022.0205

    [26] 王笑然. 煤岩裂纹震源机制定量反演及断裂行为研究[D]. 徐州:中国矿业大学,2021:1–172.

    WANG Xiaoran. Study on the crack source mechanism from quantitative inversion and its mechanical behaviors during coal and rock fracture[D]. Xuzhou:China University of Mining and Technology,2021:1–172.

    [27] 刘加柱,高永涛,吴顺川,等. 考虑岩体性质空间变异的岩爆倾向性概率评估[J]. 工程科学学报,2024,46(1):1−10.

    LIU Jiazhu,GAO Yongtao,WU Shunchuan,et al. Probability evaluation of rockburst tendency considering the spatial variation in rock mass properties[J]. Chinese Journal of Engineering,2024,46(1):1−10.

    [28]

    RAPP T,PETERS C,DACHSBACHER C. Visual analysis of large multivariate scattered data using clustering and probabilistic summaries[J]. IEEE Transactions on Visualization and Computer Graphics,2021,27(2):1580−1590. DOI: 10.1109/TVCG.2020.3030379

    [29]

    HE Zhilin,HO C H. An improved clustering algorithm based on finite Gaussian mixture model[J]. Multimedia Tools and Applications,2019,78(17):24285−24299. DOI: 10.1007/s11042-018-6988-z

    [30]

    SAMMAKNEJAD N,ZHAO Yujia,HUANG Biao. A review of the Expectation Maximization algorithm in data-driven process identification[J]. Journal of Process Control,2019,73:123−136. DOI: 10.1016/j.jprocont.2018.12.010

    [31]

    BENABDELLAH A C,BENGHABRIT A,BOUHADDOU I. A survey of clustering algorithms for an industrial context[J]. Procedia Computer Science,2019,148:291−302. DOI: 10.1016/j.procs.2019.01.022

图(12)  /  表(7)
计量
  • 文章访问数:  101
  • HTML全文浏览量:  1
  • PDF下载量:  20
  • 被引次数: 0
出版历程
  • 收稿日期:  2024-01-14
  • 修回日期:  2024-07-11
  • 刊出日期:  2024-10-24

目录

    /

    返回文章
    返回