Methodology for identifying the damage state of sandstone using Mel-frequency cepstral coefficient of acoustic emission
-
摘要:
岩体结构破裂是严重制约矿山、地铁、隧道等地下空间工程建设及其安全运行的重要因素。实现对岩体结构破裂状态的识别是当下研究的热点与重点之一。为此,开展了不同条件的砂岩加载破坏实验,提取了加载全程的声发射梅尔倒谱系数及其波动差,研究了系数及其波动差在砂岩受载破坏全程的变化规律,分析了1号系数(一组声发射梅尔倒谱系数包括12个,1号系数指第1个声发射梅尔倒谱系数)及其波动差与砂岩破裂状态的相关性特征,基于此提出了砂岩破裂状态声发射梅尔倒谱系数判识方法,构建了判识准则并进行判识效果检验。结果表明:随载荷增加,1号系数整体上增大,系数及其离散性在破坏阶段显著增大并表现出显著的规律波动性特征;1号系数波动差具有阶段性变化特征,波动差的大小及其起伏变化可表征砂岩的破裂,波动差整体增大及突增的变化可反映砂岩非稳定变形和峰后破坏阶段的宏观破裂,波动差的突增幅度可反映砂岩破裂程度;声发射梅尔倒谱系数及其波动差对砂岩破裂表现出良好的响应特征,该特征受不同加载条件的影响较小,说明声发射梅尔倒谱系数在反映砂岩破裂上具有适用性;1号系数及其波动差与砂岩破裂状态具有较好相关性,该相关性可分为3个阶段,即1号系数及其波动差在砂岩微破裂阶段分布集中,在临近失稳破坏阶段分布范围急剧增大、整体值升高且出现高异常值,在峰后破坏阶段分布范围进一步增大、整体值更高、高异常值更多;利用1号系数的75%位点值和异常值、1号系数波动差的75%位点值和异常值构建了砂岩破裂状态判识准则,采用三分类模型混淆矩阵对判识准则的效果进行了检验,判识准确度和精准度分别为90.43%、94.45%。该成果可为其他种类煤岩的破裂状态识别提供借鉴,为煤岩失稳监测预警提供参考。
Abstract:Rock mass structure rupture is an important factor that seriously restricts the construction and safe operation of underground space engineering projects such as mines, subways and tunnels. Realizing the identification of rock mass fracture state is one of the hotspots and emphases of current research. In this study, some experiments of sandstone loading failure under different conditions were carried out, the acoustic emission Mel-frequency cepstral coefficient (MFCC) and its fluctuation difference during the whole loading process were extracted, the variation law of the coefficient and its fluctuation difference during the whole loading failure process was studied, and the correlation characteristics of coefficient No.1 (According to the calculation of acoustic emission Mel-frequency cepstral coefficients, it can be seen that a set of acoustic emission Mel-frequency cepstral coefficient includes 12, and coefficient No.1 refers to the first Mel-frequency cepstral coefficient) and its fluctuation difference with the fracture state of sandstone were analyzed. Based on this, a method to identify sandstone fracture state using the Mel-frequency cepstral of acoustic emission was proposed, and the identification criteria was constructed. The identification effect was finally verified. The results show that with loading increase, the coefficient No.1 increases as a whole, and the coefficient value and its discreteness increase significantly in the failure stage and show significant regular fluctuations. The fluctuation difference of the coefficient has the characteristics of periodic variation. The size of the fluctuation difference and its fluctuation can characterize the fracture of sandstone. The overall increase and sudden increase of the fluctuation difference can reflect the macroscopic fracture of sandstone in the unstable deformation and post-peak failure stage, and the sudden increase level of the fluctuation difference can reflect the fracture degree of sandstone. The acoustic emission Mel-frequency cepstral coefficient and its fluctuation difference show good response characteristics to sandstone fracture, which is less affected by different loading conditions, thus they have applicability in reflecting sandstone fracture. The coefficient No.1 and its fluctuation difference have a good correlation with the fracture state of sandstone. The correlation can be divided into three stages as: in the micro-fracture stage of sandstone, the coefficient No.1 and its fluctuation difference are intensively distributed; in the unstable deformation stage just prior to the peak load, the distribution range increases sharply, the overall value increases and the high abnormal value appears; in the post-peak failure stage, the distribution range further increases, the overall value is higher, and more high abnormal values appear. The identification method and criteria of sandstone fracture state were constructed by using the 75% site value and outliers of coefficient No.1 and the 75% site value and outliers of the fluctuation difference of coefficient No.1. The effect of the identification criteria was tested by the confusion matrix of the three-classification model. The accuracy and precision of identification are 90.43% and 94.45%, respectively, which indicate the identification effect is good. The results can provide a reference for the identification of the fracture state of other types of coal and rocks, and for the monitoring and early warning of coal rock instability.
-
表 1 加载方案
Table 1 Loading program
试样类型 与水平方向夹角β/( ° ) 试样编号 试样数量/个 加载方式 试样平均强度/MPa 完整粗砂岩 — DZ-1、DZ-2、DZ-3 3 单轴加载 44.75 FJ-1、FJ-2、FJ-3 3 分级加载 XH-1、XH-2、XH-3 3 循环加卸载 预制裂纹粗砂岩 30 CSP1、CSP2、CSP3 3 单轴加载 60 CSP4、CSP5、CSP6 3 90 CSP7、CSP8、CSP9 3 表 2 砂岩破裂状态判识指标及分级判识准则
Table 2 Identification indexes and criteria of sandstone damage state
MFCC-1 MFCC-1波动差 试样破裂状态 状态分类 75%位点值 异常值 75%位点值 异常值 < −28 < 0 < 19 < 60 微破裂产生阶段,试样状态较为稳定 I [−28,−18) > 0 [19, 30) > 60 临近失稳破坏阶段,试样产生宏观破裂 II ≥−18 > 0 ≥30 > 60 峰后破坏阶段,试样宏观破裂贯通并破坏 III 表 3 砂岩破裂状态效果检验三分类混淆矩阵
Table 3 Three classification confusion matrix for sandstone damage state identification effect analysis
混淆矩阵 真实状态 I II III 预测状态 I TP11 TP12 TP13 II TP21 TP22 TP23 III TP31 TP32 TP33 注:TPij指实际是j类样本,但被判识为i类样本的数量。 表 4 砂岩破裂状态混淆矩阵分类结果
Table 4 Classification results of sandstone damage state confusion matrix
混淆矩阵 真实状态 I II III 预测状态 I 305 2 8 II 17 5 6 III 2 1 30 -
[1] 韦梦菡. 岩体破裂近场低频电磁定位方法研究[D]. 北京:北京科技大学,2023:1− 2. WEI Menghan. A near-field localization method for rock fractures using generated low-frequency electromagnetic field[D]. Beijing:University of Science and Technology Beijing, 2023:1− 2.
[2] 王恩元,刘晓斐,何学秋,等. 煤岩动力灾害声电协同监测技术及预警应用[J]. 中国矿业大学学报,2018,47(5):942−948. WANG Enyuan, LIU Xiaofei, HE Xueqiu, et al. Acoustic emission and electromagnetic radiation synchronized monitoring technology and early-warning application for coal and rock dynamic disaster[J]. Journal of China University of Mining & Technology,2018,47(5):942−948.
[3] 曹安业,窦林名,白贤栖,等. 我国煤矿矿震发生机理及治理现状与难题[J]. 煤炭学报,2023,48(5):1894−1918. CAO Anye, DOU Linming, BAI Xianxi, et al. State-of-the-art occurrence mechanism and hazard control of mining tremors and their challenges in Chinese coal mines[J]. Journal of China Coal Society,2023,48(5):1894−1918.
[4] 梁正召,唐春安,黄明利,等. 岩石破裂过程中声发射模式的数值模拟[J]. 东北大学学报(自然科学版),2002,23(10):1008−1011. doi: 10.3321/j.issn:1005-3026.2002.10.024 LIANG Zhengzhao, TANG Chun’an, HUANG Mingli, et al. Numerical simulation of acoustic emission patterns during rock fracture processes[J]. Journal of Northeastern University(Natural Science),2002,23(10):1008−1011. doi: 10.3321/j.issn:1005-3026.2002.10.024
[5] 杨永杰,陈绍杰,韩国栋. 煤样压缩破坏过程的声发射试验[J]. 煤炭学报,2006,31(5):562−565. YANG Yongjie, CHEN Shaojie, HAN Guodong. Experimental on acoustic emission during compression rupture procedure of coal sample[J]. Journal of China Coal Society,2006,31(5):562−565.
[6] 李炜强,许沁舒,成功,等. 单轴压缩下砂岩微破裂演化力学行为研究[J]. 煤炭科学技术,2020,48(11):60−67. LI Weiqiang, XU Qinshu, CHENG Gong, et al. Study on mechanical behavior of sandstone micro-fracture evolution under uniaxial compression test[J]. Coal Science and Technology,2020,48(11):60−67.
[7] 董陇军,张义涵,孙道元,等. 花岗岩破裂的声发射阶段特征及裂纹不稳定扩展状态识别[J]. 岩石力学与工程学报,2022,41(1):120−131. DONG Longjun, ZHANG Yihan, SUN Daoyuan, et al. Stage characteristics of acoustic emission and identification of unstable crack state for granite fractures[J]. Chinese Journal of Rock Mechanics and Engineering,2022,41(1):120−131.
[8] 孙飞跃,郭佳奇,刘希亮,等. 真三轴单面卸荷条件下中间主应力对深埋洞室岩爆影响特征[J/OL]. 煤炭学报,1− 19 [2024-02-29].https://doi.org/10.13225/j.cnki.jccs.2023.0165. SUN Feiyue, GUO Jiaqi, LIU Xiliang, et al. Study on the influence of intermediate principal stress on rockburst in deep cavern under true triaxial condition with single face unloading[J/OL]. Journal of China Coal Society, 1− 19 [2024-02-29].https://doi.org/10.13225/j.cnki.jccs.2023.0165.
[9] WANG Yuanyuan, DENG Hucheng, DENG Yong, et al. Study on crack dynamic evolution and damage-fracture mechanism of rock with pre-existing cracks based on acoustic emission location[J]. Journal of Petroleum Science and Engineering,2021,201:108420. doi: 10.1016/j.petrol.2021.108420
[10] 武旭,王帆,席迅,等. 正交型交叉裂隙岩石强度特征与破裂机理试验研究[J]. 煤炭学报,2020,45(7):2681−2690. WU Xu, WANG Fan, XU Xun, et al. Experimental investigation on the strength characteristics and fracture mechanism of rock with orthogonally crossed cracks[J]. Journal of China Coal Society,2020,45(7):2681−2690.
[11] 赵毅鑫,姜耀东,祝捷,等. 煤岩组合体变形破坏前兆信息的试验研究[J]. 岩石力学与工程学报,2008,27(2):339−346. ZHAO Yixin, JIANG Yaodong, ZHU Jie, et al. Experiment study on precursory information of deformations of coal-rock composite samples before failure[J]. Chinese Journal of Rock Mechanics and Engineering,2008,27(2):339−346.
[12] 刘倩颖,张茹,高明忠,等. 煤卸荷过程中声发射特征及综合破坏前兆分析[J]. 四川大学学报(工程科学版),2016,48(S2):67−74. LIU Qianying, ZHANG Ru, GAO Mingzhong, et al. Acoustic emission characteristics and comprehensive failure precursors of coal under unloading conditions[J]. Journal of Sichuan University (Natural Science Edition),2016,48(S2):67−74.
[13] 冯增朝,沈永星. 基于表面位移的岩石失稳前兆识别研究[J]. 岩石力学与工程学报,2021,40(S2):3024−3032. FENG Zengchao, SHEN Yongxing. Study on precursor identification of rock instability based on surface displacement[J]. Chinese Journal of Rock Mechanics and Engineering,2021,40(S2):3024−3032.
[14] 苏晓波,纪洪广,权道路,等. 劈裂条件下岩石应变空间变异性与b值关系[J]. 煤炭学报,2020,45(S1):239−246. SU Xiaobo, JI Hongguang, QUAN Daolu, et al. Relationship between spatial variability of rock strain and b value under splitting condition[J]. Journal of China Coal Society,2020,45(S1):239−246.
[15] 赵奎,杨道学,曾鹏,等. 单轴压缩条件下花岗岩声学信号频域特征分析[J]. 岩土工程学报,2020,42(12):2189−2197. ZHAO Kui, YANG Daoxue, ZENG Peng, et al. Frequency-domain characteristics of acoustic signals of granite under uniaxial compression[J]. Chinese Journal of Geotechnical Engineering,2020,42(12):2189−2197.
[16] 龚囱,包涵,王文杰,等. 红砂岩破坏过程声发射震源演化规律及其主频特征[J]. 煤炭学报,2022,47(6):2326−2339. GONG Cong, BAO Han, WANG Wenjie, et al. Evolution law and dominant frequency characteristics of acoustic emission sources during red sandstone failure process[J]. Journal of China Coal Society,2022,47(6):2326−2339.
[17] 丛宇,冯夏庭,郑颖人,等. 不同应力路径大理岩声发射破坏前兆的试验研究[J]. 岩土工程学报,2016,38(7):1193−1201. CONG Yu, FENG Xiating, ZHENG Yingren, et al. Experimental study on acoustic emission failure precursors of marble under different stress paths[J]. Chinese Journal of Geotechnical Engineering,2016,38(7):1193−1201.
[18] WANG H L, SONG D Z, LI Z L, et al. Acoustic emission characteristics of coal failure using automatic speech recognition methodology analysis[J]. International Journal of Rock Mechanics and Mining Sciences,2020,136:104472. doi: 10.1016/j.ijrmms.2020.104472
[19] 李振雷,李娜,杨菲,等. 基于声发射特征提取和机器学习的煤破坏状态预测[J]. 工程科学学报,2023,45(1):19−30. LI Zhenlei, LI Na, YANG Fei, et al. Applying feature extraction of acoustic emission and machine learning for coal failure forecasting[J]. Chinese Journal of Engineering,2023,45(1):19−30.
[20] 李振雷,杨菲,李娜,等. 预制裂纹砂岩受载破裂声发射梅尔倒谱系数响应特征[J]. 中国矿业大学学报,2023,52(4):713−726. LI Zhenlei, YANG Fei, LI Na, et al. Response characteristics of Mel-frequency cepstral coefficient of acoustic emission to fracture of sandstone specimens with prefabricated cracks[J]. Journal of China University of Mining & Technology,2023,52(4):713−726.
[21] 李振雷,李娜,杨菲,等. 声发射梅尔倒谱系数在砂岩破裂分析的应用[J]. 煤炭学报,2023,48(2):714−729. LI Zhenlei, LI Na, YANG Fei, et al. Applying Mel-frequency cepstral coefficient of acoustic emission for analyzing fracture and failure of sandstone specimens[J]. Journal of China Coal Society,2023,48(2):714−729.
[22] 何正祥,彭平安,廖智勤. 基于梅尔倒谱系数的矿山复杂微震信号自动识别分类方法[J]. 中国安全生产科学技术,2018,14(12):41−47. HE Zhengxiang, PENG Pingan, LIAO Zhiqin. An automatic identification and classification method of complex micro seismic signals in mines based on Mel-frequency cepstral coefficients[J]. Journal of Safety Science and Technology,2018,14(12):41−47.
[23] 乔兵,吴庆林,阴玉梅. 语音识别算法的VC++实现[J]. 光机电信息,2011,28(4):50−55. doi: 10.3788/OMEI20112804.0050 QIAO Bing, WU Qinglin, YIN Yumei. Implementation of speech recognition algorithm in VC++[J]. Ome Information,2011,28(4):50−55. doi: 10.3788/OMEI20112804.0050
[24] 陈润航,黄汉明,柴慧敏. 地震和爆破事件源波形信号的卷积神经网络分类研究[J]. 地球物理学进展,2018,33(4):1331. CHEN Runhang, HUANG Hanming, CHAI Huimin. Study on the discrimination of seismic waveform signals between earthquake and explosion events by convolutional neural network[J]. Progress in Geophysics,2018,33(4):1331.
[25] 蒋磊,马六章,杨克虎,等. 基于MFCC和FD-CNN卷积神经网络的综放工作面煤矸智能识别[J]. 煤炭学报,2020,45(S2):1109−1117. JIANG Lei, MA Liuzhang, YANG Kehu, et al. Coal and gangue intelligent separation based on MFCC and FD-CNN convolutional neural network for top coal caving mining[J]. Journal of China Coal Society,2020,45(S2):1109−1117.