煤岩单轴压缩破坏声发射轻量化三维卷积预测模型研究

doi:10.13722/j.cnki.jrme.2021.1217

Abstract
Figure/Table
References (0)
Related Citation (15)

Download: PDF (1695 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract The precursor of acoustic emission(AE) can reveal the internal destructive rules of coal. Therefore，the discrimination model based on AE precursor has been a hot topic on the monitoring and prediction of coal failure. Based on DenseNet architecture combining with Group Convolution(GC) and Squeeze-and-Excitation module(SE) in attention mechanism，a lightweight three-dimensional(3D) convolution prediction model was proposed to integrate spatiotemporal information of AE signals. The coal samples from the No.3－1 coal seam of Hongqinghe mine，with high outburst-proneness，were used in the tests. AE signals were collected during the uniaxial compression of samples in different loading rates. Moreover，AE signals were preprocessed to generate spatial-temporal image sequences which were later used as model input to predict the destruction level of coal samples. Then，transfer learning was employed to predict the remaining failure time of coal samples. The results show that： in the validation samples for predicting the destruction level，all the networks(DenseNet，DenseNet+GC，DenseNet+SE and DenseNet+GC+SE) can obtain more than 99.08% prediction accuracy. The recall rate of high-risk samples prediction is higher than 99.50%，which indicates that 3D convolution can effectively capture spatial-temporal information of AE. The prediction probability of the DenseNet+GC+SE network is exhibited as unitary distribution，indicating the model can distinguish different destruction levels. Group Convolution and SE module can retain model accuracy while reduce the structure and time complexity，which improve DenseNet+GC+SE network efficiency greatly. The R2 between the predicted value and the true value of the remaining failure time is 99.85%，which further proves that DenseNet+GC+SE transfer model can effectively predict coal failure based on AE signals. The diversity of AE features is represented by GC，while the importance of AE features is evaluated by SE module.

Key words： mining engineering coal uniaxial compression acoustic emission failure prediction lightweight 3D convolution

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	ZHAO Yixin1
	2
	QIAO Haiqing1
	2
	XIE Ronghuan1
	2
	GUO Jihong1
	2

Cite this article:

ZHAO Yixin1,2,QIAO Haiqing1, et al. Lightweight 3D convolution model for failure prediction of coal under uniaxial compression based on acoustic emission[J]. , 2022, 41(8): 1567-1580.

URL:

https://rockmech.whrsm.ac.cn/EN/10.13722/j.cnki.jrme.2021.1217 OR https://rockmech.whrsm.ac.cn/EN/Y2022/V41/I8/1567

[1] 姜耀东，赵毅鑫. 我国煤矿冲击地压的研究现状：机制、预警与控制[J]. 岩石力学与工程学报，2015，34(11)：2 188–2 204.(JIANG Yaodong，ZHAO Yixin. State of the art：investigation on mechanism，forecast and control of coal bumps in China[J]. Chinese Journal of Rock Mechanics and Engineering，2015，34(11)：2 188–2 204.(in Chinese)) [2] 刘超. 含瓦斯煤岩破裂过程微震监测与分析[M]. 徐州：中国矿业大学出版社，2017：14–16.(LIU Chao. Microseismic monitoring and its analysis for failure process of gas-saturated coal[M]. Xuzhou：China University of Mining and Technology Press，2017：14–16.(in Chinese)) [3] ZHANG W Q，SHI Z J，WANG Z Q，et al. Identifying critical failure information of thermal damaged sandstone through acoustic emission signal[J]. Journal of Geophysics and Engineering，2021，18(4)：558–566. [4] ZHENG Q Q，XU Y，HU H，et al. Quantitative damage，fracture mechanism and velocity structure tomography of sandstone under uniaxial load based on acoustic emission monitoring technology[J]. Construction and Building Materials，2020，272：121911. [5] ZHANG Z H，DENG J H，ZHU J B，et al. An experimental investigation of the failure mechanisms of jointed and intact marble under compression based on quantitative analysis of acoustic emission waveforms[J]. Rock Mechanics and Rock Engineering，2018，51(7)：2 299–2 307. [6] 张茹，谢和平，刘建锋，等. 单轴多级加载岩石破坏声发射特性试验研究[J]. 岩石力学与工程学报，2006，25(12)：2 584–2 588. (ZHANG Ru，XIE Heping，LIU Jianfeng，et al. Experimental study on acoustic emission characteristics of rock failure under uniaxial multilevel loadings[J]. Chinese Journal of Rock Mechanics and Engineering，2006，25(12)：2 584–2 588.(in Chinese)) [7] 李庶林，尹贤刚，王泳嘉，等. 单轴受压岩石破坏全过程声发射特征研究[J]. 岩石力学与工程学报，2004，23(15)：2 499–2 503.(LI Shulin，YIN Xiangang，WANG Yongjia，et al. Studies on acoustic emission characteristics of uniaxial compressive rock failure[J]. Chinese Journal of Rock Mechanics and Engineering，2004，23(15)：2 499–2 503.(in Chinese)) [8] 李杰，邱黎明，殷山，等. 煤岩膨胀破裂应变及声发射特征试验研究[J]. 工矿自动化，2021，47(2)：63–69.(LI Jie，QIU Liming，YIN Shan，et al. Experimental study on characteristics of strain and acoustic emission in the process of coal rock expansion and fracture[J]. Industry and Mine Automation，2021，47(2)：63–69.(in Chinese)) [9] TROMBIK M，ZUBEREK W. Microseismic research in polish coal mine[C]// Proceedings of the First Conference on Acoustic Emission/ Microseismic Activity in Geological Structures and Materials. [S. l. ]：Trans Tech Publications，1977：169–194. [10] MCKAVANAGH B M，ENEVER J R. Developing a microseismic outburst warning system[C]// Proceedings of the Second Conference on Acoustic Emission/Microseismic Activity in Geological Structures and Materials. [S. l. ]：Trans Tech Publications，1980：211–225. [11] 吕进国，潘立. 微震预警冲击地压的时间序列方法[J]. 煤炭学报，2010，35(12)：2 002–2 005.(LV Jinguo，PAN Li. Microseismic predicting coal bump by time series method[J]. Journal of China Coal Society，2010，35(12)：2 002–2 005.(in Chinese)) [12] 杨增福，杨胜利，杨文强. 煤岩单轴压缩条件下声发射与破坏特征差异性研究[J]. 煤炭工程，2021，53(4)：136–140.(YANG Zengfu，YANG Shengli，YANG Wenqiang. Difference between acoustic emission and failure characteristics of coal rock under uniaxial compression[J]. Coal Engineering，2021，53(4)：136–140.(in Chinese)) [13] 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 and Exploration，1998，26(3)：60–65.(in Chinese)) [14] 夏永学，蓝航，魏向志. 基于微震和地音监测的冲击危险性综合评价技术研究[J]. 煤炭学报，2011，36(增2)：358–364.(XIA Yongxue，LAN Hang，WEI Xiangzhi. Study of comprehensive evaluation technology for rock burst hazard based on microseismic and underground sound monitoring[J]. Journal of China Coal Society，2011，36(Supp.2)：358–364.(in Chinese)) [15] 李元辉，刘建坡，赵兴东，等. 岩石破裂过程中的声发射b值及分形特征研究[J]. 岩土力学，2009，30(9)：2 559–2 563.(LI Yuanhui，LIU Jianpo，ZHAO Xingdong，et al. Study on b-value and fractal dimension of acoustic emission during rock failure process[J]. Rock and Soil Mechanics，2009，30(9)：2 559–2 563.(in Chinese)) [16] SUN H，LIU X L，ZHU J B. Correlational fractal characterisation of stress and acoustic emission during coal and rock failure under multilevel dynamic loading[J]. International Journal of Rock Mechanics and Mining Sciences，2019，117：1–10. [17] 高文根，段会强，杨永新. 周期荷载作用下煤岩声发射特征的颗粒流模拟[J]. 应用力学学报，2021，38(1)：262–268.(GAO Wengen，DUAN Huiqiang，YANG Yongxin. Particle flow simulation of acoustic emission characteristics of coal sample subjected to cyclic loading[J]. Chinese Journal of Applied Mechanics，2021，38(1)：262–268.(in Chinese)) [18] 张志博，李树杰，王恩元，等. 基于声发射事件时–空维度聚类分析的煤体损伤演化特征研究[J]. 岩石力学与工程学报，2020，39(增2)：3 338–3 347.(ZHANG Zhibo，LI Shujie，WANG Enyuan，et al. Research on the damage evolution characteristics of coal based on cluster analysis of temporal-spatial dimension of acoustic emission events[J]. Chinese Journal of Rock Mechanics and Engineering，2020，39(Supp.2)：3 338–3 347.(in Chinese)) [19] 李建功. 深部矿井应力主导型煤岩瓦斯动力灾害声发射监测预警方法[J]. 山东科技大学学报：自然科学版，2020，39(4)：20–27.(LI Jiangong. Acoustic emission monitoring and early warning method for stress-dominated coal-gas dynamic disasters in deep mines[J]. Journal of Shandong University of Science and Technology：Natural Science，2020，39(4)：20–27.(in Chinese)) [20] WANG C L，CHEN Z，LIAO Z F，et al. Experimental investigation on predicting precursory changes in entropy for dominant frequency of rockburst[J]. Journal of Central South University，2020，27(10)：2 834–2 848. [21] 张凯. 基于神经网络分析的煤柱型冲击地压多参量综合预警研究[硕士学位论文][D]. 青岛：山东科技大学，2018.(ZHANG Kai. Research on multi parameter comprehensive warning of coal pillar rockburst based on neural network analysis[M. S. Thesis][D]. Qingdao：Shandong University of Science and Technology，2018.(in Chinese)) [22] DI Y Y，WANG E Y，LI Z H，et al. Method for EMR and AE interference signal identification in coal rock mining based on recurrent neural networks[J]. Earth Science Informatics，2021，14(3)：1 521–1 536. [23] TRAN D，BOURDEV L，FERGUS R，et al. Learning spatiotemporal features with 3d convolutional networks[C]// Proceedings of the IEEE International Conference on Computer Vision. Santiago，Chile：IEEE，2015：4 489–4 497. [24] QIU Z F，YAO T，MEI T. Learning spatio-temporal representation with pseudo-3d residual networks[C]// Proceedings of the IEEE International Conference on Computer Vision. Venice，Italy：IEEE，2017：5 533–5 541. [25] SAINATH T N，VINYALS O，SENIOR A，et al. Convolutional，long short-term memory，fully connected deep neural networks[C]// 2015 IEEE International Conference on Acoustics，speech and signal processing. New Orleans，Los Angeles，USA：IEEE，2015：4 580–4 584. [26] HE K M，ZHANG X Y，REN S P，et al. Deep residual learning for image recognition[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas，USA：IEEE，2016：770–778. [27] HUANG G，LIU Z，LAURENS V，et al. Densely connected convolutional networks[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii，USA：IEEE，2017：4 700–4 708. [28] KRIZHEVSKY A，SUTSKEVER I，HINTON G E. Imagenet classification with deep convolutional neural networks[J]. Communications of the ACM，2017，60(6)：84–90. [29] XIE S N，GIRSHICK R，DOLLáR P，et al. Aggregated residual transformations for deep neural networks[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii，USA：IEEE，2017：1 492–1 500. [30] HU J，SHEN L，SUN G，et al. Squeeze-and-excitation networks[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake，USA：IEEE，2018：7 132–7 141. [31] IOFFE S，SZEGEDY C. Batch normalization：accelerating deep network training by reducing internal covariate shift[C]// International Conference on Machine Learning，France：PMLR，2015，37：448–456. [32] BOTTOU L. Stochastic gradient descent tricks[M]. Heidelberg，Germany：Springer Berlin Heidelberg，2012：421–436. [33] 刘密歌. 采样定理研究[J]. 西安文理学院学报：自然科学版，2019，22(5)：64–68.(LIU Mige. Research on sampling theorem[J]. Journal of Xian University：Natural Science，2019，22(5)：64–68.(in Chinese)) [34] LEI X，NISHIZAWA O，KUSUNOSE K，et al. Fractal structure of the hypocenter distributions and focal mechanism solutions of acoustic emission in two granites of different grain sizes[J]. Earth Planets and Space，2009，40(6)：617–634. [35] XU Z Q，ZHANG Y Y，LUO T，et al. Frequency principle：Fourier analysis sheds light on deep neural networks[J]. Communications in Computational Physics，2020，28(5)：1 746–1 767. [36] 刘斌. 动静载荷下煤岩冲击失稳机理及多参量前兆特征研究[博士学位论文][D]. 北京：中国矿业大学，2021.(LIU Bin. Mechanism of rock burst and multi-parameter precursory characteristics under dynamic and static loads[Ph. D. Thesis][D]. Beijing：China University of Mining and Technology(Beijing)，2021.(in Chinese)) [37] LIU X L，LIU Z，LI X B，et al. Experimental study on the effect of strain rate on rock acoustic emission characteristics[J]. International Journal of Rock Mechanics and Mining Sciences，2020，133：104420. [38] 王峰. 基于深度学习的地震数据去噪和重建方法的研究[博士学位论文][D]. 浙江：浙江大学，2021.(WANG Feng. Research on seismic data denoising and reconstruction using deep learning[Ph. D. Thesis][D]. Zhejiang：Zhejiang University，2021.(in Chinese)) [39] HORNIK K，STINCHCOMBE M，WHITE H. Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks[J]. Neural Networks，1990，3(5)：551–560. [40] NEAL R M. Markov chain sampling methods for dirichlet process mixture models[J]. Journal of Computational and Graphical Statistics，2000，9(2)：249–265. [41] ELGMATI E A，GREDNI N B. Quartile method estimation of two-parameter exponential distribution data with outliers[J]. International Journal of Statistics and Probability，2016，5(5)：12–15. [42] 宗春梅，张月琴，石丁. PyTorch下基于CNN的手写数字识别及应用研究[J]. 计算机与数字工程，2021，49(6)：1 107–1 112.(ZONG Chunmei，ZHANG Yueqin，SHI Ding. Research on handwritten number recognition and application based on CNN under PyTorch[J]. Computer and Digital Engineering，2021，49(6)：1 107–1 112.(in Chinese)) [43] HUANG J C，QU L，JIA R F，et al. O2U-Net：A simple noisy label detection approach for deep neural networks[C]// Proceedings of the IEEE International Conference on Computer Vision. Seoul，South Korea：IEEE，2019：3 326–3 334. [44] KINGMA D P，BA J. Adam：A method for stochastic optimization[J]. Eprint Arxiv，2015：1412.6980. [45] HOWARD A G，ZHU M L，CHEN B，et al. MobileNets：efficient convolutional neural networks for mobile vision applications[J]. Eprint Arxiv，2017：1704.04861. [46] ZHANG X Y，ZHOU X Y，LIN M X，et al. ShuffleNet：An extremely efficient convolutional neural network for mobile devices[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake，USA：IEEE，2018：6 848–6 856. [47] ZAGORUYKO S，KOMODAKIS N. Paying more attention to attention：Improving the performance of convolutional neural networks via attention transfer[J]. Eprint Arxiv，2016：1612.03928.