基于频谱分析和卷积神经网络的岩石声发射信号定位研究

doi:10.13722/j.cnki.jrme.2021.0836

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1439 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要众所周知，在声发射测试中，如何准确定位源位置意义重大。传统的声发射定位方法存在波速模型和到时拾取不准等问题，导致其定位精度不高。因此提出一种将频谱分析与卷积神经网络相结合，无需波速模型与到时拾取的声发射定位方法。具体而言，基于主动源声发射试验收集的声发射全波形信号，首先通过小波分析得到正方体花岗岩试样各面声发射信号的频谱分布情况，根据声发射信号的频谱差异性对声发射信号进行面源定位，将复杂的三维空间定位转化为二维平面定位；继而设计一个卷积神经网络，对各面断铅点的声发射信号进行短时傅里叶变换，将得到的同时包含时域与频域信息的信号频谱图作为卷积神经网络的输入特征，各断铅点的二维空间坐标作为输出特征，进行训练、测试和验证，对各面断铅点的声发射源进行二维定位。结果表明，布设传感器的XOZ－面平均定位误差为0.5 cm，试样两侧面YOZ+，YOZ－的平均定位误差为0.7 cm，对立面XOZ+的定位误差为1.0 cm。综上所述，研究有效提升了声发射定位精度，且规避了传统定位方法存在的不足，为岩石声发射定位提供一种新思路。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	陈结1
	2
	陈紫阳1
	2
	蒲源源1
	2

关键词 ：岩石力学, 声发射, 震源定位, 卷积神经网络, 频谱分析

Abstract：As we all known，how to accurately locate the source position is of great significance in acoustic emission testing. The traditional AE localization method has some problems，such as wave velocity model and inaccurate on arrival-time picking，which brings a low localization accuracy. Therefore，a new localization method that combining spectrum analysis and convolutional neural network was developed，which don?t need the wave velocity model and the arrival-time picking for acoustic emission localization of rock. To be more specific，based on the acoustic emission full waveform signals collected by using active source acoustic emission test，we got spectral distribution of acoustic emission signals on each surface of cuboid granite sample using wavelet analysis method firstly. Then surface source positioning of acoustic emission signals was carried out，according to the spectral difference of acoustic emission signals，which cleverly transformed and the complex three-dimensional spatial positioning into two-dimensional plane positioning. At the same time，a convolutional neural network designed to transform the acoustic emission signals of the broken lead points on each surface using the short time Fourier transform. Finally，we taken the contains both time domain and frequency domain information of the signal spectrum characteristics as the convolution of the neural network input，and the two-dimensional space coordinates of the break point as the output features to train，test and verified the two-dimensional localization results of acoustic emission sources of lead points on each surface progressively. The results show that the average location errors of surface XOZ－(which attaches four transducers)，YOZ+，YOZ－，XOZ+ are 0.5 cm，0.7 cm，0.7 and 1.0 cm，respectively. To sum up，this study significantly improves the AE localization accuracy and avoids the shortcomings of traditional localization methods，which provides a new idea for rock AE localization.

Key words： rock mechanics acoustic emission source localization convolutional neural networks spectral analysis

引用本文:

陈结1，2，陈紫阳1，2，蒲源源1，2. 基于频谱分析和卷积神经网络的岩石声发射信号定位研究[J]. 岩石力学与工程学报, 2022, 41(S2): 3271-3281.
CHEN Jie1，2，CHEN Ziyang1，2，PU Yuanyuan1，2. Acoustic emission source localization in rocks based on spectral analysis and convolutional neural network. , 2022, 41(S2): 3271-3281.

链接本文:

https://rockmech.whrsm.ac.cn/CN/10.13722/j.cnki.jrme.2021.0836 或 https://rockmech.whrsm.ac.cn/CN/Y2022/V41/IS2/3271

[1]	陈浮，于昊辰，卞正富，等. 碳中和愿景下煤炭行业发展的危机与应对[J]. 煤炭学报，2021，46(6)：1 808–1 820.(CHEN Fu，YU Haochen，BIAN Zhengfu，et al. How to handles the crisis of coal industry in China under the vision of carbon neutrality[J]. Journal of China Coal Society，2021，46(6)：1 808–1 820.(in Chinese))
[2]	杨军，闵铁军，刘斌慧，等. 深部开采灾害及防治研究进展[J]. 科学技术与工程，2020，20(36)：14 767–14 776.(YANG Jun，MIN Tiejun，LIU Binghui，et al. Research progress on disasters and prevention in deeping mining[J]. Science Technology and Engineering，2020，20(36)：14 767–14 776.(in Chinese))
[3]	高明忠，王明耀，谢晶，等. 深部煤岩原位扰动力学行为研究[J]. 煤炭学报，2020，45(8)：2 691–2 703.(GAO Mingzhong，WANG Mingyao，XIE Jing，et al. In-situ disturbed mechanical behavior of deep coal rock[J]. Journal of China Coal Society，2020，45(8)：2 691– 2 703.(in Chinese))
[4]	潘一山，代连朋，李国臻，等. 煤矿冲击地压与冒顶复合灾害研究[J]. 煤炭学报，2021，46(1)：112–122.(PAN Yishan，DAI Lianpeng，LI Guozhen，et al. Study on compound disaster of rock burst and roof falling in coal mines[J]. Journal of China Coal Society，2021，46(1)：112–122.(in Chinese))
[5]	FENG X T，LIU J P，CHEN B R，et al. Monitoring，warning and control of rockburst in deep metal mines[J]. Engineering，2017，3(4)：538–545.
[6]	刘培洵，陈顺云，郭彦双，等. 声发射矩张量反演[J]. 地球物理学报，2014，57(3)：858–866.(LIU Peixun，CHEN Shunyun，GUO Yanshuang，et al. Moment tensor inversion of acoustic emission[J]. Chinese Journal of Geophysics，2014，57(3)：858–866.(in Chinese))
[7]	MA J，WU S，ZHANG X，et al. Modeling acoustic emission in the Brazilian test using moment tensor inversion[J]. Computers and Geotechnics，2020，123：103567.
[8]	ZHAO Q，GLASER S D. Relocating acoustic emission in rocks with unknown velocity structure with machine learning[J]. Rock Mechanics and Rock Engineering，2020，53(23)：2 053–2 061.
[9]	XU S，LIU J P，XU S D，et al. Experimental studies on pillar failure characteristics based on acoustic emission location technique[J]. Transactions of Nonferrous Metals Society of China，2012，22(11)：2 792–2 798.
[10]	INGLADA V. Die berechnung der herdkoordinaten eines nahbebens aus den eintrittszeiten der in einigen benachbarten stationen aufgezeichneten P-oder S-wellen[J]. Gerlands Beitrage zur Geophysik，1928，19：73–98.
[11]	LEIGHTON F W，BLAKE W. Rock noise source location techniques[R]. Washington：US Bureau of Mines，1970.
[12]	LEIGHTON F W，DUVALL W I. A least squares method for improving rock noise source location techniques[R]. Washington：US Bureau of Mines，1972.
[13]	NELDER J A，MEAD R. A simplex method for function minimization[J]. The Computer Journal，1965，7(4)：308–312.
[14]	刘培洵，刘力强，黄元敏，等. 声发射定位的稳健算法[J]. 岩石力学与工程学报，2009，28(增1)：2 760–2 764.(LIU Peixun，LIU Liqiang，HUANG Yuanmin，et al. Robust arithmetic for acoustic emission location[J]. Chinese Journal of Rock Mechanics and Engineering，2009，28(Supp.1)：2 760–2 764.(in Chinese))
[15]	刘建坡，王洪勇，杨宇江，等. 不同岩石声发射定位算法及其实验研究[J]. 东北大学学报：自然科学版，2009，30(8)：1 193–1 196. (LIU Jianpo，WANG Hongyong，YANG Yujiang，et al. Experimental Study on different rock locating algorithms with acoustic emission[J]. Journal of Northeastern University：Natural Science，2009，30(8)：1 193–1 196.(in Chinese))
[16]	LI Q Y，DONG L J，LI X B，et al. Effects of sonic speed on location accuracy of acoustic emission source in rocks[J]. Transactions of Nonferrous Metals Society of China，2011，21(12)：2 719–2 726.
[17]	TOBIAS A. Acoustic-emission source location in two dimensions by an array of three sensors[J]. Non-destructive Testing，1976，9(1)：9–12.
[18]	YIN S，CUI Z，KUNDU T. Acoustic source localization in anisotropic plates with“Z”shaped sensor clusters[J]. Ultrasonics，2018，84： 34–37.
[19]	吴顺川，张光，张诗淮，等. 二维非测速条件下声发射震源定位方法试验研究[J]. 岩石力学与工程学报，2019，38(1)：28–39.(WU Shunchuan，ZHANG Guang，ZHANG Shihuai，et al. Experimental research on two-dimensional acoustic emission source locating without knowing the velocity profile[J]. Chinese Journal of Rock Mechanics and Engineering，2019，38(1)：28–39.(in Chinese))
[20]	杨道学，赵奎，曾鹏，等. 基于粒子群优化算法的未知波速声发射定位数值模拟[J]. 岩土力学，2019，40(增1)：494–502.(YANG Daoxue，ZHAO Kui，ZENG Peng，et al. Numerical simulation of unknown wave velocity acoustic emission localization based on particle swarm optimization algorithm[J]. Rock and Soil Mechanics，2019，40(Supp.1)：494–502.(in Chinese))
[21]	刘增华，彭秋玲，李欣，等. 基于时间差映射方法的钢板声发射源定位[J]. 应用基础与工程科学学报，2020，28(2)：475–485.(LIU Zenghua，PENG Qiuling，LI Xin，et al. Acoustic emission source localization in steel plate based on time difference mapping method[J]. Journal of Basic Science and Engineering，2020，28(2)：475–485(in Chinese))
[22]	刘增华，彭秋玲，何存富，等. 复合材料板声发射源定位的时间差映射方法[J]. 声学学报，2020，45(3)：385–393.(LIU Zenghua，PENG Qiuling，HE Cunfu，et al. Time difference mapping method for acoustic emission source location of composite plates[J]. Acta Acustica，2020，45(3)：385–393.(in Chinese))
[23]	DONG L，HU Q，TONG X，et al. Velocity-free MS/AE source location method for three-dimensional hole-containing structures[J]. Engineering，2020，6(7)：827–834，936–944.