基于改进支持向量机的微震初至波到时自动拾取方法

李铁牛; 胡宾鑫; 李化坤; 耿文成; 郝鹏程; 纪旭波; 孙增荣; 朱峰; 张华; 阳铖权

doi:10.13272/j.issn.1671-251x.2022050081

基于改进支持向量机的微震初至波到时自动拾取方法

doi: 10.13272/j.issn.1671-251x.2022050081

1.
齐鲁工业大学(山东省科学院) 激光研究所, 山东济南　250300
2.
赤峰吉隆矿业有限责任公司,内蒙古赤峰　024328
3.
山东盛隆安全技术有限公司, 山东济南　250032
4.
山东恒邦矿业发展有限公司, 山东烟台　264199

基金项目: 济宁市重点研发计划项目（2021AQGX001）；山东省自然科学基金博士基金项目（ZR2019BEE019）；山东省自然科学基金重点项目（ZR2020KC012）；济南市“高校20条”资助项目（2020GXRC032）；济南市“新高校20条”资助项目（2021GXRC037）。

详细信息

作者简介:
李铁牛（1997—），男，山东济南人，硕士研究生，研究方向为信息处理技术，E-mail:Tieniul@163.com

通讯作者:
胡宾鑫（1979—），男，浙江景宁人，副研究员，博士，研究方向为传感器技术与智能系统，E-mail:bxhu@qlu.edu.cn

中图分类号: TD324
计量
- 文章访问数: 286
- HTML全文浏览量: 87
- PDF下载量: 24
- 被引次数: 0
出版历程
- 收稿日期: 2022-05-30
- 修回日期: 2023-03-09
- 网络出版日期: 2022-10-14

Automatic picking method of microseismic first arrival time based on improved support vector machine

1.
Laser Research Institute, Qilu University of Technology(Shandong Academy of Sciences), Jinan 250300, China
2.
Chifeng Jilong Mining Co., Ltd., Chifeng 024328, China
3.
Shandong Shenglong Safety Technology Co., Ltd., Jinan 250032, China
4.
Shandong Hengbang Mining Development Co., Ltd., Yantai 264199, China

摘要

摘要: 微震初至波到时拾取是实现微震震源高精度定位的重要前提。传统的人工拾取方法效率低，而自动拾取方法在低信噪比条件下难以准确拾取初至波到时。针对上述问题，提出了一种基于改进支持向量机（SVM）的微震初至波到时自动拾取方法。首先，对原始微震数据进行归一化处理、线性校正和适当裁剪，将微震数据的振幅、能量和相邻时刻的能量比作为特征对数据标记不同类别；然后采用粒子群优化（PSO）算法和网格搜索法优化SVM的惩罚参数和核函数参数，即先利用PSO算法对参数进行大范围的快速定位，得到初步最优解，再以该解为初始位置重新构建参数搜索区间，设置小步长的网格搜索法对参数进行精细搜寻，得到最优参数，并将该最优参数代入SVM模型进行训练，得到改进SVM模型；最后根据改进的SVM模型对微震数据进行分类识别，定义微震波第1个采样点对应的时刻为初至波到时。采用某矿井下微震监测数据进行实验，结果表明：该方法对微震初至波到时的拾取准确率达96.5%，平均拾取误差为3.8 ms，在低信噪比情况下仍可对微震初至波到时进行准确拾取，拾取精度高于自动拾取方法中常用的长短时窗能量比（STA/LTA）法。
- 微震监测 /
- 微震初至波 /
- 初至波到时 /
- 支持向量机 /
- 网格搜索法 /
- 粒子群优化算法
Abstract: The microseismic first arrival time picking is an important prerequisite for the high-precision positioning of the microseismic source. The traditional manual picking method is inefficient. The automatic picking method is difficult to pick the arrival time of the first wave accurately under the condition of low signal-to-noise ratio. In order to solve the above problems, an automatic picking method of microseismic first arrival time based on improved support vector machine (SVM) is proposed. Firstly, the method carries out normalization processing, linear correction and proper clipping on original microseismic data. The method marks different categories of the data by taking the amplitude, the energy and the energy ratio of adjacent moments of the microseismic data as features. Secondly, the method adopts a particle swarm optimization (PSO) algorithm and a grid search method to optimize the penalty parameters and the kernel function parameters of the SVM. The method carries out large-range fast positioning on the parameters by using the PSO algorithm to obtain a preliminary optimal solution. Then the method re-constructs a parameter search interval by taking the solution as an initial position, sets a small-step grid search method to carry out fine searching on the parameters to obtain the optimal parameters. The method substitutes the optimal parameters into the SVM model to train, and obtains the improved SVM model. Finally, the microseismic data are classified and identified according to the improved SVM model. The time corresponding to the first sampling point of the microseismic wave is defined as the arrival time of the first wave. The microseismic monitoring data from a mine shaft is used for the experiment. The results show that the accuracy of the method for picking the microseismic first arrival time is 96.5%, and the average picking error is 3.8 ms. Under the condition of low signal-to-noise ratio, the microseismic first arrival time can still be picked accurately. The picking precision is higher than the short term average/long term average (STA/LTA) method commonly used in automatic picking methods.
- microseismic monitoring /
- first arrival of microseism /
- the arrival time of the first wave /
- support vector machine /
- grid search method /
- particle swarm optimization algorithm

HTML全文

图 1 最优分类超平面

Figure 1. Optimal classification hyperplane

下载: 全尺寸图片幻灯片

图 2 SVM结构

Figure 2. Support vector machine structure

下载: 全尺寸图片幻灯片

图 3 基于改进SVM的微震初至波到时自动拾取流程

Figure 3. Automatic picking process of microseismic first-arrival time based on improved support vector machine

下载: 全尺寸图片幻灯片

图 4 数据预处理流程

Figure 4. Data preprocessing process

下载: 全尺寸图片幻灯片

图 5 网格搜索法参数寻优结果

Figure 5. Parameter optimization results of grid search algorithm

下载: 全尺寸图片幻灯片

图 6 微震信号加噪后初至波到时拾取结果

Figure 6. First-arrival time picking results after microseismic signal plus noise

下载: 全尺寸图片幻灯片

图 7 8通道微震初至波到时拾取结果

Figure 7. 8-channel microseismic first-arrival time picking results

下载: 全尺寸图片幻灯片

表 1 微震初至波到时统计结果

Table 1. Statistical results of microseismic first-arrival time

微震检波器序号	微震信号数量/组	人工拾取数量/组	自动拾取数量/组		拾取准确率/%		拾取误差/ms
微震检波器序号	微震信号数量/组	人工拾取数量/组	STA/ LTA法	本文方法	STA/ LTA法	本文方法	STA/ LTA法	本文方法
1	360	357	323	351	90.5	98.3	6.5	3.5
2	360	355	315	343	88.7	96.6	7.3	4.2
3	360	356	318	346	89.3	97.2	5.9	2.9
4	360	352	307	335	87.2	95.2	7.4	4.5
5	360	354	316	339	89.2	95.8	6.7	3.4
6	360	352	311	334	88.3	94.9	7.5	5.1
7	360	357	331	348	92.7	97.5	6.9	3.7
8	360	355	312	341	87.9	96.1	7.1	4.3
9	360	358	329	353	91.9	98.6	6.3	2.7
10	360	354	316	336	89.3	94.9	6.9	3.9
11	360	353	309	335	87.5	94.9	7.7	4.2
12	360	356	322	348	90.4	97.8	6.6	3.6
平均值	360	354.9	317.4	342.4	89.4	96.5	6.9	3.8

下载: 导出CSV

参考文献(22)

[1]	孙继平,程继杰. 煤矿冲击地压和煤与瓦斯突出感知报警方法研究[J]. 工矿自动化,2022,48(1):1-6. doi: 10.13272/j.issn.1671-251x.17881 SUN Jiping,CHENG Jijie. Study on the perception and alarm method of coal mine rock burst and coal and gas outburst[J]. Industry and Mine Automation,2022,48(1):1-6. doi: 10.13272/j.issn.1671-251x.17881
[2]	马天辉,唐春安,唐烈先,等. 基于微震监测技术的岩爆预测机制研究[J]. 岩石力学与工程学报,2016,35(3):470-483. MA Tianhui,TANG Chun'an,TANG Liexian,et al. Mechanism of rock burst forecasting based on micro-seismic monitoring technology[J]. Chinese Journal of Rock Mechanics and Engineering,2016,35(3):470-483.
[3]	刘强,蔡永顺,石峰,等. 微震监测技术在某金矿的应用与研究[J]. 中国矿业,2020,29(增刊1):145-148. LIU Qiang,CAI Yongshun,SHI Feng,et al. Application and study of microseismic monitoring technology in a gold mine[J]. China Mining Magazine,2020,29(S1):145-148.
[4]	WAMRIEW D,DORHJIE D B,BOGOEDOV D,et al. Microseismic monitoring and analysis using cutting-edge technology:a key enabler for reservoir characterization[J]. Remote Sensing,2022,14(14):3417-3438. doi: 10.3390/rs14143417
[5]	LIU Fei,MA Tianhui,TANG Chun'an,et al. Prediction of rockburst in tunnels at the Jinping II hydropower station using microseismic monitoring technique[J]. Tunnelling and Underground Space Technology,2018,81:480-493. doi: 10.1016/j.tust.2018.08.010
[6]	李楠,王恩元,GE Maochen. 微震监测技术及其在煤矿的应用现状与展望[J]. 煤炭学报,2017,42(增刊1):83-96. doi: 10.13225/j.cnki.jccs.2016.0852 LI Nan,WANG Enyuan,GE Maochen. Microseismic monitoring technique and its applications at coal mines:present status and future prospects[J]. Journal of China Coal Society,2017,42(S1):83-96. doi: 10.13225/j.cnki.jccs.2016.0852
[7]	GESRET A,DESASSIS N,NOBLE M,et al. Propagation of the velocity model uncertainties to the seismic event location[J]. Geophysical Journal International,2014(1):52-66.
[8]	宋广东. 基于光纤传感的微震信号采集和识别与震源定位研究[D]. 北京: 中国矿业大学（北京）, 2019. SONG Guangdong. Research on acquisition and recognition of microseismic signal and source location based on optical fiber sensing[D]. Beijing: China University of Mining and Technology-Beijing, 2019.
[9]	STEFANO R D,ALDERSONS F,KISSLING E,et al. Automatic seismic phase picking and consistent observation error assessment:application to the Italian seismicity[J]. Geophysical Journal International,2006,165(1):121-134. doi: 10.1111/j.1365-246X.2005.02799.x
[10]	贾瑞生,谭云亮,孙红梅,等. 低信噪比微震P波震相初至自动拾取方法[J]. 煤炭学报,2015,40(8):1845-1852. doi: 10.13225/j.cnki.jccs.2014.1122 JIA Ruisheng,TAN Yunliang,SUN Hongmei,et al. Method of automatic detection on micro-seismic P-arrival time under low signal-to-noise ratio[J]. Journal of China Coal Society,2015,40(8):1845-1852. doi: 10.13225/j.cnki.jccs.2014.1122
[11]	高新成, 杜功鑫, 王莉利, 等. 深度学习在地震初至拾取中的应用综述[J]. 计算机技术与发展, 2022, 32（8）: 1-6. GAO Xincheng, DU Gongxin, WANG Lili, et al. Application of deep learning in earthquake first break picking[J]. Computer Technology and Development, 2022, 32（8）: 1-6.
[12]	LEE M,BYUN J,KIM D,et al. Improved modified energy ratio method using a multi-window approach for accurate arrival picking[J]. Journal of Applied Geophysics,2017,139:117-130. doi: 10.1016/j.jappgeo.2017.02.019
[13]	MARTON S,LUDTKE S,BARTELT C. Explanations for neural networks by neural networks[J]. Applied Sciences,2022,12(3):980-993. doi: 10.3390/app12030980
[14]	刘佳楠,武杰. 基于全卷积神经网络的地震初至波拾取[J]. 信息技术与网络安全,2018,37(11):58-63. LIU Jianan,WU Jie. Seismic first arrival picking based on full convolutional networks[J]. Information Technology and Network Security,2018,37(11):58-63.
[15]	李洪丽,张晗. 基于长短时均值比法、偏振法和AIC法三种微地震初至拾取方法的对比[J]. 世界地质,2020,39(3):649-655,663. doi: 10.3969/j.issn.1004-5589.2020.03.014 LI Hongli,ZHANG Han. Comparison of three microseismic first arrival picking methods based on ratio of short-term average and long-term average,polarization method and AIC method[J]. Global Geology,2020,39(3):649-655,663. doi: 10.3969/j.issn.1004-5589.2020.03.014
[16]	王洪超. 基于Fast−AIC算法的微地震事件初至拾取及自动识别技术研究[D]. 长春: 吉林大学, 2017. WANG Hongchao. Research on automatic microseismic event detection and arrival picking based on Fast-AIC algorithm[D]. Changchun: Jilin University, 2017.
[17]	高煜,胡宾鑫,朱峰,等. 微震初至波到时自动拾取研究[J]. 工矿自动化,2020,46(12):106-110. doi: 10.13272/j.issn.1671-251x.17564 GAO Yu,HU Binxin,ZHU Feng,et al. Research on automatic picking of microseismic first arrival[J]. Industry and Mine Automation,2020,46(12):106-110. doi: 10.13272/j.issn.1671-251x.17564
[18]	李亦滔. 基于支持向量机的改进分类算法[J]. 计算机系统应用,2019,28(10):145-151. doi: 10.15888/j.cnki.csa.007080 LI Yitao. Improved classification algorithm based on support vector machine[J]. Computer System & Applications,2019,28(10):145-151. doi: 10.15888/j.cnki.csa.007080
[19]	丁世飞,齐丙娟,谭红艳. 支持向量机理论与算法研究综述[J]. 电子科技大学学报,2011,40(1):2-10. DING Shifei,QI Bingjuan,TAN Hongyan. An overview on theory and algorithm of support vector machines[J]. Journal of University of Electronic Science and Technology of China,2011,40(1):2-10.
[20]	MA Qian, SUN Cong, CUI Baojiang, et al. A novel model for anomaly detection in network traffic based on kernel support vector machine[J]. Computers & Security, 2021, 104. DOI: 10.1016/J.COSE.2021.102215.
[21]	LYU Zhiming,ZHAO Jun,WANG Wei,et al. A multiple surrogates based PSO algorithm[J]. Artificial Intelligence Review,2019,52(4):2169-2190. doi: 10.1007/s10462-017-9601-3
[22]	SUN Yuting,DING Shifei,ZHANG Zichen,et al. An improved grid search algorithm to optimize SVR for prediction[J]. Soft Computing,2021(10):5633-5644.