Article(id=1322506435397800188, tenantId=1146029695717560320, journalId=1281212831689347082, issueId=1322506335908901129, articleNumber=null, orderNo=null, doi=10.14075/j.jgg.2024.09.433, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1726675200000, receivedDateStr=2024-09-19, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1793239705180, onlineDateStr=2026-10-29, pubDate=1760457600000, pubDateStr=2025-10-15, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793239705180, onlineIssueDateStr=2026-10-29, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793239705180, creator=13701087609, updateTime=1793239705180, updator=13701087609, issue=Issue{id=1322506335908901129, tenantId=1146029695717560320, journalId=1281212831689347082, year='2025', volume='45', issue='10', pageStart='991', pageEnd='1100', issueExtLink='null', onlineDate='null', pubDate='1760457600000', pubDateStr='2025-10-15', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1793239681460, creator='13701087609', updateTime=1793244369709, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1322525999896576487, tenantId=1146029695717560320, journalId=1281212831689347082, issueId=1322506335908901129, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1322525999896576488, tenantId=1146029695717560320, journalId=1281212831689347082, issueId=1322506335908901129, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=1093, endPage=1100, ext={EN=ArticleExt(id=1322506436215689469, articleId=1322506435397800188, tenantId=1146029695717560320, journalId=1281212831689347082, language=EN, title=Classification of Mining Seismic and Blasting Signals Based on Machine Learning, columnId=null, journalTitle=Journal of Geodesy and Geodynamics, columnName=null, runingTitle=null, highlight=null, articleAbstract=

This study focuses on the classification problem of mining seismic and blasting signals in a mine in Gansu province. Common unsupervised classification methods such as support vector machine, K-means clustering, and principal component analysis were analyzed. These methods face significant challenges in terms of insufficient feature selection, low classification accuracy, and imbalanced samples. To attempt to address these issues, this paper employs a lightweight collaborative learning method(LCL-SSS) that combines MiniRocket feature extraction with improved K-means clustering, aiming to enhance the accuracy and efficiency of classification. Through time-frequency analysis, it was found that the initial P-wave frequency of blasting events is mainly concentrated between 80 to 200 Hz, while the P-wave frequency of mining seismic events is distributed between 20 to 120 Hz. After 30 training experiments, the classification accuracy of the LCL-SSS method reached 95.07%, effectively capturing key features in mining seismic waveforms.

, authors=Xiaonan LIANG1, Jianjun WANG1, Xinxin YIN2, *, authorsList=Xiaonan LIANG, Jianjun WANG, Xinxin YIN, authorCompany=null, correspAuthors=Xinxin YIN, authorNote=

LIANG Xiaonan, postgraduate, majors in seismology, E-mail:

, correspAuthorsNote=null, copyrightStatement=All rights reserved. Unauthorized reproduction is prohibited., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1322506439709544713, articleId=1322506435397800188, tenantId=1146029695717560320, journalId=1281212831689347082, language=CN, title=基于机器学习的矿震与爆破信号分类, columnId=1322506256904994864, journalTitle=大地测量与地球动力学, columnName=观测技术, runingTitle=null, highlight=null, articleAbstract=

针对甘肃某矿矿震与爆破信号的分类问题,分析了支持向量机、K-means聚类、主成分分析等常用无监督分类方法在特征选择不足、分类精度较低和样本不平衡等方面存在的显著挑战。为尝试解决这些问题,本文使用一种轻量级协同学习方法(LCL-SSS),该方法结合了MiniRocket特征提取与改进的K-means聚类,旨在提升分类的准确性与效率。通过时频分析发现,爆破事件的P波初动频率主要集中在80~200 Hz,而矿震事件的P波频率则分布在20~120 Hz。经过30次训练实验,LCL-SSS方法的分类准确率达到了95.07%,有效捕捉到矿震波形中的关键特征。

, authors=梁潇南1, 王建军1, 尹欣欣2, *, authorsList=梁潇南, 王建军, 尹欣欣, authorCompany=null, correspAuthors=尹欣欣, authorNote=

梁潇南,硕士生,主要研究方向为地震学,E-mail:

, correspAuthorsNote=

尹欣欣,博士生,高级工程师,主要研究方向为地震台网监测和诱发地震,E-mail:

YIN Xinxin, PhD candidate, senior engineer, majors in seismic network monitoring and induced earthquakes, E-mail:

, copyrightStatement=版权所有,未经授权,不得转载。, copyrightOwner=大地测量与地球动力学编辑部, extLink=null, articleAbsUrl=null, sourceXml=Gbmv4IruKIus+jOv25mTJw==, magXml=kMT49ANWvH4be1IYZc013g==, pdfUrl=null, pdf=mWY5aII9irlc+GLLs70wlw==, pdfFileSize=9041272, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=A8Frni7wOe/uQawurlj0ZA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=lbm4F8BOTE9w1z8tVxC9Uw==, mapNumber=null, fund=null)}, authors=[Author(id=1322506440116392209, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liangxiaonan22@mails.ucas.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322506440221249811, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, authorId=1322506440116392209, language=EN, stringName=Xiaonan LIANG, firstName=Xiaonan, middleName=null, lastName=LIANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Lanzhou Institute of Seismology, CEA, 450 West-Donggang Road, Lanzhou 730000, China, bio={"content":"

LIANG Xiaonan, postgraduate, majors in seismology, E-mail:

"}, bioImg=null, bioContent=

LIANG Xiaonan, postgraduate, majors in seismology, E-mail:

, aboutCorrespAuthor=null), CN=AuthorExt(id=1322506440330301716, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, authorId=1322506440116392209, language=CN, stringName=梁潇南, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中国地震局兰州地震研究所,兰州市东岗西路450号,730000, bio={"content":"

梁潇南,硕士生,主要研究方向为地震学,E-mail:

"}, bioImg=null, bioContent=

梁潇南,硕士生,主要研究方向为地震学,E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322506439906677002, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, xref=null, ext=[AuthorCompanyExt(id=1322506439910871307, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, companyId=1322506439906677002, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Lanzhou Institute of Seismology, CEA, 450 West-Donggang Road, Lanzhou 730000, China), AuthorCompanyExt(id=1322506439919259916, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, companyId=1322506439906677002, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国地震局兰州地震研究所,兰州市东岗西路450号,730000)])]), Author(id=1322506440409993494, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322506440485490968, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, authorId=1322506440409993494, language=EN, stringName=Jianjun WANG, firstName=Jianjun, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Lanzhou Institute of Seismology, CEA, 450 West-Donggang Road, Lanzhou 730000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322506440560988441, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, authorId=1322506440409993494, language=CN, stringName=王建军, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中国地震局兰州地震研究所,兰州市东岗西路450号,730000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322506439906677002, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, xref=null, ext=[AuthorCompanyExt(id=1322506439910871307, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, companyId=1322506439906677002, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Lanzhou Institute of Seismology, CEA, 450 West-Donggang Road, Lanzhou 730000, China), AuthorCompanyExt(id=1322506439919259916, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, companyId=1322506439906677002, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国地震局兰州地震研究所,兰州市东岗西路450号,730000)])]), Author(id=1322506440657457435, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yxx@gsdzj.gov.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322506440774897949, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, authorId=1322506440657457435, language=EN, stringName=Xinxin YIN, firstName=Xinxin, middleName=null, lastName=YIN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2 Gansu Earthquake Agency, 450 West-Donggang Road, Lanzhou 730000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322506440842006814, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, authorId=1322506440657457435, language=CN, stringName=尹欣欣, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2 甘肃省地震局,兰州市东岗西路450号,730000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322506439990563085, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, xref=null, ext=[AuthorCompanyExt(id=1322506439998951694, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, companyId=1322506439990563085, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Gansu Earthquake Agency, 450 West-Donggang Road, Lanzhou 730000, China), AuthorCompanyExt(id=1322506440011534607, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, companyId=1322506439990563085, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 甘肃省地震局,兰州市东岗西路450号,730000)])])], keywords=[Keyword(id=1322506440972030239, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=EN, orderNo=1, keyword=mining earthquake), Keyword(id=1322506441039139104, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=EN, orderNo=2, keyword=time frequency analysis), Keyword(id=1322506441097859361, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=EN, orderNo=3, keyword=unsupervised learning), Keyword(id=1322506441177551138, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=EN, orderNo=4, keyword=classification of seismic signals), Keyword(id=1322506441278214435, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=CN, orderNo=1, keyword=矿震), Keyword(id=1322506441362100516, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=CN, orderNo=2, keyword=时频分析), Keyword(id=1322506443182428455, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=CN, orderNo=3, keyword=无监督学习), Keyword(id=1322506443262120232, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=CN, orderNo=4, keyword=地震信号分类)], refs=[Reference(id=1322506447766802751, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=1998, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=SlawomirJ G, AndrzejK, journalName=矿山地震学引论, refType=null, unstructuredReference=SlawomirJ G, AndrzejK. 矿山地震学引论[M]. 北京: 地震出版社, 1998, articleTitle=null, refAbstract=null), Reference(id=1322506447926186304, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=1998, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=1, authorNames=Slawomir J G, Andrzej K, journalName=null, refType=null, unstructuredReference= Slawomir J G , Andrzej K . Introduction to Mine Seismology[M]. Beijing: Seismological Press, 1998, articleTitle=null, refAbstract=null), Reference(id=1322506448014266689, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=2022, volume=47, issue=9, pageStart=3396, pageEnd=3409, url=null, language=null, rfNumber=2, rfOrder=2, authorNames=朱建波, 马斌文, 谢和平, journalName=煤炭学报, refType=null, unstructuredReference=朱建波, 马斌文, 谢和平, 等. 煤矿矿震与冲击地压的区别与联系及矿震扰动诱冲初探[J]. 煤炭学报, 2022, 47 (9): 3396- 3409, articleTitle=煤矿矿震与冲击地压的区别与联系及矿震扰动诱冲初探, refAbstract=null), Reference(id=1322506448278507842, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=2022, volume=47, issue=9, pageStart=3396, pageEnd=3409, url=null, language=null, rfNumber=2, rfOrder=3, authorNames=Zhu Jianbo, Ma Binwen, Xie Heping, journalName=null, refType=null, unstructuredReference= Zhu Jianbo , Ma Binwen , Xie Heping , et al. Differences and Connections between Mining Seismicity and Coal Bursts in Coal Mines and Preliminary Study on Coal Bursts Induced by Mining Seismicity[J]. Journal of China Coal Society, 2022, 47 (9): 3396- 3409, articleTitle=null, refAbstract=null), Reference(id=1322506448387559747, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=2017, volume=3, issue=4, pageStart=9, pageEnd=12, url=null, language=null, rfNumber=3, rfOrder=4, authorNames=Cai M F, Brown E T, journalName=Engineering, refType=null, unstructuredReference= Cai M F , Brown E T . Challenges in the Mining and Utilization of Deep Mineral Resources[J]. Engineering, 2017, 3 (4): 9- 12, articleTitle=Challenges in the Mining and Utilization of Deep Mineral Resources, refAbstract=null), Reference(id=1322506448500805956, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=2018, volume=43, issue=2, pageStart=306, pageEnd=318, url=null, language=null, rfNumber=4, rfOrder=5, authorNames=袁亮, 姜耀东, 何学秋, journalName=煤炭学报, refType=null, unstructuredReference=袁亮, 姜耀东, 何学秋, 等. 煤矿典型动力灾害风险精准判识及监控预警关键技术研究进展[J]. 煤炭学报, 2018, 43 (2): 306- 318, articleTitle=煤矿典型动力灾害风险精准判识及监控预警关键技术研究进展, refAbstract=null), Reference(id=1322506448697938245, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=2018, volume=43, issue=2, pageStart=306, pageEnd=318, url=null, language=null, rfNumber=4, rfOrder=6, authorNames=Yuan Liang, Jiang Yaodong, He Xueqiu, journalName=null, refType=null, unstructuredReference= Yuan Liang , Jiang Yaodong , He Xueqiu , et al. Research Progress of Precise Risk Accurate Identification and Monitoring Early Warning on Typical Dynamic Disasters in Coal Mine[J]. Journal of China Coal Society, 2018, 43 (2): 306- 318, articleTitle=null, refAbstract=null), Reference(id=1322506448794407238, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=2010, volume=31, issue=3, pageStart=24, pageEnd=31, url=null, language=null, rfNumber=5, rfOrder=7, authorNames=黄汉明, 边银菊, 卢世军, journalName=地震地磁观测与研究, refType=null, unstructuredReference=黄汉明, 边银菊, 卢世军, 等. v-SVC算法在地震与爆破识别及窗长度选取中的应用[J]. 地震地磁观测与研究, 2010, 31 (3): 24- 31, articleTitle=v-SVC算法在地震与爆破识别及窗长度选取中的应用, refAbstract=null), Reference(id=1322506448882487623, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=2010, volume=31, issue=3, pageStart=24, pageEnd=31, url=null, language=null, rfNumber=5, rfOrder=8, authorNames=Huang Hanming, Bian Yinju, Lu Shijun, journalName=null, refType=null, unstructuredReference= Huang Hanming , Bian Yinju , Lu Shijun , et al. v—SVC Algorithm Applied in Earthquake and Explosion Recognition and the Choice of Window Length[J]. Seismological and Geomagnetic Observation and Research, 2010, 31 (3): 24- 31, articleTitle=null, refAbstract=null), Reference(id=1322506448953790792, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=10.1007/s11069-016-2421-y, pmid=null, pmcid=null, year=2016, volume=84, issue=1, pageStart=335, pageEnd=350, url=null, language=null, rfNumber=6, rfOrder=9, authorNames=Ghaffarzadeh H, journalName=Natural Hazards, refType=null, unstructuredReference= Ghaffarzadeh H . A Classification Method for Pulse-Like Ground Motions Based on S-Transform[J]. Natural Hazards, 2016, 84 (1): 335- 350, articleTitle=A Classification Method for Pulse-Like Ground Motions Based on S-Transform, refAbstract=null), Reference(id=1322506449230614857, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=韩绍卿, 李夕海. 基于离散Gabor变换的特征提取及其在核爆地震识别中的应用[C]. 第四届国家安全地球物理学术研讨会, 青岛, 2008, articleTitle=null, refAbstract=null), Reference(id=1322506449570353482, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Han Shaoqing, Li Xihai. Feature Extraction Based on Discrete Gabor Transform and Its Application in Nuclear Explosion Earthquake Identification[C]. The 4th National Security Geophysics Academic Symposium, Qingdao, 2008, articleTitle=null, refAbstract=null), Reference(id=1322506449654239563, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=2010, volume=32, issue=3, pageStart=270, pageEnd=276, url=null, language=null, rfNumber=8, rfOrder=12, authorNames=黄汉明, 边银菊, 卢世军, journalName=地震学报, refType=null, unstructuredReference=黄汉明, 边银菊, 卢世军, 等. 天然地震与人工爆破的波形小波特征研究[J]. 地震学报, 2010, 32 (3): 270- 276, articleTitle=天然地震与人工爆破的波形小波特征研究, refAbstract=null), Reference(id=1322506449721348428, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=2010, volume=32, issue=3, pageStart=270, pageEnd=276, url=null, language=null, rfNumber=8, rfOrder=13, authorNames=Huang Hanming, Bian Yinju, Lu Shijun, journalName=null, refType=null, unstructuredReference= Huang Hanming , Bian Yinju , Lu Shijun , et al. A Wavelet Feature Research on Seismic Waveforms of Earthquakes and Explosions[J]. Acta Seismologica Sinica, 2010, 32 (3): 270- 276, articleTitle=null, refAbstract=null), Reference(id=1322506449943646541, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=10.5194/npg-19-411-2012, pmid=null, pmcid=null, year=2012, volume=19, issue=4, pageStart=411, pageEnd=419, url=null, language=null, rfNumber=9, rfOrder=14, authorNames=Kuyuk H S, Yildirim E, Dogan E, journalName=Nonlinear Processes in Geophysics, refType=null, unstructuredReference= Kuyuk H S , Yildirim E , Dogan E , et al. Application of k-Means and Gaussian Mixture Model for Classification of Seismic Activities in Istanbul[J]. Nonlinear Processes in Geophysics, 2012, 19 (4): 411- 419, articleTitle=Application of k-Means and Gaussian Mixture Model for Classification of Seismic Activities in Istanbul, refAbstract=null), Reference(id=1322506450035921230, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=2019, volume=62, issue=1, pageStart=374, pageEnd=382, url=null, language=null, rfNumber=10, rfOrder=15, authorNames=赵明, 陈石, YuenD, journalName=地球物理学报, refType=null, unstructuredReference=赵明, 陈石, YuenD. 基于深度学习卷积神经网络的地震波形自动分类与识别[J]. 地球物理学报, 2019, 62 (1): 374- 382, articleTitle=基于深度学习卷积神经网络的地震波形自动分类与识别, refAbstract=null), Reference(id=1322506450115613007, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=2019, volume=62, issue=1, pageStart=374, pageEnd=382, url=null, language=null, rfNumber=10, rfOrder=16, authorNames=Zhao Ming, Chen Shi, Yuen D, journalName=null, refType=null, unstructuredReference= Zhao Ming , Chen Shi , Yuen D . Waveform Classification and Seismic Recognition by Convolution Neural Network[J]. Chinese Journal of Geophysics, 2019, 62 (1): 374- 382, articleTitle=null, refAbstract=null), Reference(id=1322506450178527568, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=10.1029/2018GL081119, pmid=null, pmcid=null, year=2019, volume=46, issue=7, pageStart=3643, pageEnd=3651, url=null, language=null, rfNumber=11, rfOrder=17, authorNames=Linville L, Pankow K, Draelos T, journalName=Geophysical Research Letters, refType=null, unstructuredReference= Linville L , Pankow K , Draelos T . Deep Learning Models Augment Analyst Decisions for Event DiscriminationJ][J]. Geophysical Research Letters, 2019, 46 (7): 3643- 3651, articleTitle=Deep Learning Models Augment Analyst Decisions for Event DiscriminationJ], refAbstract=null), Reference(id=1322506450233053521, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=10.1190/INT-2020-0212.1, pmid=null, pmcid=null, year=2022, volume=10, issue=3, pageStart=451, pageEnd=460, url=null, language=null, rfNumber=12, rfOrder=18, authorNames=Zhou Y H, Chen W C, journalName=Interpretation, refType=null, unstructuredReference= Zhou Y H , Chen W C . Recurrent Autoencoder Model for Unsupervised Seismic Facies Analysis[J]. Interpretation, 2022, 10 (3): 451- 460, articleTitle=Recurrent Autoencoder Model for Unsupervised Seismic Facies Analysis, refAbstract=null), Reference(id=1322506450375659858, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=2022, volume=87, issue=4, pageStart=125, pageEnd=132, url=null, language=null, rfNumber=13, rfOrder=19, authorNames=Puzyrev V, Elders C, journalName=Geophysics, refType=null, unstructuredReference= Puzyrev V , Elders C . Unsupervised Seismic Facies Classification Using Deep Convolutional Autoencoder[J]. Geophysics, 2022, 87 (4): 125- 132, articleTitle=Unsupervised Seismic Facies Classification Using Deep Convolutional Autoencoder, refAbstract=null), Reference(id=1322506450467934547, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=1, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=20, authorNames=Dong L J, Li X B, Xie G N, journalName=Abstract and Applied Analysis, refType=null, unstructuredReference= Dong L J , Li X B , Xie G N . Nonlinear Methodologies for Identifying Seismic Event and Nuclear Explosion Using Random Forest, Support Vector Machine, and Naive Bayes Classification[J]. Abstract and Applied Analysis, 2014 (1), articleTitle=Nonlinear Methodologies for Identifying Seismic Event and Nuclear Explosion Using Random Forest, Support Vector Machine, and Naive Bayes Classification, refAbstract=null), Reference(id=1322506452145656148, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=2020, volume=47, issue=1, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=21, authorNames=Mousavi S M, Beroza G C, journalName=Geophysical Research Letters, refType=null, unstructuredReference= Mousavi S M , Beroza G C . A Machine-Learning Approach for Earthquake Magnitude Estimation[J]. Geophysical Research Letters, 2020, 47 (1), articleTitle=A Machine-Learning Approach for Earthquake Magnitude Estimation, refAbstract=null), Reference(id=1322506452242125141, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=2022, volume=12, issue=16, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=22, authorNames=Yin X X, Liu F, Cai R, journalName=Applied Sciences, refType=null, unstructuredReference= Yin X X , Liu F , Cai R , et al. Research on Seismic Signal Analysis Based on Machine Learning[J]. Applied Sciences, 2022, 12 (16), articleTitle=Research on Seismic Signal Analysis Based on Machine Learning, refAbstract=null), Reference(id=1322506452321816918, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=徐增光. 地震信号的时频分析方法研究及实际应用[D]. 北京: 中国石油大学(北京), 2019, articleTitle=null, refAbstract=null), Reference(id=1322506452418285911, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Zengguang. Research and Practical Application of Time-Frequency Analysis Method of Seismic Signal[D]. Beijing: China University of Petroleum(Beijing), 2019, articleTitle=null, refAbstract=null), Reference(id=1322506452485394776, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Dempster A, Schmidt D F, Webb G I. MiniRocket: A very Fast(almost) Deterministic Transform for Time Series Classification[C]. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Singapore, 2021, articleTitle=null, refAbstract=null), Reference(id=1322506452569280857, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=MacQueen J. Some Methods for Classification and Analysis of Multivariate Observations[C]. Proceedings of 5th Berkeley Symposium on Mathematical Statistics and Probability, Berkeley, 1967, articleTitle=null, refAbstract=null), Reference(id=1322506452632195418, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=null, pmid=null, pmcid=null, year=2002, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=27, authorNames=Jolliffe I T, journalName=Principal Component Analysis for Special Types of Data, refType=null, unstructuredReference= Jolliffe I T . Principal Component Analysis for Special Types of Data[M]. New York: Springer, 2002, articleTitle=null, refAbstract=null), Reference(id=1322506452699304283, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, doi=10.1023/A:1022627411411, pmid=null, pmcid=null, year=1995, volume=20, issue=3, pageStart=273, pageEnd=297, url=null, language=null, rfNumber=21, rfOrder=28, authorNames=Cortes C, Vapnik V, journalName=Machine Learning, refType=null, unstructuredReference= Cortes C , Vapnik V . Support-Vector Networks[J]. Machine Learning, 1995, 20 (3): 273- 297, articleTitle=Support-Vector Networks, refAbstract=null)], funds=[Fund(id=1322506445841617210, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, awardId=2023IESLZ01, language=EN, fundingSource=Fundamental Research Funds of the Institute of Earthquake Prediction, CEA(2023IESLZ01), fundOrder=null, country=null), Fund(id=1322506445917114683, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, awardId=2023IESLZ01, language=CN, fundingSource=中国地震局地震预测研究所基本科研业务费(2023IESLZ01), fundOrder=null, country=null), Fund(id=1322506445996806460, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, awardId=23YFFA0015, language=EN, fundingSource=Science and Technology Program of Gansu Province(23YFFA0015), fundOrder=null, country=null), Fund(id=1322506447636779326, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, awardId=23YFFA0015, language=CN, fundingSource=甘肃省科技计划(23YFFA0015), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1322506439906677002, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, xref=null, ext=[AuthorCompanyExt(id=1322506439910871307, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, companyId=1322506439906677002, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Lanzhou Institute of Seismology, CEA, 450 West-Donggang Road, Lanzhou 730000, China), AuthorCompanyExt(id=1322506439919259916, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, companyId=1322506439906677002, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国地震局兰州地震研究所,兰州市东岗西路450号,730000)]), AuthorCompany(id=1322506439990563085, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, xref=null, ext=[AuthorCompanyExt(id=1322506439998951694, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, companyId=1322506439990563085, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Gansu Earthquake Agency, 450 West-Donggang Road, Lanzhou 730000, China), AuthorCompanyExt(id=1322506440011534607, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, companyId=1322506439990563085, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 甘肃省地震局,兰州市东岗西路450号,730000)])], figs=[ArticleFig(id=1322506443408920873, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=EN, label=Fig. 1, caption=Regional structure and distribution of stations, figureFileSmall=G76aFsveel7NXIEnowJzGw==, figureFileBig=A8Frni7wOe/uQawurlj0ZA==, tableContent=null), ArticleFig(id=1322506443492806954, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=CN, label=图1, caption=区域构造及台站分布, figureFileSmall=G76aFsveel7NXIEnowJzGw==, figureFileBig=A8Frni7wOe/uQawurlj0ZA==, tableContent=null), ArticleFig(id=1322506443736076587, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=EN, label=Fig. 2, caption=Waveform spectrum diagram of mining earthquakes and blastings, figureFileSmall=8moQCG2MRqWKhJNfbAoR8w==, figureFileBig=FQHxbV33Ax55oEObDhpKXg==, tableContent=null), ArticleFig(id=1322506444067426604, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=CN, label=图2, caption=矿震和爆破的波形频谱, figureFileSmall=8moQCG2MRqWKhJNfbAoR8w==, figureFileBig=FQHxbV33Ax55oEObDhpKXg==, tableContent=null), ArticleFig(id=1322506444142924077, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=EN, label=Fig. 3, caption=Accuracy, recall, F1 score, and deviation from median of classification method trained 30 times, figureFileSmall=0MQ6FvyB7YIc6NcQBGxqFg==, figureFileBig=Z7G4U+KvBL//Rl72ZoQvDg==, tableContent=null), ArticleFig(id=1322506444512022831, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=CN, label=图3, caption=分类方法训练30次的准确率、召回率和F1分数及与中位数的偏差, figureFileSmall=0MQ6FvyB7YIc6NcQBGxqFg==, figureFileBig=Z7G4U+KvBL//Rl72ZoQvDg==, tableContent=null), ArticleFig(id=1322506444600103216, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=EN, label=Fig. 4, caption=Visualization of feature extraction for four classification models of mining seismic and blasting signals, figureFileSmall=AQ/n0tDV9KhH/fvGkbidoA==, figureFileBig=cWXLeM1WHfS350OHHsP4gQ==, tableContent=null), ArticleFig(id=1322506444914676017, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=CN, label=图4, caption=矿震与爆破信号4种分类模型的特征提取可视化, figureFileSmall=AQ/n0tDV9KhH/fvGkbidoA==, figureFileBig=cWXLeM1WHfS350OHHsP4gQ==, tableContent=null), ArticleFig(id=1322506444985979186, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=EN, label=Fig. 5, caption=Waveforms of ground stations and underground stations, figureFileSmall=YRxSTnCy6+aWLkv2PpFYBA==, figureFileBig=01eU2BxlFICEr15H2dNBPQ==, tableContent=null), ArticleFig(id=1322506445057282355, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=CN, label=图5, caption=地面台站与井下台站波形, figureFileSmall=YRxSTnCy6+aWLkv2PpFYBA==, figureFileBig=01eU2BxlFICEr15H2dNBPQ==, tableContent=null), ArticleFig(id=1322506445136974132, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=EN, label=Tab. 1, caption=

Results of different classification methods

, figureFileSmall=null, figureFileBig=null, tableContent=
方法 类别 类型 准确率/% 召回率/% F1分数/%
基于K-means分类 无监督学习 矿震 60.02 65.76 61.34
爆破 76.44 69.76 73.03
基于PCA分类 无监督学习 矿震 71.89 74.09 71.19
爆破 82.13 78.83 80.88
基于SVM分类 监督学习 矿震 80.47 82.07 79.75
爆破 87.59 85.25 86.81
基于LCL-SSS分类 协同学习 矿震 93.75 93.03 93.45
爆破 96.39 96.23 95.96
), ArticleFig(id=1322506445334106421, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=CN, label=表1, caption=

不同分类方法结果

, figureFileSmall=null, figureFileBig=null, tableContent=
方法 类别 类型 准确率/% 召回率/% F1分数/%
基于K-means分类 无监督学习 矿震 60.02 65.76 61.34
爆破 76.44 69.76 73.03
基于PCA分类 无监督学习 矿震 71.89 74.09 71.19
爆破 82.13 78.83 80.88
基于SVM分类 监督学习 矿震 80.47 82.07 79.75
爆破 87.59 85.25 86.81
基于LCL-SSS分类 协同学习 矿震 93.75 93.03 93.45
爆破 96.39 96.23 95.96
), ArticleFig(id=1322506445413798198, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=EN, label=Tab. 2, caption=

Standard deviation of accuracy, recall, and F1 score for different classification methods

, figureFileSmall=null, figureFileBig=null, tableContent=
方法 类别 准确率标准差/% 召回率标准差/% F1分数标准差/%
基于K-means分类 无监督学习 1.62 1.47 1.15
基于PCA分类 无监督学习 1.86 1.49 1.44
基于SVM分类 监督学习 1.44 1.82 0.78
基于LCL-SSS分类 协同学习 1.33 1.50 1.68
), ArticleFig(id=1322506445480907063, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=CN, label=表2, caption=

不同分类方法准确率、召回率、F1分数的标准差

, figureFileSmall=null, figureFileBig=null, tableContent=
方法 类别 准确率标准差/% 召回率标准差/% F1分数标准差/%
基于K-means分类 无监督学习 1.62 1.47 1.15
基于PCA分类 无监督学习 1.86 1.49 1.44
基于SVM分类 监督学习 1.44 1.82 0.78
基于LCL-SSS分类 协同学习 1.33 1.50 1.68
), ArticleFig(id=1322506445556404536, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=EN, label=Tab. 3, caption=

Classification results of different classification methods on surface and underground stations

, figureFileSmall=null, figureFileBig=null, tableContent=
方法 类别 类型 准确率/% 召回率/% F1分数/%
基于K-means分类 无监督学习 地面台站 64.12 66.45 62.10
井下台站 72.34 70.56 72.22
基于PCA分类 无监督学习 地面台站 74.04 72.88 70.00
井下台站 79.98 79.01 80.50
基于SVM分类 监督学习 地面台站 80.50 81.94 79.80
井下台站 87.56 84.50 85.90
基于LCL-SSS分类 协同学习 地面台站 94.02 92.15 93.08
井下台站 96.12 95.00 95.50
), ArticleFig(id=1322506445644484921, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, language=CN, label=表3, caption=

不同分类方法在地面与井下台站上的分类结果

, figureFileSmall=null, figureFileBig=null, tableContent=
方法 类别 类型 准确率/% 召回率/% F1分数/%
基于K-means分类 无监督学习 地面台站 64.12 66.45 62.10
井下台站 72.34 70.56 72.22
基于PCA分类 无监督学习 地面台站 74.04 72.88 70.00
井下台站 79.98 79.01 80.50
基于SVM分类 监督学习 地面台站 80.50 81.94 79.80
井下台站 87.56 84.50 85.90
基于LCL-SSS分类 协同学习 地面台站 94.02 92.15 93.08
井下台站 96.12 95.00 95.50
)], attaches=null, journal=Journal(id=1281211523964080133, delFlag=0, nameCn=大地测量与地球动力学, nameEn=Journal of Geodesy and Geodynamics, nameHistory1=null, nameHistory2=null, issn=1671-5942, eissn=null, cn=42-1655/P, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=BeWo6OWOseISH6uPOmc2hA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Geodesy and Geodynamics, journalRemark=null, publicationField=null, createdTime=1783394231074, updatedTime=1788951966472, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=D, firstLetterEn=D, subjectCode=Science, subjectName=null, subjectCodeEn=Science, subjectNameEn=null, picCn=BeWo6OWOseISH6uPOmc2hA==, picEn=YHLfVa8gITbOo0FeIjbLDg==, jcr=null, cjcr=null, exts=[JournalExt(id=1304522356412666698, language=CN, name=大地测量与地球动力学, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788951966622, updatedTime=1788951966622, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.jgg09.com/journalx_ddcl/authorLogOn.action, submissionEditorUrl=http://www.jgg09.com/journalx_ddcl/editorLogOn.action, submissionReviewUrl=http://www.jgg09.com/journalx_ddcl/expertLogOn.action, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1304522356576244555, language=EN, name=Journal of Geodesy and Geodynamics, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788951966661, updatedTime=1788951966661, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.jgg09.com/journalx_ddcl/authorLogOn.action, submissionEditorUrl=http://www.jgg09.com/journalx_ddcl/editorLogOn.action, submissionReviewUrl=http://www.jgg09.com/journalx_ddcl/expertLogOn.action, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1281212831689347082, websiteList=[Website(id=1281216327125799907, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1281212831689347082, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/ddcl/CN, language=CN, createTime=1783395376235, createBy=18614031015, updateTime=1783395439358, updateBy=18614031015, name=大地测量与地球动力学-中文, tplId=1146099689490845704, title=大地测量与地球动力学, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1281216715371548758, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=articleTextType, value=kx, createTime=1783395468800, updateTime=1783395468800, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715346382931, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=banner, value=null, createTime=1783395468794, updateTime=1783395468794, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715400908889, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=grayFlag, value=0, createTime=1783395468807, updateTime=1783395468807, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715333800018, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=logo, value=https://castjournals.cast.org.cn/joweb/ddcl/CN/file/pic?fileId=87adUdwolRb6UqGo0QjlJQ==, createTime=1783395468791, updateTime=1783395468791, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715421880411, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=minRunFlag, value=0, createTime=1783395468812, updateTime=1783395468812, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715363160149, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/ddcl/CN/file/pic, createTime=1783395468798, updateTime=1783395468798, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715409297498, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=silenceFlag, value=0, createTime=1783395468809, updateTime=1783395468809, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715358965844, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1783395468797, updateTime=1783395468797, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715384131671, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=themeColor, value=null, createTime=1783395468803, updateTime=1783395468803, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715392520280, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=themeStyle, value=null, createTime=1783395468805, updateTime=1783395468805, creator=18614031015, updator=18614031015)]), Website(id=1281216327713002474, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1281212831689347082, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/ddcl/EN, language=EN, createTime=1783395376375, createBy=18614031015, updateTime=1783395435863, updateBy=18614031015, name=大地测量与地球动力学-英文, tplId=1146101810881728533, title=Journal of Geodesy and Geodynamics, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1281216680483328066, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=articleTextType, value=kx, createTime=1783395460482, updateTime=1783395460483, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680453967935, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=banner, value=null, createTime=1783395460475, updateTime=1783395460475, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680521076805, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=grayFlag, value=0, createTime=1783395460491, updateTime=1783395460491, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680437190718, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=logo, value=https://castjournals.cast.org.cn/joweb/ddcl/EN/file/pic?fileId=87adUdwolRb6UqGo0QjlJQ==, createTime=1783395460471, updateTime=1783395460471, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680542048327, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=minRunFlag, value=0, createTime=1783395460496, updateTime=1783395460496, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680474939457, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/ddcl/EN/file/pic, createTime=1783395460480, updateTime=1783395460480, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680533659718, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=silenceFlag, value=0, createTime=1783395460494, updateTime=1783395460494, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680462356544, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1783395460477, updateTime=1783395460477, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680495910979, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=themeColor, value=null, createTime=1783395460485, updateTime=1783395460485, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680508493892, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=themeStyle, value=null, createTime=1783395460488, updateTime=1783395460488, creator=18614031015, updator=18614031015)])], journalTitle=大地测量与地球动力学, weixinUrl=null, journalUrl=http://www.jgg09.com/CN/home, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Geodesy and Geodynamics, journalPhotoCn=BeWo6OWOseISH6uPOmc2hA==, journalPhotoEn=YHLfVa8gITbOo0FeIjbLDg==, journalFirstLetter=D, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/ddcl/CN/10.14075/j.jgg.2024.09.433, detailUrlEn=https://castjournals.cast.org.cn/joweb/ddcl/EN/10.14075/j.jgg.2024.09.433, pdfUrlCn=https://castjournals.cast.org.cn/joweb/ddcl/CN/PDF/10.14075/j.jgg.2024.09.433, pdfUrlEn=https://castjournals.cast.org.cn/joweb/ddcl/EN/PDF/10.14075/j.jgg.2024.09.433, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1760457600000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于机器学习的矿震与爆破信号分类
收藏切换
PDF下载
梁潇南 1 , 王建军 1 , 尹欣欣 2, *
大地测量与地球动力学 | 观测技术 2025,45(10): 1093-1100
收起
收藏切换
大地测量与地球动力学 |观测技术 2025 , 45 (10) : 1093 -1100
基于机器学习的矿震与爆破信号分类
全屏
[Author(id=1322506440116392209, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liangxiaonan22@mails.ucas.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322506440221249811, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, authorId=1322506440116392209, language=EN, stringName=Xiaonan LIANG, firstName=Xiaonan, middleName=null, lastName=LIANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Lanzhou Institute of Seismology, CEA, 450 West-Donggang Road, Lanzhou 730000, China, bio={"content":"

LIANG Xiaonan, postgraduate, majors in seismology, E-mail:

"}, bioImg=null, bioContent=

LIANG Xiaonan, postgraduate, majors in seismology, E-mail:

, aboutCorrespAuthor=null), CN=AuthorExt(id=1322506440330301716, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, authorId=1322506440116392209, language=CN, stringName=梁潇南, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中国地震局兰州地震研究所,兰州市东岗西路450号,730000, bio={"content":"

梁潇南,硕士生,主要研究方向为地震学,E-mail:

"}, bioImg=null, bioContent=

梁潇南,硕士生,主要研究方向为地震学,E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322506439906677002, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, xref=null, ext=[AuthorCompanyExt(id=1322506439910871307, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, companyId=1322506439906677002, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Lanzhou Institute of Seismology, CEA, 450 West-Donggang Road, Lanzhou 730000, China), AuthorCompanyExt(id=1322506439919259916, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, companyId=1322506439906677002, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国地震局兰州地震研究所,兰州市东岗西路450号,730000)])]), Author(id=1322506440409993494, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322506440485490968, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, authorId=1322506440409993494, language=EN, stringName=Jianjun WANG, firstName=Jianjun, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Lanzhou Institute of Seismology, CEA, 450 West-Donggang Road, Lanzhou 730000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322506440560988441, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, authorId=1322506440409993494, language=CN, stringName=王建军, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中国地震局兰州地震研究所,兰州市东岗西路450号,730000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322506439906677002, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, xref=null, ext=[AuthorCompanyExt(id=1322506439910871307, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, companyId=1322506439906677002, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Lanzhou Institute of Seismology, CEA, 450 West-Donggang Road, Lanzhou 730000, China), AuthorCompanyExt(id=1322506439919259916, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, companyId=1322506439906677002, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国地震局兰州地震研究所,兰州市东岗西路450号,730000)])]), Author(id=1322506440657457435, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yxx@gsdzj.gov.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322506440774897949, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, authorId=1322506440657457435, language=EN, stringName=Xinxin YIN, firstName=Xinxin, middleName=null, lastName=YIN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2 Gansu Earthquake Agency, 450 West-Donggang Road, Lanzhou 730000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322506440842006814, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, authorId=1322506440657457435, language=CN, stringName=尹欣欣, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2 甘肃省地震局,兰州市东岗西路450号,730000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322506439990563085, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, xref=null, ext=[AuthorCompanyExt(id=1322506439998951694, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, companyId=1322506439990563085, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Gansu Earthquake Agency, 450 West-Donggang Road, Lanzhou 730000, China), AuthorCompanyExt(id=1322506440011534607, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322506435397800188, companyId=1322506439990563085, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 甘肃省地震局,兰州市东岗西路450号,730000)])])]
梁潇南1 , 王建军1, 尹欣欣2, *
作者信息
  • 1 中国地震局兰州地震研究所,兰州市东岗西路450号,730000
  • 2 甘肃省地震局,兰州市东岗西路450号,730000
通讯作者:

尹欣欣,博士生,高级工程师,主要研究方向为地震台网监测和诱发地震,E-mail:

YIN Xinxin, PhD candidate, senior engineer, majors in seismic network monitoring and induced earthquakes, E-mail:

作者简介:

梁潇南,硕士生,主要研究方向为地震学,E-mail:

Classification of Mining Seismic and Blasting Signals Based on Machine Learning
Xiaonan LIANG1 , Jianjun WANG1, Xinxin YIN2, *
Affiliations
  • 1 Lanzhou Institute of Seismology, CEA, 450 West-Donggang Road, Lanzhou 730000, China
  • 2 Gansu Earthquake Agency, 450 West-Donggang Road, Lanzhou 730000, China
  • LIANG Xiaonan, postgraduate, majors in seismology, E-mail:

出版时间: 2025-10-15 doi: 10.14075/j.jgg.2024.09.433
文章导航
收藏切换

针对甘肃某矿矿震与爆破信号的分类问题,分析了支持向量机、K-means聚类、主成分分析等常用无监督分类方法在特征选择不足、分类精度较低和样本不平衡等方面存在的显著挑战。为尝试解决这些问题,本文使用一种轻量级协同学习方法(LCL-SSS),该方法结合了MiniRocket特征提取与改进的K-means聚类,旨在提升分类的准确性与效率。通过时频分析发现,爆破事件的P波初动频率主要集中在80~200 Hz,而矿震事件的P波频率则分布在20~120 Hz。经过30次训练实验,LCL-SSS方法的分类准确率达到了95.07%,有效捕捉到矿震波形中的关键特征。

矿震  /  时频分析  /  无监督学习  /  地震信号分类

This study focuses on the classification problem of mining seismic and blasting signals in a mine in Gansu province. Common unsupervised classification methods such as support vector machine, K-means clustering, and principal component analysis were analyzed. These methods face significant challenges in terms of insufficient feature selection, low classification accuracy, and imbalanced samples. To attempt to address these issues, this paper employs a lightweight collaborative learning method(LCL-SSS) that combines MiniRocket feature extraction with improved K-means clustering, aiming to enhance the accuracy and efficiency of classification. Through time-frequency analysis, it was found that the initial P-wave frequency of blasting events is mainly concentrated between 80 to 200 Hz, while the P-wave frequency of mining seismic events is distributed between 20 to 120 Hz. After 30 training experiments, the classification accuracy of the LCL-SSS method reached 95.07%, effectively capturing key features in mining seismic waveforms.

mining earthquake  /  time frequency analysis  /  unsupervised learning  /  classification of seismic signals
梁潇南, 王建军, 尹欣欣. 基于机器学习的矿震与爆破信号分类. 大地测量与地球动力学, 2025 , 45 (10) : 1093 -1100 . DOI: 10.14075/j.jgg.2024.09.433
Xiaonan LIANG, Jianjun WANG, Xinxin YIN. Classification of Mining Seismic and Blasting Signals Based on Machine Learning[J]. Journal of Geodesy and Geodynamics, 2025 , 45 (10) : 1093 -1100 . DOI: 10.14075/j.jgg.2024.09.433
矿震是采矿活动引发的非天然地震现象,伴随弹性能量迅速释放,可能导致地下工程或地面建筑物损坏,甚至造成人员伤亡[1-2]。随着采矿深度的增加、规模的扩大和方式的革新,矿震灾害日益复杂[3-4]。矿震的发生与地质构造、应力状态及开采方式密切相关,准确识别震动事件类型,深入研究矿震发生机理、破坏特征及其与采矿活动的关系,对保障矿区安全生产、预防和控制矿震灾害具有重要意义。
在矿震与爆破事件的识别领域,研究方法已经从传统判据向人工智能技术转变。传统判据主要基于地球物理特征,如P/S震幅比、震源深度、P波初至等[5-6]。随着研究的深入,新的判据和方法不断涌现[7-13],目前大多数研究集中在天然地震和人工爆炸事件上,针对矿震识别的研究相对较少。由于矿震和爆破事件的复杂时频特征,传统方法在识别效果上存在局限性[14],尽管多层卷积神经网络在分类精度上表现出色,但其训练过程复杂,计算效率较低[15]。为解决上述问题,本文专注于矿震与爆破事件的识别,采用一种轻量级协同学习方法(LCL-SSS)[16],该方法融合了无监督学习和监督学习的优势,通过一维卷积神经网络实现了高效分类。与传统监督分类方法相比,LCL-SSS方法减少了对大量标记数据的依赖,提高了计算效率,降低了过拟合的风险。本文旨在准确识别矿震与爆破事件,为矿震灾害的预防提供科学依据。
选取2024-01-01—04-06甘肃某矿矿震事件,研究区范围为102.88°~102.92°E、36.35°~36.38°N,分析震级大于ML-0.56的矿震和爆破事件,共选取矿震事件46个,爆破事件73个。矿震和爆破的能量分布相似,集中在ML-0.56~0.12之间,其中矿震震级为ML-0.49~0.68,爆破震级为ML-0.56~0.72。研究数据来自于由11个地表ALLSEIS-4C三分量地震监测台站和20个井下SOS台站组成的井地一体监测台网(图 1)。
本文采用连续小波变换(CWT)进行时频分析。小波变换是一种时间尺度平面分析方法,能够对高频和低频信号分别使用窄时窗和宽时窗,在时域和频域中都可表现信号的局部特征,其中高频部分具有高时间分辨率和低频率分辨率,低频部分具有高频率分辨率和低时间分辨率。小波变换的窗口面积恒定,形状可变,时间窗和频率窗可灵活调整[17]。
对基本小波母函数ψ(t)进行伸缩和平移变换,得到一系列与母函数波形相似但波形宽度不同的新函数ψa, b(t):
$\psi_{a, b}(t)=|a|^{-\frac{1}{2}} \psi\left(\frac{t-b}{a}\right), b \in R, a \in R-\{0\}$
函数f(t)∈L2的小波变换定义为:
$W_f(a, b)=|a|^{-\frac{1}{2}} \int f(t) \psi\left(\frac{t-b}{a}\right) \mathrm{d} t$
相应反变换公式为:
$f(t)=C_{\varphi}^{-\frac{1}{2}} \iint W_f(a, b) \psi_{a, b}(t) \frac{\mathrm{d} a \mathrm{~d} b}{a^2}$
由ψ(t)生成的函数族{Ψa, b(t)}称为连续小波。式(1)中,b为定位参数,a为尺度参数,ψa, b(t)随参数a、b改变而变化。当a>1时,函数ψa, b(t)表现为伸展;当a<1时,函数ψa, b(t)表现为压缩。随着a的减小,ψa, b(t)支撑区变窄,频谱$\hat{\psi}_{a, b}(\omega)$向高频扩展;当a增大时,ψa, b(t)支撑区变宽,频谱$\hat{\psi}_{a, b}(\omega)$移向低频,这使得窗口大小呈自适应特性。当信号在高频段时,时窗宽度减小,时间分辨率提高,频率分辨率降低。
采用LCL-SSS地震信号分类方法,结合监督学习的特征提取和无监督学习的聚类灵活性,通过两步协同学习框架提高地震事件分类的准确性和效率。
1) 第1步,LCL-SSS使用MiniRocket方法[18]提取地震波形特征。MiniRocket是一种高效时间序列特征提取技术,使用固定长度为9的卷积核进行数据变换,权重为α=-1和β=2,应用膨胀卷积,膨胀率范围为[[20], [222·max/m], ···, [2m·max/m]],其中m为最大膨胀数,限制为32。MiniRocket通过计算概率峰值(PPV)进行特征提取,利用预计算和组合操作提高计算效率,其卷积操作公式为:
$\begin{gathered}X * W_d=\sum\limits_{j=0}^{m-1} x_i-\left(\left|\frac{m}{2}\right| d\right)+(j \cdot d) w_j, \\\forall i \in\{0, 1 \cdots, n-1\}\end{gathered}$
式中,xi为输入地震波形数据;W为卷积核权重;d为膨胀率。这种操作可有效处理长时间序列数据,计算复杂度低。
2) 第2步,LCL-SSS使用改进K-means算法对提取特征进行无监督聚类分析,将SCAN损失函数集成到聚类方法中,提高聚类分布的均匀性。利用欧几里得距离(Euclidean distance)找到每个样本的k个最近邻点,通过神经网络学习聚类函数softmax函数进行软分配,得到类别概率分布。SCAN损失包括一致性损失和熵损失,其中一致性损失确保样本及其邻居预测一致,熵损失避免聚类集中于单一类别。这种设计可有效解决传统K-means算法可能出现的聚类退化问题,即单个聚类主导预测趋势或聚类消失。
为评估LCL-SSS方法的性能,本文还对比了3种常用分类方法:K-means、主成分分析(PCA)和支持向量机(SVM)。K-means是一种经典的无监督学习算法,通过迭代将数据划分为K个簇,最小化每个数据点到簇中心的距离平方和[19];PCA是一种降维技术,通过线性变换将高维数据投影到低维空间,保留数据主要变异性,用于提取波形特征和减少数据维度[20];SVM是一种有监督学习算法,通过在高维特征空间中构建超平面,最大化不同类别数据点之间的间隔[21]。
采用标准神经网络评估指标计算召回率、准确率和F1分数。TP表示正确预测为正样本,FP表示错误预测为正样本,TN表示正确预测为负样本,FN表示错误预测为负样本,则准确率A为模型整体的预测正确性:
$A=(\mathrm{TP}+\mathrm{TN}) /(\mathrm{TP}+\mathrm{TN}+\mathrm{FP}+\mathrm{FN})$
召回率R为实际正样本中被预测为正样本的比例:
$R=\mathrm{TP} /(\mathrm{TP}+\mathrm{FN})$
精确率P表示正确预测为正样本的比例。F1分数为精确率和召回率调和平均值,用于综合衡量分类性能,计算公式为:
$P=\mathrm{TP} /(\mathrm{TP}+\mathrm{FP})$
$F_1=2 \mathrm{TP} /(2 \mathrm{TP}+\mathrm{FP}+\mathrm{FN})$
由于数据量较小,本文采用留一交叉验证方法(leave-one-out cross-validation)来验证方法的准确性和稳定性。每次测试保留1个事件,完成所有子测试后给出整体识别率。此方法只能计算最终识别率,无法计算平均、最高和最低识别率。为应对类别不平衡问题,输出参数时使用加权计算,每个类别的权重根据其在真实标签中的比例确定。
为分析矿震和爆破事件的波形特征,采用连续小波变换对两类事件进行时频分析。两类事件的采样频率为500 Hz,奈奎斯特频率(Nyquist frequency)为250 Hz。图 2为6组矿震和爆破事件的频谱分析结果。
图 2显示,爆破和矿震波形差异显著。爆破波形表现为P波能量强,初动多为向上,初始阶段震动明显、振幅大、衰减快,尾部能量减弱迅速;相比之下,矿震波形特点为P波能量大,初动方向多为向下,能量分布均匀,波形持续时间长、衰减慢,尾部仍有明显震动。时频分析显示,矿震和爆破信号在频率特征上既有差异又存在重叠。矿震信号频率分布相对集中,主要在20~120 Hz;爆破信号频率复杂,主要集中在80~200 Hz。在80~120 Hz范围内,矿震和爆破信号都有明显的频率成分,形成重叠区域,这种频率特征的部分重叠和复杂性使得仅依靠频率阈值难以准确区分两类事件。
尽管时频分析揭示矿震和爆破事件在波形和频率特征上存在显著差异,但在实际应用中仍面临挑战。部分事件可能呈现出介于典型矿震和爆破之间的特征,这种模糊性使得仅依靠时频特征进行准确分类变得困难。此外,矿区环境复杂,可能存在干扰信号或非典型事件,这些因素会影响基于时频特征的识别效果。鉴于以上局限性,有必要引入更先进的机器学习方法以提高分类的准确性和效率。
本文采用K-means、PCA、SVM和LCL-SSS四种方法对46个矿震事件和73个爆破事件进行分类,并进行30次训练实验,结果如图 3和表 1所示。在分类过程中,提取每个事件的时域和频域特征,如振幅和峰值频率等。K-means通过特征聚类进行分类;PCA利用降维来识别主要特征;SVM通过标记数据进行训练,学习分类边界;LCL-SSS结合时频分析和多层次特征进行学习,优化分类结果并减少误判。
由表 1可见,LCL-SSS结果最佳,准确率达95.07%,在矿震和爆破事件的分类中均表现出色;SVM和PCA次之,准确率分别为84.03%和77.01%,两者都在爆破事件的识别上优于矿震;K-means的准确率最低,为68.23%,在识别矿震事件上存在较大困难。总体而言,所有分类方法在爆破事件的识别上均优于矿震,这可能是因为爆破事件的特征更加一致,便于识别。
图 3显示,4种分类方法的性能显著不同。其中,LCL-SSS表现最佳,其准确率、召回率和F1分数均较高且波动最小,展现出优异的分类性能和稳定性;SVM次之,表现相对稳定,但训练过程中有波动;PCA表现一般,波动较大,反映出特征提取和分类的不稳定性;K-means表现最差,波动最大,显示分类能力较弱。通过计算训练准确率、召回率和F1分数与中位数的偏差,并结合4种方法的标准差来评估结果的稳定性,标准差越小结果越稳定。由表 2可以看出,LCL-SSS在准确率上最稳定,大部分集中在0附近,且多在0线上方,表明其性能普遍高于中位数;SVM在准确率和F1分数上较为稳定,但召回率波动较大;PCA和K-means则显示出较大波动,尤其是K-means,结果不稳定。
为直观比较各分类方法的效果,对矿震和爆破事件进行分类分析,并将结果可视化。由图 4可见,K-means在区分矿震和爆破事件时困难较大,尤其在交界区域,错误分类现象明显;PCA有所改善,但仍存在错误分类;SVM显著提高了准确性,错误点减少,分类能力良好;LCL-SSS表现最佳,错误点最少,几乎实现完全正确分类。整体趋势显示,随着方法的进步,分类效果不断提升,错误率逐渐降低,LCL-SSS在处理这类地震数据时展现出最佳性能。
本文采用K-means、PCA、SVM和LCL-SSS四种方法对矿震与爆破事件进行分类识别,旨在评估不同算法在地震事件分类中的性能。结果显示,LCL-SSS分类效果最佳,总体准确率达95.07%,显著优于其他方法。LCL-SSS结合高效的MiniRocket特征提取,能迅速捕捉地震波形关键特征;改进的K-means聚类算法增强了对非线性数据的处理能力;轻量化设计在确保高准确度的同时降低了计算复杂度,适合大规模实时数据的处理。此外,LCL-SSS通过协同学习策略,结合无监督的特征提取和有监督的分类过程,减少了对大量标记数据的依赖,提高了模型的泛化能力。特别是在频率特征的识别上,LCL-SSS能有效区分矿震(20~120 Hz)与爆破事件(80~200 Hz),在复杂频谱特征分类中表现出色。30轮训练测试结果显示,LCL-SSS方法高度稳定,保证了其在实际应用中的可靠性。
相比之下,其他方法的分类能力与LCL-SSS相比存在明显差距。SVM的准确率为84.03%,表明监督分类方法在利用标记数据学习特征表示方面有优势,但其性能依赖于对手工特征的提取和选择,其表现受到特征质量的限制,无法全面捕捉地震信号的信息[21]。PCA的准确率为77.01%,作为一种线性降维方法,对地震信号的非线性特征提取能力有限[20],虽然低于监督学习,但仍表明无监督学习方法在处理地震信号时有潜力。K-means的准确率最低,为68.23%,表明其在处理信号特征方面的能力不足,难以有效区分矿震和爆破事件[19]。所有方法在识别爆破事件时的表现均优于矿震事件,可能因为爆破事件的波形和频谱特征更加一致和明显。
本文采用的地震事件数据包括地面台站和井下台站记录,比较两者的差异有助于理解矿震与爆破信号的分类(图 5和表 3)。地面台站记录具有较大的震动幅度和广泛的频率范围,适合识别强震或爆破事件,但由于环境噪声干扰,面波较为发育,且高频成分较少,地面台站数量少,数据量不足,限制了特征提取,可能影响分类准确性。相比之下,井下台站记录因受矿井结构保护,噪声较少,高频成分丰富且衰减快,能提供更清晰的震动信号,有利于捕捉矿震特征并减少干扰,LCL-SSS方法在井下记录中的分类效果优于地面记录。
矿震本质上可视为一种特殊的构造地震,其发生机制与天然地震相似,均涉及岩体内应力的积累和释放,主要区别在于矿震通常发生在采矿活动影响区域,震源深度较浅,震中分布相对集中。在波形特征上,天然地震的波形在频谱和P/S比特征上介于典型爆破和矿震之间。通过对比各分类方法的效果发现,LCL-SSS在识别典型事件时表现出较高的准确性,而其他方法的分类结果存在较大误差,说明LCL-SSS在处理复杂信号时具有优势。
无监督学习方法具有独特优势,特别是在处理大规模数据集或面对未知事件时不需要人工标记。在实际应用中,获取大量准确标记的地震数据耗时且昂贵,因此无监督方法可作为初步分析工具。建立无监督方法在实践中应用相对简单,与有监督方法相比,不需要制作标签,计算成本低[16]。监督分类任务优化目标函数是E(x, y)~D[lnpθ(y|x)],从标记数据中提取与标签相关的信息;而无监督任务主要用于最大似然估计Ex~D[lnpθ(x)]。由于缺乏类别信息,无监督方法难以正确估计基于类别的分布,因此在基于全波形识别的地震类型研究中,较少使用无监督方法[23]。
LCL-SSS结合MiniRocket特征提取和改进的K-means聚类,能更好地捕捉地震信号的复杂非线性特征,尽管不直接使用标签信息,该方法通过特征提取和聚类算法发现数据中与不同类型地震事件相关的内在结构。与传统的无监督聚类方法(如K-means和PCA)相比,LCL-SSS能更准确地识别事件区分特征,表现更佳。这表明,创新的无监督学习技术有潜力克服传统无监督方法的限制,为地震数据分析提供新的可能。
本文对矿震与爆破事件进行时频分析和多种分类方法比较,得出以下结论:
1) 矿震与爆破事件在时频特征上存在差异。时频分析表明,爆破事件波形P波能量强,初动多为向上,频率较高且分散,集中在80~200 Hz;相比之下,矿震事件波形更复杂,P波初动多为向下,衰减缓慢,频率主要分布在20~120 Hz。这些差异反映了两类事件的不同形成机制,也为自动化分类提供了重要特征,有助于矿山安全生产和矿震预警。
2) LCL-SSS在矿震信号分类中表现出色。LCL-SSS总体准确率达95.07%,显著优于SVM(84.03%)、PCA(77.01%)和K-means(68.23%),所有方法在识别爆破事件时的表现优于矿震事件,可能是因为爆破特征更为一致。尽管SVM等监督学习方法通常优于无监督方法,但LCL-SSS展示了无监督学习在矿震信号分类中的巨大潜力,特别适用于标记数据不足的情况。
3) LCL-SSS在矿震信号分类中展现出独特优势。在技术层面,LCL-SSS集成了高效的MiniRocket特征提取和改进的K-means聚类算法,增强了对复杂非线性数据的处理能力,其轻量级设计保证了高准确度,同时降低了计算复杂度,适合实时处理大规模数据,在多轮训练测试中表现出优异的稳定性,能够识别复杂频谱特征。此外,LCL-SSS无需手动制作标签,减少了前期工作量,计算成本低,适合处理缺乏先验信息的大规模地震数据。
尽管LCL-SSS表现优异,但由于矿震事件样本较少,存在过拟合问题。未来需不断收集不同区域的非天然地震事件样本,以提高方法的泛化能力。此外,随着机器学习方法的改进,分类准确率和计算效率仍有提升空间,未来将致力于实现更快速、精确的矿震事件分类研究。
  • 中国地震局地震预测研究所基本科研业务费(2023IESLZ01)
  • 甘肃省科技计划(23YFFA0015)
参考文献 引证文献
排序方式:
1
SlawomirJ G, AndrzejK. 矿山地震学引论[M]. 北京: 地震出版社, 1998
Slawomir J G , Andrzej K . Introduction to Mine Seismology[M]. Beijing: Seismological Press, 1998
2
朱建波, 马斌文, 谢和平, 等. 煤矿矿震与冲击地压的区别与联系及矿震扰动诱冲初探[J]. 煤炭学报, 2022, 47 (9): 3396- 3409
Zhu Jianbo , Ma Binwen , Xie Heping , et al. Differences and Connections between Mining Seismicity and Coal Bursts in Coal Mines and Preliminary Study on Coal Bursts Induced by Mining Seismicity[J]. Journal of China Coal Society, 2022, 47 (9): 3396- 3409
3
Cai M F , Brown E T . Challenges in the Mining and Utilization of Deep Mineral Resources[J]. Engineering, 2017, 3 (4): 9- 12
4
袁亮, 姜耀东, 何学秋, 等. 煤矿典型动力灾害风险精准判识及监控预警关键技术研究进展[J]. 煤炭学报, 2018, 43 (2): 306- 318
Yuan Liang , Jiang Yaodong , He Xueqiu , et al. Research Progress of Precise Risk Accurate Identification and Monitoring Early Warning on Typical Dynamic Disasters in Coal Mine[J]. Journal of China Coal Society, 2018, 43 (2): 306- 318
5
黄汉明, 边银菊, 卢世军, 等. v-SVC算法在地震与爆破识别及窗长度选取中的应用[J]. 地震地磁观测与研究, 2010, 31 (3): 24- 31
Huang Hanming , Bian Yinju , Lu Shijun , et al. v—SVC Algorithm Applied in Earthquake and Explosion Recognition and the Choice of Window Length[J]. Seismological and Geomagnetic Observation and Research, 2010, 31 (3): 24- 31
6
Ghaffarzadeh H . A Classification Method for Pulse-Like Ground Motions Based on S-Transform[J]. Natural Hazards, 2016, 84 (1): 335- 350
7
韩绍卿, 李夕海. 基于离散Gabor变换的特征提取及其在核爆地震识别中的应用[C]. 第四届国家安全地球物理学术研讨会, 青岛, 2008
Han Shaoqing, Li Xihai. Feature Extraction Based on Discrete Gabor Transform and Its Application in Nuclear Explosion Earthquake Identification[C]. The 4th National Security Geophysics Academic Symposium, Qingdao, 2008
8
黄汉明, 边银菊, 卢世军, 等. 天然地震与人工爆破的波形小波特征研究[J]. 地震学报, 2010, 32 (3): 270- 276
Huang Hanming , Bian Yinju , Lu Shijun , et al. A Wavelet Feature Research on Seismic Waveforms of Earthquakes and Explosions[J]. Acta Seismologica Sinica, 2010, 32 (3): 270- 276
9
Kuyuk H S , Yildirim E , Dogan E , et al. Application of k-Means and Gaussian Mixture Model for Classification of Seismic Activities in Istanbul[J]. Nonlinear Processes in Geophysics, 2012, 19 (4): 411- 419
10
赵明, 陈石, YuenD. 基于深度学习卷积神经网络的地震波形自动分类与识别[J]. 地球物理学报, 2019, 62 (1): 374- 382
Zhao Ming , Chen Shi , Yuen D . Waveform Classification and Seismic Recognition by Convolution Neural Network[J]. Chinese Journal of Geophysics, 2019, 62 (1): 374- 382
11
Linville L , Pankow K , Draelos T . Deep Learning Models Augment Analyst Decisions for Event DiscriminationJ][J]. Geophysical Research Letters, 2019, 46 (7): 3643- 3651
12
Zhou Y H , Chen W C . Recurrent Autoencoder Model for Unsupervised Seismic Facies Analysis[J]. Interpretation, 2022, 10 (3): 451- 460
13
Puzyrev V , Elders C . Unsupervised Seismic Facies Classification Using Deep Convolutional Autoencoder[J]. Geophysics, 2022, 87 (4): 125- 132
14
Dong L J , Li X B , Xie G N . Nonlinear Methodologies for Identifying Seismic Event and Nuclear Explosion Using Random Forest, Support Vector Machine, and Naive Bayes Classification[J]. Abstract and Applied Analysis, 2014 (1)
15
Mousavi S M , Beroza G C . A Machine-Learning Approach for Earthquake Magnitude Estimation[J]. Geophysical Research Letters, 2020, 47 (1)
16
Yin X X , Liu F , Cai R , et al. Research on Seismic Signal Analysis Based on Machine Learning[J]. Applied Sciences, 2022, 12 (16)
17
徐增光. 地震信号的时频分析方法研究及实际应用[D]. 北京: 中国石油大学(北京), 2019
Xu Zengguang. Research and Practical Application of Time-Frequency Analysis Method of Seismic Signal[D]. Beijing: China University of Petroleum(Beijing), 2019
18
Dempster A, Schmidt D F, Webb G I. MiniRocket: A very Fast(almost) Deterministic Transform for Time Series Classification[C]. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Singapore, 2021
19
MacQueen J. Some Methods for Classification and Analysis of Multivariate Observations[C]. Proceedings of 5th Berkeley Symposium on Mathematical Statistics and Probability, Berkeley, 1967
20
Jolliffe I T . Principal Component Analysis for Special Types of Data[M]. New York: Springer, 2002
21
Cortes C , Vapnik V . Support-Vector Networks[J]. Machine Learning, 1995, 20 (3): 273- 297
2025年第45卷第10期
PDF下载
45
22
引用本文
BibTeX
文章信息
doi: 10.14075/j.jgg.2024.09.433
  • 接收时间:2024-09-19
  • 首发时间:2026-10-29
  • 出版时间:2025-10-15
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-09-19
基金
Fundamental Research Funds of the Institute of Earthquake Prediction, CEA(2023IESLZ01)
中国地震局地震预测研究所基本科研业务费(2023IESLZ01)
Science and Technology Program of Gansu Province(23YFFA0015)
甘肃省科技计划(23YFFA0015)
作者信息
    1 中国地震局兰州地震研究所,兰州市东岗西路450号,730000
    2 甘肃省地震局,兰州市东岗西路450号,730000

通讯作者:

尹欣欣,博士生,高级工程师,主要研究方向为地震台网监测和诱发地震,E-mail:

YIN Xinxin, PhD candidate, senior engineer, majors in seismic network monitoring and induced earthquakes, E-mail:

参考文献
分享链接
https://castjournals.cast.org.cn/joweb/ddcl/CN/10.14075/j.jgg.2024.09.433
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏