Article(id=1156983786463384402, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156983783787421903, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2402941, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1713715200000, receivedDateStr=2024-04-22, revisedDate=1731945600000, revisedDateStr=2024-11-19, acceptedDate=null, acceptedDateStr=null, onlineDate=1753776030412, onlineDateStr=2025-07-29, pubDate=1739808000000, pubDateStr=2025-02-18, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1753776030412, onlineIssueDateStr=2025-07-29, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1753776030412, creator=13701087609, updateTime=1753776030412, updator=13701087609, issue=Issue{id=1156983783787421903, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='5', pageStart='1753', pageEnd='2192', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1753776029774, creator=13701087609, updateTime=1769691857141, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1223739602251436918, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156983783787421903, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1223739602251436919, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156983783787421903, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=2111, endPage=2118, ext={EN=ArticleExt(id=1156983787235136345, articleId=1156983786463384402, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Rockburst Intensity Level Prediction Based on Parallel Fusion Graph Transformer, columnId=1156262728772735295, journalTitle=Science Technology and Engineering, columnName=Papers·Traffics and Transportations, runingTitle=null, highlight=null, articleAbstract=

Rockburst is an extremely destructive geological disaster in deep underground engineering. In order to accurately predict the intensity level of rockburst, a method for rockburst intensity level prediction based on parallel fusion graph Transformer (PFGT) was proposed. Firstly, the similarity structure relationship of rockburst data in Euclidean space was utilized to construct graph-structured data. Besides, another kind of graph-structured data was constructed by utilizing multiple rockburst criteria to constrain the structural distortion of rockburst data in European space. Single-scale features of rockburst data was obtained through parallel training. Secondly, a feature fusion graph Transformer strategy was designed, which obtains multi-scale features of rockburst data by fusing two types of graph-structured data features based on Euclidean space and based on rockburst criteria. The method improves the data representation capability by simultaneously utilizing single-scale features and multi-scale features. During the training process, using Transformer for feature fusion enables the model to more comprehensively capture the optimized features of rockburst data, thus improving model performance. Compared with traditional neural networks and other machine learning algorithms, the prediction accuracy of the PFGT model is 94.87%, which is superior to other algorithms, proving the effectiveness of this algorithm and providing a new method for rockburst level prediction.

, correspAuthors=Yan-min ZHU, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, 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, authorCompany=null, fund=null, authors=null, authorsList=Tian-xiang GAO, Shu-zhi SU, Yan-min ZHU, Teng-yue FAN), CN=ArticleExt(id=1156983936321672152, articleId=1156983786463384402, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于平行融合图Transformer的岩爆烈度等级预测, columnId=1156262730664366426, journalTitle=科学技术与工程, columnName=论文·交通运输, runingTitle=null, highlight=null, articleAbstract=

岩爆是地下深部工程中一种破坏性极强的地质灾害,为准确预测岩爆烈度等级,提出了一种基于平行融合图Transformer(parallel fusion graph Transformer, PFGT)的岩爆烈度等级预测方法。首先,该方法利用岩爆数据在欧氏空间中的相似性结构关系构建图结构数据,并通过多重岩爆判据来约束岩爆数据在欧式空间中结构的畸变构建另一种图结构数据,通过平行训练获得岩爆数据的单尺度特征。其次,该方法设计了一种特征融合图Transformer策略,通过融合基于欧式空间和基于岩爆判据的两种图结构数据特征,获得岩爆数据的多尺度特征。该方法能够同时利用单尺度特征和多尺度特征,增强了数据表示能力,在训练过程中使用Transformer进行特征融合使得模型能够更全面地捕捉岩爆数据的优化特征,提升模型性能。通过与传统神经网络和其他机器学习算法相比,PFGT模型的预测准确率为94.87%,优于其他算法,证明了该算法的有效性,为岩爆等级预测提供了一种新的方法。

, correspAuthors=朱彦敏, authorNote=null, correspAuthorsNote=
*朱颜敏(1988—),女,汉族,山东泰安人,博士,讲师。研究方向:模式识别、岩爆预测等。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=VM3MxZa1KqsJbsPpOj/5aA==, magXml=VcTrFvUsuKAod9LgoqpukQ==, pdfUrl=null, pdf=xOmINiyO2wOusxO2LXiWWQ==, pdfFileSize=7881378, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=i7ADepBiseYpY9y1hl+QWw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=HaP9M7TvY7JfgiVEigtXXw==, mapNumber=null, authorCompany=null, fund=null, authors=

高天祥(1997—),男,汉族,湖北十堰人,硕士研究生。研究方向:图神经网络、岩爆预测等。E-mail:

, authorsList=高天祥, 苏树智, 朱彦敏, 樊腾悦)}, authors=[Author(id=1225467185179574589, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=gao369260@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1225467185309598032, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, authorId=1225467185179574589, language=EN, stringName=Tian-xiang GAO, firstName=Tian-xiang, middleName=null, lastName=GAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Computer Science and Engineering, Anhui University of Science & Technology, Huainan 232001, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225467185519313259, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, authorId=1225467185179574589, language=CN, stringName=高天祥, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 安徽理工大学计算机科学与工程学院, 淮南 232001, bio={"content":"

高天祥(1997—),男,汉族,湖北十堰人,硕士研究生。研究方向:图神经网络、岩爆预测等。E-mail:

"}, bioImg=null, bioContent=

高天祥(1997—),男,汉族,湖北十堰人,硕士研究生。研究方向:图神经网络、岩爆预测等。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225467184575594757, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, xref=1, ext=[AuthorCompanyExt(id=1225467184655286544, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, companyId=1225467184575594757, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Computer Science and Engineering, Anhui University of Science & Technology, Huainan 232001, China), AuthorCompanyExt(id=1225467184672063763, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, companyId=1225467184575594757, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 安徽理工大学计算机科学与工程学院, 淮南 232001)])]), Author(id=1225467187025068413, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, 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=1225467187272532367, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, authorId=1225467187025068413, language=EN, stringName=Shu-zhi SU, firstName=Shu-zhi, middleName=null, lastName=SU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Computer Science and Engineering, Anhui University of Science & Technology, Huainan 232001, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225467187603882415, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, authorId=1225467187025068413, language=CN, stringName=苏树智, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 安徽理工大学计算机科学与工程学院, 淮南 232001, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225467184575594757, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, xref=1, ext=[AuthorCompanyExt(id=1225467184655286544, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, companyId=1225467184575594757, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Computer Science and Engineering, Anhui University of Science & Technology, Huainan 232001, China), AuthorCompanyExt(id=1225467184672063763, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, companyId=1225467184575594757, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 安徽理工大学计算机科学与工程学院, 淮南 232001)])]), Author(id=1225467187771654592, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zyanmin1988@163.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1225467187897483729, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, authorId=1225467187771654592, language=EN, stringName=Yan-min ZHU, firstName=Yan-min, middleName=null, lastName=ZHU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2 School of Mechanical Engineering, Anhui University of Science & Technology, Huainan 232001, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225467188040090081, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, authorId=1225467187771654592, language=CN, stringName=朱彦敏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2 安徽理工大学机械工程学院, 淮南 232001, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225467184902750506, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, xref=2, ext=[AuthorCompanyExt(id=1225467184974053677, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, companyId=1225467184902750506, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Mechanical Engineering, Anhui University of Science & Technology, Huainan 232001, China), AuthorCompanyExt(id=1225467185003413806, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, companyId=1225467184902750506, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 安徽理工大学机械工程学院, 淮南 232001)])]), Author(id=1225467188195279346, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, orderNo=3, 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=1225467188400800254, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, authorId=1225467188195279346, language=EN, stringName=Teng-yue FAN, firstName=Teng-yue, middleName=null, lastName=FAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Computer Science and Engineering, Anhui University of Science & Technology, Huainan 232001, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225467188543406606, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, authorId=1225467188195279346, language=CN, stringName=樊腾悦, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 安徽理工大学计算机科学与工程学院, 淮南 232001, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225467184575594757, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, xref=1, ext=[AuthorCompanyExt(id=1225467184655286544, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, companyId=1225467184575594757, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Computer Science and Engineering, Anhui University of Science & Technology, Huainan 232001, China), AuthorCompanyExt(id=1225467184672063763, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, companyId=1225467184575594757, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 安徽理工大学计算机科学与工程学院, 淮南 232001)])])], keywords=[Keyword(id=1225467188816036396, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=EN, orderNo=1, keyword=graph neural network), Keyword(id=1225467188996391482, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=EN, orderNo=2, keyword=rockburst), Keyword(id=1225467189164163662, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=EN, orderNo=3, keyword=Transformer), Keyword(id=1225467189524873828, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=EN, orderNo=4, keyword=level prediction), Keyword(id=1225467189659091575, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=CN, orderNo=1, keyword=图神经网络), Keyword(id=1225467189805892231, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=CN, orderNo=2, keyword=岩爆), Keyword(id=1225467189902361231, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=CN, orderNo=3, keyword=Transformer), Keyword(id=1225467190040773280, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=CN, orderNo=4, keyword=等级预测)], refs=[Reference(id=1225467201902264550, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2024, volume=43, issue=1, pageStart=50, pageEnd=58, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=张志强, 张康健, 许佳磊, journalName=岩石力学与工程学报, refType=null, unstructuredReference=张志强, 张康健, 许佳磊, 等. 高地应力硬质砂岩断裂特征及岩爆孕育过程研究[J]. 岩石力学与工程学报, 2024, 43(1): 50-58., articleTitle=高地应力硬质砂岩断裂特征及岩爆孕育过程研究, refAbstract=null), Reference(id=1225467202124562676, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2024, volume=43, issue=1, pageStart=50, pageEnd=58, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Zhang Zhiqiang, Zhang Kangjian, Xu Jialei, journalName=Chinese Journal of Rock Mechanics and Engineering, refType=null, unstructuredReference=Zhang Zhiqiang, Zhang Kangjian, Xu Jialei, et al. Study on fracture characteristics and rockburst process of hard sandstone underhigh ground stresses[J]. Chinese Journal of Rock Mechanics and Engineering, 2024, 43(1): 50-58., articleTitle=Study on fracture characteristics and rockburst process of hard sandstone underhigh ground stresses, refAbstract=null), Reference(id=1225467202267169021, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=12, pageStart=25, pageEnd=29, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=李国圣, journalName=铁道工程学报, refType=null, unstructuredReference=李国圣. 构造发育区域地应力模拟及灾害判释研究[J]. 铁道工程学报, 2023, 40(12): 25-29., articleTitle=构造发育区域地应力模拟及灾害判释研究, refAbstract=null), Reference(id=1225467202443329797, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=12, pageStart=25, pageEnd=29, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Li Guosheng, journalName=Journal of Railway Engineering Society, refType=null, unstructuredReference=Li Guosheng. Study on in-situ stress simulation and disater interpretation in structral development area[j]. Journal of Railway Engineering Society, 2023, 40(12): 25-29., articleTitle=Study on in-situ stress simulation and disater interpretation in structral development area[j], refAbstract=null), Reference(id=1225467202569158931, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=12, pageStart=48, pageEnd=54, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=周航, 张广泽, 赵晓彦, journalName=铁道工程学报, refType=null, unstructuredReference=周航, 张广泽, 赵晓彦, 等. 西南山区某隧道地应力特征及岩爆危险性评价[J]. 铁道工程学报, 2023, 40(12): 48-54., articleTitle=西南山区某隧道地应力特征及岩爆危险性评价, refAbstract=null), Reference(id=1225467202724348189, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=12, pageStart=48, pageEnd=54, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=Zhou Hang, Zhang Guangze, Zhao Xiaoyan, journalName=Journal of Railway Engineering Society, refType=null, unstructuredReference=Zhou Hang, Zhang Guangze, Zhao Xiaoyan, et al. In-situ stress characteristics and rockburst risk evaluation of a tunnel in the southwest mountains[J]. Journal of Railway Engineering Society, 2023, 40(12): 48-54., articleTitle=In-situ stress characteristics and rockburst risk evaluation of a tunnel in the southwest mountains, refAbstract=null), Reference(id=1225467202896314667, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=12, pageStart=55, pageEnd=60, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=郭利民, journalName=铁道工程学报, refType=null, unstructuredReference=郭利民. 特长隧道TBM适应性评价方法[J]. 铁道工程学报, 2023, 40(12): 55-60., articleTitle=特长隧道TBM适应性评价方法, refAbstract=null), Reference(id=1225467203089252665, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=12, pageStart=55, pageEnd=60, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=Guo Limin, journalName=Journal of Railway Engineering Society, refType=null, unstructuredReference=Guo Limin. Evaluation method for TBM adaptability of extra long tunnels[J]. Journal of Railway Engineering Society, 2023, 40(12): 55-60., articleTitle=Evaluation method for TBM adaptability of extra long tunnels, refAbstract=null), Reference(id=1225467203223470404, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=11, pageStart=3694, pageEnd=3710, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=刘冬桥, 凌凯, 李娜, journalName=岩石力学与工程学报, refType=null, unstructuredReference=刘冬桥, 凌凯, 李娜, 等. 砂岩四面卸载矿柱岩爆实验研究[J]. 岩石力学与工程学报, 2023, 42(11): 3694-3710., articleTitle=砂岩四面卸载矿柱岩爆实验研究, refAbstract=null), Reference(id=1225467203332522312, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=11, pageStart=3694, pageEnd=3710, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=Liu Dongqiao, Ling Kai, Li Na, journalName=Chinese Journal of Rock Mechanics and Engineering, refType=null, unstructuredReference=Liu Dongqiao, Ling Kai, Li Na, et al. Experimental study on pillar burst of sandstone under four-faces unloading conditions[J]. Chinese Journal of Rock Mechanics and Engineering, 2023, 42(11): 3694-3710., articleTitle=Experimental study on pillar burst of sandstone under four-faces unloading conditions, refAbstract=null), Reference(id=1225467203466740049, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=29, pageStart=12451, pageEnd=12457, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=赵斌, 王寅, 赵善坤, journalName=科学技术与工程, refType=null, unstructuredReference=赵斌, 王寅, 赵善坤, 等. 特厚煤层综放工作面矿震诱发机理及防控技术: 以龙王沟煤矿为例[J]. 科学技术与工程, 2023, 23(29): 12451-12457., articleTitle=特厚煤层综放工作面矿震诱发机理及防控技术: 以龙王沟煤矿为例, refAbstract=null), Reference(id=1225467204855054688, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=29, pageStart=12451, pageEnd=12457, url=null, language=null, rfNumber=[6], rfOrder=11, authorNames=Zhao Bin, Wang Yin, Zhao Shankun, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Zhao Bin, Wang Yin, Zhao Shankun, et al. Mechanism and prevention and control technology of mine earthquake in fully mechanized top coal caving face in extra thick seam: taking Longwanggou coal mine as an example[J]. Science Technology and Engineering, 2023, 23(29): 12451-12457., articleTitle=Mechanism and prevention and control technology of mine earthquake in fully mechanized top coal caving face in extra thick seam: taking Longwanggou coal mine as an example, refAbstract=null), Reference(id=1225467205207376235, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2024, volume=52, issue=6, pageStart=51, pageEnd=66, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=许文涛, 成云海, journalName=煤炭科学技术, refType=null, unstructuredReference=许文涛, 成云海. 易弹射煤体力学特性及能量演化机制[J]. 煤炭科学技术, 2024, 52(6): 51-66., articleTitle=易弹射煤体力学特性及能量演化机制, refAbstract=null), Reference(id=1225467205345788274, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2024, volume=52, issue=6, pageStart=51, pageEnd=66, url=null, language=null, rfNumber=[7], rfOrder=13, authorNames=Xu Wentao, Cheng Yunhai, journalName=Coal Science and Technology, refType=null, unstructuredReference=Xu Wentao, Cheng Yunhai. Mechanical properties and energy evolution mechanism of coal prone to ejection[J]. Coal Science and Technology, 2024, 52(6): 51-66., articleTitle=Mechanical properties and energy evolution mechanism of coal prone to ejection, refAbstract=null), Reference(id=1225467205505171835, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2023, volume=19, issue=S1, pageStart=353, pageEnd=361, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=陈冠甫, 刘晓丽, 黎作尚, journalName=地下空间与工程学报, refType=null, unstructuredReference=陈冠甫, 刘晓丽, 黎作尚. 深埋隧道微震数据规律及岩爆特征分析[J]. 地下空间与工程学报, 2023, 19(S1): 353-361., articleTitle=深埋隧道微震数据规律及岩爆特征分析, refAbstract=null), Reference(id=1225467205693915526, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2024, volume=19, issue=S1, pageStart=353, pageEnd=361, url=null, language=null, rfNumber=[8], rfOrder=15, authorNames=Chen Guanfu, Liu Xiaoli, Li Zuoshang, journalName=Chinese Journal of Underground Space and Engineering, refType=null, unstructuredReference=Chen Guanfu, Liu Xiaoli, Li Zuoshang. Analysis on microseismic data law and rockburst characteristics of deep-buried tunnels[J]. Chinese Journal of Underground Space and Engineering, 2024, 2023, 19(S1): 353-361., articleTitle=Analysis on microseismic data law and rockburst characteristics of deep-buried tunnels, refAbstract=null), Reference(id=1225467205983322510, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2024, volume=33, issue=1, pageStart=471, pageEnd=494, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=Sun J, Wang W, Xie L, journalName=Natural Resources Research, refType=null, unstructuredReference=Sun J, Wang W, Xie L. Predicting short-term rockburst using RF-CRITIC and improved cloud model[J]. Natural Resources Research, 2024, 33(1): 471-494., articleTitle=Predicting short-term rockburst using RF-CRITIC and improved cloud model, refAbstract=null), Reference(id=1225467206155288982, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2012, volume=50, issue=4, pageStart=629, pageEnd=644, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=Zhou J, Li X, Shi X, journalName=Safety Science, refType=null, unstructuredReference=Zhou J, Li X, Shi X. Long-term prediction model of rockburst in underground openings using heuristic algorithms and support vector machines[J]. Safety Science, 2012, 50(4): 629-644., articleTitle=Long-term prediction model of rockburst in underground openings using heuristic algorithms and support vector machines, refAbstract=null), Reference(id=1225467206251757985, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=2, pageStart=617, pageEnd=635, url=null, language=null, rfNumber=[11], rfOrder=18, authorNames=Zhou J, Yang P, Peng P, journalName=Mining, Metallurgy & Exploration, refType=null, unstructuredReference=Zhou J, Yang P, Peng P, et al. Performance evaluation of rockburst prediction based on PSO-SVM, HHO-SVM, and MFO-SVM hybrid models[J]. Mining, Metallurgy & Exploration, 2023, 40(2): 617-635., articleTitle=Performance evaluation of rockburst prediction based on PSO-SVM, HHO-SVM, and MFO-SVM hybrid models, refAbstract=null), Reference(id=1225467206344032680, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2021, volume=61, issue=6, pageStart=543, pageEnd=555, url=null, language=null, rfNumber=[12], rfOrder=19, authorNames=Tang Z L, Wang X, Xu Q J, journalName=Journal of Tsinghua University (Science and Technology), refType=null, unstructuredReference=Tang Z L, Wang X, Xu Q J. Rockburst prediction based on oversampling and objective weighting method[J]. Journal of Tsinghua University (Science and Technology), 2021, 61(6): 543-555., articleTitle=Rockburst prediction based on oversampling and objective weighting method, refAbstract=null), Reference(id=1225467206461473201, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2016, volume=30, issue=5, pageStart=04016003, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=20, authorNames=Zhou J, Li X, Mitri H S, journalName=Journal of Computing in Civil Engineering, refType=null, unstructuredReference=Zhou J, Li X, Mitri H S. Classification of rockburst in underground projects: comparison of ten supervised learning methods[J]. Journal of Computing in Civil Engineering, 2016, 30(5): 04016003., articleTitle=Classification of rockburst in underground projects: comparison of ten supervised learning methods, refAbstract=null), Reference(id=1225467206633439671, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2019, volume=78, issue=null, pageStart=417, pageEnd=429, url=null, language=null, rfNumber=[14], rfOrder=21, authorNames=Xue Y, Li Z, Li S, journalName=Bulletin of Engineering Geology and the Environment, refType=null, unstructuredReference=Xue Y, Li Z, Li S, et al. Prediction of rock burst in underground caverns based on rough set and extensible comprehensive evaluation[J]. Bulletin of Engineering Geology and the Environment, 2019, 78: 417-429., articleTitle=Prediction of rock burst in underground caverns based on rough set and extensible comprehensive evaluation, refAbstract=null), Reference(id=1225467206809600452, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2019, volume=90, issue=null, pageStart=12, pageEnd=18, url=null, language=null, rfNumber=[15], rfOrder=22, authorNames=Pu Y, Apel D B, Xu H, journalName=Tunnelling and Underground Space Technology, refType=null, unstructuredReference=Pu Y, Apel D B, Xu H. Rockburst prediction in kimberlite with unsupervised learning method and support vector classifier[J]. Tunnelling and Underground Space Technology, 2019, 90: 12-18., articleTitle=Rockburst prediction in kimberlite with unsupervised learning method and support vector classifier, refAbstract=null), Reference(id=1225467206897680840, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2019, volume=31, issue=null, pageStart=8185, pageEnd=8193, url=null, language=null, rfNumber=[16], rfOrder=23, authorNames=Liu R, Ye Y, Hu N, journalName=Neural Computing and Applications, refType=null, unstructuredReference=Liu R, Ye Y, Hu N, et al. Classified prediction model of rockburst using rough sets-normal cloud[J]. Neural Computing and Applications, 2019, 31: 8185-8193., articleTitle=Classified prediction model of rockburst using rough sets-normal cloud, refAbstract=null), Reference(id=1225467207019315663, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2017, volume=24, issue=9, pageStart=2105, pageEnd=2113, url=null, language=null, rfNumber=[17], rfOrder=24, authorNames=Li T, Li Y, Yang X, journalName=Journal of Central South University, refType=null, unstructuredReference=Li T, Li Y, Yang X. Rock burst prediction based on genetic algorithms and extreme learning machine[J]. Journal of Central South University, 2017, 24(9): 2105-2113., articleTitle=Rock burst prediction based on genetic algorithms and extreme learning machine, refAbstract=null), Reference(id=1225467207145144789, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2023, volume=138, issue=null, pageStart=105180, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=25, authorNames=Liu Q, Xue Y, Li G, journalName=Tunnelling and Underground Space Technology, refType=null, unstructuredReference=Liu Q, Xue Y, Li G, et al. Application of KM-SMOTE for rockburst intelligent prediction[J]. Tunnelling and Underground Space Technology, 2023, 138: 105180., articleTitle=Application of KM-SMOTE for rockburst intelligent prediction, refAbstract=null), Reference(id=1225467207262585306, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2020, volume=45, issue=S1, pageStart=191, pageEnd=201, url=null, language=null, rfNumber=[19], rfOrder=26, authorNames=田睿, 孟海东, 陈世江, journalName=煤炭学报, refType=null, unstructuredReference=田睿, 孟海东, 陈世江, 等. 基于深度神经网络的岩爆烈度分级预测[J]. 煤炭学报, 2020, 45(S1): 191-201., articleTitle=基于深度神经网络的岩爆烈度分级预测, refAbstract=null), Reference(id=1225467207371637217, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2020, volume=45, issue=S1, pageStart=191, pageEnd=201, url=null, language=null, rfNumber=[19], rfOrder=27, authorNames=Tian Rui, Meng Haidong, Chen Shijiang, journalName=Journal of China Coal Society, refType=null, unstructuredReference=Tian Rui, Meng Haidong, Chen Shijiang, et al. Prediction of intensity classification of rockburst based on deep neural network[J]. Journal of China Coal Society, 2020, 45(S1): 191-201., articleTitle=Prediction of intensity classification of rockburst based on deep neural network, refAbstract=null), Reference(id=1225467207505854955, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=27, pageStart=11835, pageEnd=11840, url=null, language=null, rfNumber=[20], rfOrder=28, authorNames=张昱, 张明魁, journalName=科学技术与工程, refType=null, unstructuredReference=张昱, 张明魁. 基于GD-DNN模型的岩爆烈度等级预测方法与应用[J]. 科学技术与工程, 2023, 23(27): 11835-11840., articleTitle=基于GD-DNN模型的岩爆烈度等级预测方法与应用, refAbstract=null), Reference(id=1225467207631684080, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=27, pageStart=11835, pageEnd=11840, url=null, language=null, rfNumber=[20], rfOrder=29, authorNames=Zhang Yu, Zhang Mingkui, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Zhang Yu, Zhang Mingkui. Prediction method and application of rockburst intensity grade based on GD-DNN model[J]. Science Technology and Engineering, 2023, 23(27): 11835-11840., articleTitle=Prediction method and application of rockburst intensity grade based on GD-DNN model, refAbstract=null)], funds=[Fund(id=1225467198433574977, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, awardId=QNZD202202, language=CN, fundingSource=安徽理工大学青年基金(重点项目)(QNZD202202), fundOrder=null, country=null), Fund(id=1225467198546821192, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, awardId=2023142, language=CN, fundingSource=淮南市指导性科技计划(2023142), fundOrder=null, country=null), Fund(id=1225467198660067414, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, awardId=2023147, language=CN, fundingSource=淮南市指导性科技计划(2023147), fundOrder=null, country=null), Fund(id=1225467198827839587, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, awardId=52374155, language=CN, fundingSource=国家自然科学基金面上项目(52374155), fundOrder=null, country=null), Fund(id=1225467199050137715, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, awardId=2308085MF218, language=CN, fundingSource=安徽省自然科学基金(面上项目)(2308085MF218), fundOrder=null, country=null), Fund(id=1225467200417480836, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, awardId=2022AH040113, language=CN, fundingSource=安徽省高等学校自然科学研究项目(重大项目)(2022AH040113), fundOrder=null, country=null), Fund(id=1225467200832716958, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, awardId=YQZD2023035, language=CN, fundingSource=安徽省高校中青年教师培养行动项目(YQZD2023035), fundOrder=null, country=null), Fund(id=1225467201000489126, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, awardId=YZ2023H2A007, language=CN, fundingSource=安徽理工大学医学专项培育项目(重大项目)(YZ2023H2A007), fundOrder=null, country=null), Fund(id=1225467201306673342, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, awardId=OMH-2023-05, language=CN, fundingSource=合肥综合性国家科学中心大健康研究院职业医学与健康联合研究中心项目(OMH-2023-05), fundOrder=null, country=null), Fund(id=1225467201461862598, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, awardId=OMH-2023-24, language=CN, fundingSource=合肥综合性国家科学中心大健康研究院职业医学与健康联合研究中心项目(OMH-2023-24), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1225467184575594757, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, xref=1, ext=[AuthorCompanyExt(id=1225467184655286544, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, companyId=1225467184575594757, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Computer Science and Engineering, Anhui University of Science & Technology, Huainan 232001, China), AuthorCompanyExt(id=1225467184672063763, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, companyId=1225467184575594757, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 安徽理工大学计算机科学与工程学院, 淮南 232001)]), AuthorCompany(id=1225467184902750506, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, xref=2, ext=[AuthorCompanyExt(id=1225467184974053677, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, companyId=1225467184902750506, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Mechanical Engineering, Anhui University of Science & Technology, Huainan 232001, China), AuthorCompanyExt(id=1225467185003413806, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, companyId=1225467184902750506, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 安徽理工大学机械工程学院, 淮南 232001)])], figs=[ArticleFig(id=1225467192188256998, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=EN, label=Fig.1, caption=3D data distribution of the same rockburst data with different indicators, figureFileSmall=NXyVbQ4zG32qaSfYFgiotg==, figureFileBig=xRHyQvrbw62cNID/Nvs/Tg==, tableContent=null), ArticleFig(id=1225467192368612080, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=CN, label=图1, caption=相同岩爆数据选用不同指标的三维数据分布图, figureFileSmall=NXyVbQ4zG32qaSfYFgiotg==, figureFileBig=xRHyQvrbw62cNID/Nvs/Tg==, tableContent=null), ArticleFig(id=1225467192699962115, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=EN, label=Fig.2, caption=Correlation coefficients of each indicator, figureFileSmall=VRlt0wk5nXz7/Pin4T4jBA==, figureFileBig=d3YDqd22ZwDE2FGuOD4gMQ==, tableContent=null), ArticleFig(id=1225467192876122890, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=CN, label=图2, caption=各指标因素相关系数图, figureFileSmall=VRlt0wk5nXz7/Pin4T4jBA==, figureFileBig=d3YDqd22ZwDE2FGuOD4gMQ==, tableContent=null), ArticleFig(id=1225467193064866584, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=EN, label=Fig.3, caption=Main architecture of the model, figureFileSmall=q5IY3h/F1IJFo621GAQh8Q==, figureFileBig=ezijLaMuJo0EbizIelwOdw==, tableContent=null), ArticleFig(id=1225467193291359002, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=CN, label=图3, caption=模型主要架构, figureFileSmall=q5IY3h/F1IJFo621GAQh8Q==, figureFileBig=ezijLaMuJo0EbizIelwOdw==, tableContent=null), ArticleFig(id=1225467193580766001, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=EN, label=Fig.4, caption=Construct graph structure data based on Euclidean distance, figureFileSmall=DJwz11Z3ZMr/9/Z0LwYo9A==, figureFileBig=DBM33pw6WxuDxIw2WWXrZA==, tableContent=null), ArticleFig(id=1225467193798869826, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=CN, label=图4, caption=基于欧式距离构建图结构数据, figureFileSmall=DJwz11Z3ZMr/9/Z0LwYo9A==, figureFileBig=DBM33pw6WxuDxIw2WWXrZA==, tableContent=null), ArticleFig(id=1225467193983419211, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=EN, label=Fig.5, caption=Construct graph structure data based on multiple rockburst criteria, figureFileSmall=K42vb98EP3VUwWz40GdMOw==, figureFileBig=QCqoBu6gmiumYuertRNvvQ==, tableContent=null), ArticleFig(id=1225467194163774299, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=CN, label=图5, caption=基于多重岩爆判据构建图结构数据, figureFileSmall=K42vb98EP3VUwWz40GdMOw==, figureFileBig=QCqoBu6gmiumYuertRNvvQ==, tableContent=null), ArticleFig(id=1225467194381878121, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=EN, label=Fig.6, caption=The structure of standard graph convolutional network, figureFileSmall=Vf4MVlbQFHrYXLQsU/nH+A==, figureFileBig=7Cka31l4FXayHyZlhz9tmA==, tableContent=null), ArticleFig(id=1225467194646119289, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=CN, label=图6, caption=标准图卷积网络结构

X1~X5为输入向量;Z1~Z5为嵌入向量;Y1~Y5为输出向量

, figureFileSmall=Vf4MVlbQFHrYXLQsU/nH+A==, figureFileBig=7Cka31l4FXayHyZlhz9tmA==, tableContent=null), ArticleFig(id=1225467195942159229, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=EN, label=Fig.7, caption=The structure of Transformer encoder, figureFileSmall=DcpcEOv0UpPF2lhVpM+/tg==, figureFileBig=cqzPeYch2H4j6fIy4bR/+g==, tableContent=null), ArticleFig(id=1225467196051211147, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=CN, label=图7, caption=Transformer编码器结构, figureFileSmall=DcpcEOv0UpPF2lhVpM+/tg==, figureFileBig=cqzPeYch2H4j6fIy4bR/+g==, tableContent=null), ArticleFig(id=1225467196198011799, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=EN, label=Fig.8, caption=Flowchart of the algorithm, figureFileSmall=Ej3aorHkNuh0IqZYxXzxZg==, figureFileBig=yQ24GfHTyCffZloiaYsO2A==, tableContent=null), ArticleFig(id=1225467196390949802, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=CN, label=图8, caption=算法流程图, figureFileSmall=Ej3aorHkNuh0IqZYxXzxZg==, figureFileBig=yQ24GfHTyCffZloiaYsO2A==, tableContent=null), ArticleFig(id=1225467196500001718, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=EN, label=Fig.9, caption=Prediction accuracy of each algorithm, figureFileSmall=oIt7hkc2UdnsWzIl3icapw==, figureFileBig=HsqgxyeL1co9GAWykurnoQ==, tableContent=null), ArticleFig(id=1225467196709716936, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=CN, label=图9, caption=各算法预测准确率, figureFileSmall=oIt7hkc2UdnsWzIl3icapw==, figureFileBig=HsqgxyeL1co9GAWykurnoQ==, tableContent=null), ArticleFig(id=1225467196948792276, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=EN, label=Fig.10, caption=Prediction accuracy of each algorithm for different rockburst level, figureFileSmall=a1/v33IH5hrLjkuaHfG6hg==, figureFileBig=R0ERk+62aQ6zyf7f76KvPg==, tableContent=null), ArticleFig(id=1225467197129147358, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=CN, label=图10, caption=各算法对不同岩爆等级预测准确率, figureFileSmall=a1/v33IH5hrLjkuaHfG6hg==, figureFileBig=R0ERk+62aQ6zyf7f76KvPg==, tableContent=null), ArticleFig(id=1225467197389194218, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=EN, label=Table 1, caption=

Part of rockburst data

, figureFileSmall=null, figureFileBig=null, tableContent=
编号 σθ σc σt Wet 级别
1 2.6 20 3 1.39 1
2 7.28 52 3.7 1.3 1
3 39.94 117.48 2.98 2.37 2
4 40.1 72.1 2.3 4.6 3
5 40.6 66.6 2.6 3.7 3
189 274.3 61.1 5.3 7.2 4
190 274.3 99.2 7.3 8.31 4
191 274.3 91.3 14.5 21 4
), ArticleFig(id=1225467197636658175, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=CN, label=表1, caption=

部分岩爆数据

, figureFileSmall=null, figureFileBig=null, tableContent=
编号 σθ σc σt Wet 级别
1 2.6 20 3 1.39 1
2 7.28 52 3.7 1.3 1
3 39.94 117.48 2.98 2.37 2
4 40.1 72.1 2.3 4.6 3
5 40.6 66.6 2.6 3.7 3
189 274.3 61.1 5.3 7.2 4
190 274.3 99.2 7.3 8.31 4
191 274.3 91.3 14.5 21 4
), ArticleFig(id=1225467197817012232, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=EN, label=Table 2, caption=

Rockburst criterion and its discriminant

, figureFileSmall=null, figureFileBig=null, tableContent=
判据名称 判别式 阈值 岩爆等级
二郎山隧洞判据 $\frac{{\sigma }_{\theta }}{{\sigma }_{c}}$ <0.3 1
0.5~0.7 可能有岩爆
>0.7 可能有强岩爆
脆性判据 $\frac{{\sigma }_{c}}{{\sigma }_{t}}$ <10 1
10~14 2
14~18 3
>18 4
弹性变形能指数 Wet <2.0 1
2.0~3.5 2
3.5~5.0 3
>5.0 4
), ArticleFig(id=1225467197955424276, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983786463384402, language=CN, label=表2, caption=

岩爆判据及其判别式

, figureFileSmall=null, figureFileBig=null, tableContent=
判据名称 判别式 阈值 岩爆等级
二郎山隧洞判据 $\frac{{\sigma }_{\theta }}{{\sigma }_{c}}$ <0.3 1
0.5~0.7 可能有岩爆
>0.7 可能有强岩爆
脆性判据 $\frac{{\sigma }_{c}}{{\sigma }_{t}}$ <10 1
10~14 2
14~18 3
>18 4
弹性变形能指数 Wet <2.0 1
2.0~3.5 2
3.5~5.0 3
>5.0 4
)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, language=CN, oaType=是, 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=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, 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=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2402941, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2402941, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2402941, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2402941, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于平行融合图Transformer的岩爆烈度等级预测
收藏切换
PDF下载
高天祥 1 , 苏树智 1 , 朱彦敏 2, * , 樊腾悦 1
科学技术与工程 | 论文·交通运输 2025,25(5): 2111-2118
收起
收藏切换
科学技术与工程 | 论文·交通运输 2025, 25(5): 2111-2118
基于平行融合图Transformer的岩爆烈度等级预测
全屏
高天祥1 , 苏树智1, 朱彦敏2, * , 樊腾悦1
作者信息
  • 1 安徽理工大学计算机科学与工程学院, 淮南 232001
  • 2 安徽理工大学机械工程学院, 淮南 232001
  • 高天祥(1997—),男,汉族,湖北十堰人,硕士研究生。研究方向:图神经网络、岩爆预测等。E-mail:

通讯作者:

*朱颜敏(1988—),女,汉族,山东泰安人,博士,讲师。研究方向:模式识别、岩爆预测等。E-mail:
Rockburst Intensity Level Prediction Based on Parallel Fusion Graph Transformer
Tian-xiang GAO1 , Shu-zhi SU1, Yan-min ZHU2, * , Teng-yue FAN1
Affiliations
  • 1 School of Computer Science and Engineering, Anhui University of Science & Technology, Huainan 232001, China
  • 2 School of Mechanical Engineering, Anhui University of Science & Technology, Huainan 232001, China
出版时间: 2025-02-18 doi: 10.12404/j.issn.1671-1815.2402941
文章导航
收藏切换

岩爆是地下深部工程中一种破坏性极强的地质灾害,为准确预测岩爆烈度等级,提出了一种基于平行融合图Transformer(parallel fusion graph Transformer, PFGT)的岩爆烈度等级预测方法。首先,该方法利用岩爆数据在欧氏空间中的相似性结构关系构建图结构数据,并通过多重岩爆判据来约束岩爆数据在欧式空间中结构的畸变构建另一种图结构数据,通过平行训练获得岩爆数据的单尺度特征。其次,该方法设计了一种特征融合图Transformer策略,通过融合基于欧式空间和基于岩爆判据的两种图结构数据特征,获得岩爆数据的多尺度特征。该方法能够同时利用单尺度特征和多尺度特征,增强了数据表示能力,在训练过程中使用Transformer进行特征融合使得模型能够更全面地捕捉岩爆数据的优化特征,提升模型性能。通过与传统神经网络和其他机器学习算法相比,PFGT模型的预测准确率为94.87%,优于其他算法,证明了该算法的有效性,为岩爆等级预测提供了一种新的方法。

图神经网络  /  岩爆  /  Transformer  /  等级预测

Rockburst is an extremely destructive geological disaster in deep underground engineering. In order to accurately predict the intensity level of rockburst, a method for rockburst intensity level prediction based on parallel fusion graph Transformer (PFGT) was proposed. Firstly, the similarity structure relationship of rockburst data in Euclidean space was utilized to construct graph-structured data. Besides, another kind of graph-structured data was constructed by utilizing multiple rockburst criteria to constrain the structural distortion of rockburst data in European space. Single-scale features of rockburst data was obtained through parallel training. Secondly, a feature fusion graph Transformer strategy was designed, which obtains multi-scale features of rockburst data by fusing two types of graph-structured data features based on Euclidean space and based on rockburst criteria. The method improves the data representation capability by simultaneously utilizing single-scale features and multi-scale features. During the training process, using Transformer for feature fusion enables the model to more comprehensively capture the optimized features of rockburst data, thus improving model performance. Compared with traditional neural networks and other machine learning algorithms, the prediction accuracy of the PFGT model is 94.87%, which is superior to other algorithms, proving the effectiveness of this algorithm and providing a new method for rockburst level prediction.

graph neural network  /  rockburst  /  Transformer  /  level prediction
高天祥, 苏树智, 朱彦敏, 樊腾悦. 基于平行融合图Transformer的岩爆烈度等级预测. 科学技术与工程, 2025 , 25 (5) : 2111 -2118 . DOI: 10.12404/j.issn.1671-1815.2402941
Tian-xiang GAO, Shu-zhi SU, Yan-min ZHU, Teng-yue FAN. Rockburst Intensity Level Prediction Based on Parallel Fusion Graph Transformer[J]. Science Technology and Engineering, 2025 , 25 (5) : 2111 -2118 . DOI: 10.12404/j.issn.1671-1815.2402941
在地下深度开采工程中,由于地质条件复杂,岩石物理性质多样,岩爆是一种常见的地质灾害[1-2],爆发时岩石中累积的弹性势能突然释放,进而发生岩石破裂、弹射和坍塌现象,直接威胁工作人员的人身安全,影响工程进度且造成巨大经济损失,严重时能摧毁整个工程并诱发地震灾害。
国内外学者从多角度深入研究岩爆灾害[3-4],先后提出多种岩爆等级划分方法。从强度、能量、刚度等理论分析岩爆灾害提出多种岩爆倾向性经验判据,如以最大切向应力为主要因素的Hoke判据、Russenes判据、Turchaninov判据和二郎山隧洞判据[5-6],这些判据在确定判据度量值时需要评估最大切向应力值。Barton判据则仅参考原岩应力场的最大主应力为特征参量,弹性变形能指数Wet判据[7-8]以岩石力学性质为标准。岩爆倾向性经验判据多以单一指标为参考,单一指标不能充分考虑到其他指标的影响,使用单一判据评估具体岩爆案例时准确率低,存在较大的局限性。
随着研究的深入和工程数量的增加,累积了大量的岩爆数据,这为机器学习模型的应用奠定了基础。在岩爆等级预测中,机器学习模型具有更强的数据处理和分析能力,不仅能有效提取数据特征,还能根据特征进行数据优化,大大削弱了主观因素的影响,具有很强的处理非线性数据的能力。单一算法虽然削弱了主观因素的影响,但是对岩爆数据特征敏感,依赖模型的构建和优化算法。Sun等[9]使用过采样技术对每一聚类中的低类样本进行过采样,解决岩爆数据类别分布不均衡问题,提高K近邻(K-nearest neighbor,KNN)算法的准确率。Zhou等[10]利用启发式算法自动确定支持向量机(support vector machine,SVM)的最优超参数,使用SVM算法实现预测岩爆等级。Zhou等[11]结合粒子群优化(particle swarm optimization,PSO)和Harris Hawk优化(Harris Hawk optimization,HHO)提出PSO-SVM和HHO-SVM模型,效果均优于未优化的SVM模型。Tang等[12]使用过采样和客观赋权值的方法解决岩爆数据的离散问题,提高了随机森林算法的准确率。
上述算法对数据特征要求较高,集成算法虽然有良好的效果,但实现起来难度大,神经网络算法虽然有良好的特征提取能力,但通常选取的岩爆预测指标较少,对岩爆特征敏感。为解决上述问题,现提出一种基于平行融合图Transformer(parallel fusion graph Transformer, PFGT)的岩爆等级预测方法,该方法能利用单尺度特征,增强数据表示能力,克服单尺度特征局限的缺点。同时,该方法利用Transformer融合岩爆数据不同单尺度特征,可以更全面地捕捉岩爆数据的信息,使得模型能够充分利用融合后的多尺度特征,信息表征能力弱和特征单一的问题,进一步提升模型的表达能力和预测性能。通过利用不同方法构建图结构数据,使模型在训练过程中能利用单尺度和多尺度特征,从而更全面地捕捉岩爆数据的优化特征,实现岩爆等级预测。
使用岩爆数据191条,所有数据均来自研究文献,包括矿山项目和隧道项目等工程[13-18],部分数据如表1所示。其中岩爆等级共分为4个级别,无岩爆、轻微岩爆、中等岩爆和强岩爆,为方便识别分别用1、2、3、4标识。其中无岩爆数据48条,轻微岩爆50条,中等岩爆58条,强岩爆35条。
岩爆发生机理复杂,预测指标选取十分重要。文献[19]仅选取σθσcσtWet,文献[20]选取σθcσctWet作为预测指标。
图1所示,对相同岩爆数据选择不同预测指标其数据分布和数据特征是不同的,不同预测指标的选择需要选择合适算法。
岩爆各个指标是从不同方面描述岩爆发生时的力学特征,在深度地下工程中,由于应力结构被破坏使岩石释放累积的弹性势能进而发生岩爆。
图2所示,σθσθc存在较强正相关性,与σct存在负相关性,σθ是围岩最大切向力与σc单轴抗压强度是两个不同角度描述岩爆力学特征的参数,因此二者几乎没有相关性。σθWet的相关系数为0.48,虽然二者也是不同角度描述岩爆力学特征的参数,但也存在较大的正相关性。σcσt也存在较强的正相关性,但与σθc存在负相关性。除σct外各个预测指标与Wet存在一定的正相关性,而σct与各指标存在一定的负相关性。正相关表示两个因素在变化时往往会同时增加或减小,而负相关则表示一个因素增加时,另一个因素往往会减小,这对于理解岩爆指标之间的相互作用和依赖关系具有重要作用,因此选择多种预测指标具有一定意义。
提出的PFGT模型的主要架构包括3个部分:一是两种图结构数据的构建,通过平行训练获得单尺度特征;二是经过Transformer融合单尺度特征获得多尺度特征;三是融合两种单尺度图结构数据,结合多尺度特征实现岩爆烈度等级预测。模型框架共3个部分,如图3所示。
该模型首先利用欧式空间距离构建图结构数据。同时为了约束岩爆数据在欧式空间中结构的畸变,使用多重岩爆判据构建图结构数据,通过平行训练获得单尺度特征。其次利用Transformer编码器将两种单尺度特征融合获得多尺度特征,将两种图结构数据加权求平均获得融合后的图结构数据,经过图卷积网络获得岩爆等级。
在图卷积网络中,最常用欧式空间距离衡量两个节点之间的相似性,使用数据之间的欧式距离来衡量数据之间的相似性,n维空间中的两点之间的距离公式为
dist(A,B)=$\sqrt{\sum _{i=1}^{n}[{\mu }_{A}\left({x}_{i}\right)-{\mu }_{B}({x}_{i}{\left)\right]}^{2}}$
式(1)中:dist(A,B)为n维空间中A,B两点之间的真实距离;μA(xi)为向量A在第i个维度上的坐标;μB(xi)为向量B在第i个维度上的坐标。从式(1)可以看出, 欧式距离越小, 则两个向量的距离越近,代表两个数据相似性越大;反之则对应向量相差越远,数据相似性越小,通过选取k个最相似节点构建图结构数据,如图4所示,根据欧式空间距离选取2个最相似节点构建图结构数据的邻接矩阵可视化,每一个点代表该位置横坐标对应的数据与纵坐标对应的数据之间存在一条连接边。
岩爆判据是以强度、能量、刚度等理论为基础,并且不同判据是从不同方面描述岩爆影响因素,进而判断岩爆等级。在实际工程应用中也有使用多种岩爆判据综合评估岩爆等级的实例,因此通过多重岩爆判据能克服单指标判据的局限性,各种岩爆判据的取值区间和对应的岩爆等级如表2所示。
使用多重岩爆判据构建图结构数据的可视化如图5所示,由于使用了3种岩爆判据,所以各个节点之间都存在互相影响,为了平衡岩爆判据的特征影响,在融合两种图结构数据时,通过削弱岩爆判据构建图结构数据的比例来平衡两种图数据的融合。
图卷积网络是一种处理图结构数据的神经网络,通过在图节点上执行卷积操作,聚合邻域节点信息来表示自身的嵌入,能够提取非欧数据特征,普域图卷积可以表示为
(x*gθ)ζ=Ugθ(Λ)UTx
式(2)中:x为数据特征;gθ为可学习的参数;ζ为图卷积运算;U为傅里叶变换;Λ为对角矩阵。
为了减少计算量并不影响卷积效果采用切比雪夫多项式近似表示,令gθ(Λ)=$\sum _{k=0}^{k}$θkTk($\stackrel{~}{\Lambda }$),其中θk为多项式的系数向量,Tk($\stackrel{~}{\Lambda }$)为切比雪夫多项式,$\stackrel{~}{A}$=2Λ/λmax-IN,λmax为最大特征值,考虑λmax=2且 k=1,图卷积可以表示为
(x*gθ)ζ=$\sum _{k=0}^{k}$θkTk($\stackrel{~}{\Lambda }$)=θ0x-θ1x${D}^{-\frac{1}{2}}$A${D}^{-\frac{1}{2}}$x
θ=θ0=-θ1,则图卷积公式可被简化为
(x*gθ)ζ=Ugθ(Λ)UTx=θ(I+${D}^{-\frac{1}{2}}$A${D}^{-\frac{1}{2}}$)x=θ(${\stackrel{~}{D}}^{-\frac{1}{2}}\stackrel{~}{A}{\stackrel{~}{D}}^{-\frac{1}{2}}$)
结合激活函数,GCN卷积层的更新公式为
Hl+1=σ(${\stackrel{~}{D}}^{-\frac{1}{2}}\stackrel{~}{A}{\stackrel{~}{D}}^{-\frac{1}{2}}$HlWl)
式(5)中:σ(·)为激活函数;Hl为第l层的输出;W为权值矩阵;Hl+1为图卷积核输出的第l+1层的图卷积运算。
将每条岩爆数据作为图卷积网络的节点,预测指标作为节点特征构建图结构数据,使用图卷积网络实现岩爆烈度等级预测,标准图卷积结构如图6所示。
Transformer编码器使用多头注意力来并行地捕捉不同子空间的信息。多头注意力的输出是所有头的输出拼接起来,然后通过另一个可学习的权重矩阵WO进行变换,即
$\begin{aligned} \operatorname{MultiHead}(\boldsymbol{Q}, \boldsymbol{K}, \boldsymbol{V})= & \text { Concat }\left(\operatorname{Head}_{1},\right. \\ & \left.\operatorname{Head}_{2}, \cdots, \operatorname{Head}_{n}\right) \boldsymbol{W}^{o} \end{aligned}$
式(6)中:Q为当前正在进行注意力计算的对象;K为与查询相关的其他对象;V为对应键的特征表示;每个头Headi是一个自注意力层的输出。
Headi=Attention(Q${W}_{i}^{Q}$,K ${W}_{i}^{K}$,V ${W}_{i}^{V}$)
式(7)中:Q${W}_{i}^{Q}$K${W}_{i}^{K}$V${W}_{i}^{V}$为每个头的可学习权重矩阵,位置编码是与输入特征X相加的,即
Xpositional=X+P
式(8)中:P为位置编码矩阵,它可以根据位置的不同使用不同的频率的正弦和余弦函数来生成。Transformer编码器由多个相同的层堆叠而成。
EncoderLayer(X)=LayerNorm[X+MultiHeadAttention(WQ,WK,WV)WO]
EncoderLayer(X)=LayerNorm[X+FFN(X)]
式中:LayerNorm为层归一化操作;FFN为前馈神经网络,通常包含两个线性变换和一个激活函数,Transformer编码器结构如图7所示。
图卷积网络一般仅由两层卷积层构成,通过汇聚邻居节点的信息来表示自身特征,输入的数据为数据特征和邻接矩阵,每一层的邻接矩阵是相同的。设计了一种平行训练方式,使用三层图卷积层,每一层邻接矩阵对应其数据特征。在训练过程中的第一层图卷积层和第二层图卷积层分别输入基于欧式空间构建的图结构数据和基于多重岩爆判据构建的图结构数据,第三层图卷积层则输入融合后的特征和图结构数据。为了提高模型的表达能力,获得更准确的特征,使用Transformer编码器融合两种图结构数据的特征,获得第三层图卷积层的多尺度输入特征。将前两层中的两种图数据的邻接矩阵均值相加获得第三层输入的邻接矩阵,具体为Adjfused=aAdjcriteria+bAdjEuclidean。其中Adjcriteria为第一层由多重岩爆判据构建的邻接矩阵;AdjEuclidean为第二层由欧式空间距离构建的邻接矩阵;AdjFused为融合后的多尺度图邻接矩阵;ab为比例系数,且a+b=1。经过第三层图卷积训练后得到岩爆预测结果。由于Transformer编码器使用注意力机制提取数据特征,在训练过程中利用Transformer融合岩爆数据不同单一尺度特征,可以更全面地捕捉岩爆数据的信息,在迭代中不断优化下一层的特征和权重,第三层卷积层获得多尺度特征,进而有更好的性能表现。
首先将岩爆数据随机划分,80%岩爆数据为训练数据,20%岩爆数据为测试数据。首先利用多重岩爆判据获取岩爆数据节点之间的连接关系,构建图结构数据。其次将数据标准化,使用欧式空间距离计算各节点之间的距离,选取k个最相似节点构建图结构数据,图结构数据通过邻接矩阵表示。上述两种图结构数据在训练过程中使用两层图卷积层平行训练,从而获得不同尺度的特征嵌入。上述两种特征嵌入经过Transformer编码器进行特征融合,进而获得多尺度特征嵌入,该嵌入作为第三层图卷积层的输入特征。通过将上述两个邻接矩阵均值求和获得融合后的多尺度图结构数据,将多尺度特征嵌入和多尺度图经过第三层图卷积的输入,经过SoftMax获得岩爆等级预测结果,具体过程如图8所示。
在对比实验中,CNN整体准确率为64.54%,DNN算法整体准确率为74.36%,SVM算法整体准确率为66.67%,而本文算法整体准确率为94.87%,优于其他算法,各算法整体准确率如图9所示。
进一步分析各算法对不同岩爆等级的预测结果,具体如图10所示。
其中无岩爆数据中CNN准确率最低为40%,轻微岩爆SVM准确率最低为60%,中等岩爆CNN准确率最低为50%,强岩爆SVM准确率最低为45.5%,提出的算法在轻微岩爆、中等岩爆和强岩爆中均预测正确,准确率为100%,优于其他算法,无岩爆预测准确率为80%,优于其他算法。
(1)欧式空间中岩爆数据的相似结构关系和多重岩爆判据的指标相关约束可以构建不同的图结构数据,设计了一种平行训练方式,通过平行训练充分利用岩爆数据不同的单尺度特征。
(2)模型采用三层图卷积结构,并使每一层的邻接矩阵与其对应的数据特征相匹配。在训练过程中的第一层和第二层分别以基于欧式空间构建的图结构数据和基于多重岩爆判据构建的图结构数据作为输入,而第三层图卷积层则以融合后的多尺度特征和多尺度图结构数据作为输入。这种方法能够充分利用单尺度特征,从而增强数据的表示能力。
(3)利用Transformer融合岩爆数据的不同单尺度特征,能够更全面地捕捉岩爆数据的信息。在迭代过程中,不断优化下一通道的特征和权重,从而提升模型的性能。该方法的训练方式和模型结构使得模型能够充分利用融合后的多尺度特征,进一步提升模型的表达能力和预测性能,实现岩爆等级的预测。
  • 安徽理工大学青年基金(重点项目)(QNZD202202)
  • 淮南市指导性科技计划(2023142)
  • 淮南市指导性科技计划(2023147)
  • 国家自然科学基金面上项目(52374155)
  • 安徽省自然科学基金(面上项目)(2308085MF218)
  • 安徽省高等学校自然科学研究项目(重大项目)(2022AH040113)
  • 安徽省高校中青年教师培养行动项目(YQZD2023035)
  • 安徽理工大学医学专项培育项目(重大项目)(YZ2023H2A007)
  • 合肥综合性国家科学中心大健康研究院职业医学与健康联合研究中心项目(OMH-2023-05)
  • 合肥综合性国家科学中心大健康研究院职业医学与健康联合研究中心项目(OMH-2023-24)
参考文献 引证文献
排序方式:
[1]
张志强, 张康健, 许佳磊, 等. 高地应力硬质砂岩断裂特征及岩爆孕育过程研究[J]. 岩石力学与工程学报, 2024, 43(1): 50-58.
Zhang Zhiqiang, Zhang Kangjian, Xu Jialei, et al. Study on fracture characteristics and rockburst process of hard sandstone underhigh ground stresses[J]. Chinese Journal of Rock Mechanics and Engineering, 2024, 43(1): 50-58.
[2]
李国圣. 构造发育区域地应力模拟及灾害判释研究[J]. 铁道工程学报, 2023, 40(12): 25-29.
Li Guosheng. Study on in-situ stress simulation and disater interpretation in structral development area[j]. Journal of Railway Engineering Society, 2023, 40(12): 25-29.
[3]
周航, 张广泽, 赵晓彦, 等. 西南山区某隧道地应力特征及岩爆危险性评价[J]. 铁道工程学报, 2023, 40(12): 48-54.
Zhou Hang, Zhang Guangze, Zhao Xiaoyan, et al. In-situ stress characteristics and rockburst risk evaluation of a tunnel in the southwest mountains[J]. Journal of Railway Engineering Society, 2023, 40(12): 48-54.
[4]
郭利民. 特长隧道TBM适应性评价方法[J]. 铁道工程学报, 2023, 40(12): 55-60.
Guo Limin. Evaluation method for TBM adaptability of extra long tunnels[J]. Journal of Railway Engineering Society, 2023, 40(12): 55-60.
[5]
刘冬桥, 凌凯, 李娜, 等. 砂岩四面卸载矿柱岩爆实验研究[J]. 岩石力学与工程学报, 2023, 42(11): 3694-3710.
Liu Dongqiao, Ling Kai, Li Na, et al. Experimental study on pillar burst of sandstone under four-faces unloading conditions[J]. Chinese Journal of Rock Mechanics and Engineering, 2023, 42(11): 3694-3710.
[6]
赵斌, 王寅, 赵善坤, 等. 特厚煤层综放工作面矿震诱发机理及防控技术: 以龙王沟煤矿为例[J]. 科学技术与工程, 2023, 23(29): 12451-12457.
Zhao Bin, Wang Yin, Zhao Shankun, et al. Mechanism and prevention and control technology of mine earthquake in fully mechanized top coal caving face in extra thick seam: taking Longwanggou coal mine as an example[J]. Science Technology and Engineering, 2023, 23(29): 12451-12457.
[7]
许文涛, 成云海. 易弹射煤体力学特性及能量演化机制[J]. 煤炭科学技术, 2024, 52(6): 51-66.
Xu Wentao, Cheng Yunhai. Mechanical properties and energy evolution mechanism of coal prone to ejection[J]. Coal Science and Technology, 2024, 52(6): 51-66.
[8]
陈冠甫, 刘晓丽, 黎作尚. 深埋隧道微震数据规律及岩爆特征分析[J]. 地下空间与工程学报, 2023, 19(S1): 353-361.
Chen Guanfu, Liu Xiaoli, Li Zuoshang. Analysis on microseismic data law and rockburst characteristics of deep-buried tunnels[J]. Chinese Journal of Underground Space and Engineering, 2024, 2023, 19(S1): 353-361.
[9]
Sun J, Wang W, Xie L. Predicting short-term rockburst using RF-CRITIC and improved cloud model[J]. Natural Resources Research, 2024, 33(1): 471-494.
[10]
Zhou J, Li X, Shi X. Long-term prediction model of rockburst in underground openings using heuristic algorithms and support vector machines[J]. Safety Science, 2012, 50(4): 629-644.
[11]
Zhou J, Yang P, Peng P, et al. Performance evaluation of rockburst prediction based on PSO-SVM, HHO-SVM, and MFO-SVM hybrid models[J]. Mining, Metallurgy & Exploration, 2023, 40(2): 617-635.
[12]
Tang Z L, Wang X, Xu Q J. Rockburst prediction based on oversampling and objective weighting method[J]. Journal of Tsinghua University (Science and Technology), 2021, 61(6): 543-555.
[13]
Zhou J, Li X, Mitri H S. Classification of rockburst in underground projects: comparison of ten supervised learning methods[J]. Journal of Computing in Civil Engineering, 2016, 30(5): 04016003.
[14]
Xue Y, Li Z, Li S, et al. Prediction of rock burst in underground caverns based on rough set and extensible comprehensive evaluation[J]. Bulletin of Engineering Geology and the Environment, 2019, 78: 417-429.
[15]
Pu Y, Apel D B, Xu H. Rockburst prediction in kimberlite with unsupervised learning method and support vector classifier[J]. Tunnelling and Underground Space Technology, 2019, 90: 12-18.
[16]
Liu R, Ye Y, Hu N, et al. Classified prediction model of rockburst using rough sets-normal cloud[J]. Neural Computing and Applications, 2019, 31: 8185-8193.
[17]
Li T, Li Y, Yang X. Rock burst prediction based on genetic algorithms and extreme learning machine[J]. Journal of Central South University, 2017, 24(9): 2105-2113.
[18]
Liu Q, Xue Y, Li G, et al. Application of KM-SMOTE for rockburst intelligent prediction[J]. Tunnelling and Underground Space Technology, 2023, 138: 105180.
[19]
田睿, 孟海东, 陈世江, 等. 基于深度神经网络的岩爆烈度分级预测[J]. 煤炭学报, 2020, 45(S1): 191-201.
Tian Rui, Meng Haidong, Chen Shijiang, et al. Prediction of intensity classification of rockburst based on deep neural network[J]. Journal of China Coal Society, 2020, 45(S1): 191-201.
[20]
张昱, 张明魁. 基于GD-DNN模型的岩爆烈度等级预测方法与应用[J]. 科学技术与工程, 2023, 23(27): 11835-11840.
Zhang Yu, Zhang Mingkui. Prediction method and application of rockburst intensity grade based on GD-DNN model[J]. Science Technology and Engineering, 2023, 23(27): 11835-11840.
2025年第25卷第5期
PDF下载
350
140
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2402941
  • 接收时间:2024-04-22
  • 首发时间:2025-07-29
  • 出版时间:2025-02-18
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-04-22
  • 修回日期:2024-11-19
基金
安徽理工大学青年基金(重点项目)(QNZD202202)
淮南市指导性科技计划(2023142)
淮南市指导性科技计划(2023147)
国家自然科学基金面上项目(52374155)
安徽省自然科学基金(面上项目)(2308085MF218)
安徽省高等学校自然科学研究项目(重大项目)(2022AH040113)
安徽省高校中青年教师培养行动项目(YQZD2023035)
安徽理工大学医学专项培育项目(重大项目)(YZ2023H2A007)
合肥综合性国家科学中心大健康研究院职业医学与健康联合研究中心项目(OMH-2023-05)
合肥综合性国家科学中心大健康研究院职业医学与健康联合研究中心项目(OMH-2023-24)
作者信息
    1 安徽理工大学计算机科学与工程学院, 淮南 232001
    2 安徽理工大学机械工程学院, 淮南 232001

通讯作者:

*朱颜敏(1988—),女,汉族,山东泰安人,博士,讲师。研究方向:模式识别、岩爆预测等。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2402941
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

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

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