Article(id=1207343638288376680, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1207343627223802520, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2404440, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1718294400000, receivedDateStr=2024-06-14, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1765782754727, onlineDateStr=2025-12-15, pubDate=1750176000000, pubDateStr=2025-06-18, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1765782754727, onlineIssueDateStr=2025-12-15, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1765782754727, creator=13701087609, updateTime=1765782754727, updator=13701087609, issue=Issue{id=1207343627223802520, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='17', pageStart='7023', pageEnd='7453', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1765782752085, creator=13701087609, updateTime=1765783816840, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1207348093192872694, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1207343627223802520, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1207348093192872695, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1207343627223802520, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=7132, endPage=7141, ext={EN=ArticleExt(id=1207343649399087554, articleId=1207343638288376680, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Logging Curve Prediction Based on Modal Decomposition Fused with Machine Learning, columnId=1207343632848364254, journalTitle=Science Technology and Engineering, columnName=Papers-Petroleum and Natural Gas Industry, runingTitle=null, highlight=null, articleAbstract=

Logging data constitutes the basis for oil and gas field development and evaluation. However, in actual mining, factors like poor wellbore stability and equipment failure give rise to the distortion or loss of logging data. A prediction model based on variational mode decomposition (VMD) was proposed to address the issues of unstable and inaccurate results in existing prediction models. The model combines convolutional neural networks (CNN), bidirectional long short term memory (Bi-LSTM), and attention mechanism to predict missing sections in well logging curves. With logging sequence data as input, the VMD algorithm was employed to decompose the sequence into a series of amplitude-modulated and frequency-modulated signal subsequences. The features were extracted by the CNN network and trained by the Bi-LSTM network. During training, the Attention mechanism was utilized to learn the importance weight of each time step dynamically. Finally, the predicted value of the logging curve was outputted. The method was applied to predict logging curves in the Biyang Block of Henan Province and compared with other common machine learning prediction models. The results show that the application effect of the CNN-BiLSTM-Att model improved based on VMD is remarkable, with an error of only the order of 10-3 and a prediction accuracy of 92.02%. The research results provide new ideas for accurate prediction of logging curves.

, correspAuthors=Xian-kang XIN, 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=Xue-fei CHEN, Xian-kang XIN, Gao-ming YU, Yan-dong HU, Wu DENG, Yi-lin LIU), CN=ArticleExt(id=1207343655258530742, articleId=1207343638288376680, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于模态分解融合机器学习的测井曲线预测, columnId=1156262729603207500, journalTitle=科学技术与工程, columnName=论文·石油、天然气工业, runingTitle=null, highlight=null, articleAbstract=

测井数据是油气田开发和评价的基础,然而实际开采过程中因井壁稳定性不佳、设备故障等因素导致测井数据的失真或缺失,针对现有预测模型结果不稳定、精度不高等问题,提出一种基于变分模态分解(variational mode decomposition, VMD)改进的由卷积神经网络(convolutional neural networks, CNN)、双向长短期记忆网络(bidirectional long short-term memory, Bi-LSTM)与注意力机制Attention组合的预测模型对测井曲线缺失段进行预测。以测井序列数据作为输入,利用VMD算法将测井序列分解成一系列调幅调频信号子序列;通过CNN网络提取测井序列的特征并利用Bi-LSTM网络进行训练,训练过程使用Attention机制来动态地学习每个时间步的重要性权重;最后输出测井曲线预测值。将该方法应用于河南泌阳区块测井曲线预测,并与其他常用机器学习预测模型进行对比分析,结果显示,基于VMD改进的CNN-BiLSTM-Att模型的测井曲线预测方法应用效果显著,误差仅10-3数量级,预测精度可达92.02%,研究成果为测井曲线的准确预测提供了新思路。

, correspAuthors=辛显康, authorNote=null, correspAuthorsNote=
*辛显康(1986—),男,汉族,山东汶上人,博士,副教授。研究方向:数值模拟。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=Q1zsO9ndyVFoJLB574wvQw==, magXml=VY5DaGFotw63018Qsp/CKQ==, pdfUrl=null, pdf=E7pC+135e/JivjkY4w992g==, pdfFileSize=14499266, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=lCYhWmzcy0edewxN6VpqXA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=cY2pGl/94g0xgHGRA5eh4g==, mapNumber=null, authorCompany=null, fund=null, authors=

陈雪菲(1999—),女,汉族,陕西西安人,硕士研究生。研究方向:油气田开发,人工智能。E-mail:

, authorsList=陈雪菲, 辛显康, 喻高明, 胡砚东, 邓悟, 刘怡麟)}, authors=[Author(id=1207768402702209248, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=cynthia14fei@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1207768402849009890, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, authorId=1207768402702209248, language=EN, stringName=Xue-fei CHEN, firstName=Xue-fei, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Petroleum Engineering, Yangtze University, Wuhan 430100, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1207768402928701669, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, authorId=1207768402702209248, language=CN, stringName=陈雪菲, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=长江大学石油工程学院, 武汉 430100, bio={"content":"

陈雪菲(1999—),女,汉族,陕西西安人,硕士研究生。研究方向:油气田开发,人工智能。E-mail:

"}, bioImg=null, bioContent=

陈雪菲(1999—),女,汉族,陕西西安人,硕士研究生。研究方向:油气田开发,人工智能。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1207768402584768729, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, xref=null, ext=[AuthorCompanyExt(id=1207768402593157338, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, companyId=1207768402584768729, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Petroleum Engineering, Yangtze University, Wuhan 430100, China), AuthorCompanyExt(id=1207768402605740251, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, companyId=1207768402584768729, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=长江大学石油工程学院, 武汉 430100)])]), Author(id=1207768403058725096, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=xinxk@yangtzeu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1207768403146805486, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, authorId=1207768403058725096, language=EN, stringName=Xian-kang XIN, firstName=Xian-kang, middleName=null, lastName=XIN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=College of Petroleum Engineering, Yangtze University, Wuhan 430100, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1207768403234885877, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, authorId=1207768403058725096, language=CN, stringName=辛显康, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=长江大学石油工程学院, 武汉 430100, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1207768402584768729, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, xref=null, ext=[AuthorCompanyExt(id=1207768402593157338, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, companyId=1207768402584768729, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Petroleum Engineering, Yangtze University, Wuhan 430100, China), AuthorCompanyExt(id=1207768402605740251, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, companyId=1207768402584768729, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=长江大学石油工程学院, 武汉 430100)])]), Author(id=1207768403318771962, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, orderNo=2, 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=1207768403406852351, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, authorId=1207768403318771962, language=EN, stringName=Gao-ming YU, firstName=Gao-ming, middleName=null, lastName=YU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Petroleum Engineering, Yangtze University, Wuhan 430100, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1207768403473961221, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, authorId=1207768403318771962, language=CN, stringName=喻高明, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=长江大学石油工程学院, 武汉 430100, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1207768402584768729, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, xref=null, ext=[AuthorCompanyExt(id=1207768402593157338, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, companyId=1207768402584768729, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Petroleum Engineering, Yangtze University, Wuhan 430100, China), AuthorCompanyExt(id=1207768402605740251, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, companyId=1207768402584768729, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=长江大学石油工程学院, 武汉 430100)])]), Author(id=1207768403557847308, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, 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=1207768403645927697, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, authorId=1207768403557847308, language=EN, stringName=Yan-dong HU, firstName=Yan-dong, middleName=null, lastName=HU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Petroleum Engineering, Yangtze University, Wuhan 430100, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1207768403725619477, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, authorId=1207768403557847308, language=CN, stringName=胡砚东, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=长江大学石油工程学院, 武汉 430100, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1207768402584768729, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, xref=null, ext=[AuthorCompanyExt(id=1207768402593157338, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, companyId=1207768402584768729, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Petroleum Engineering, Yangtze University, Wuhan 430100, China), AuthorCompanyExt(id=1207768402605740251, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, companyId=1207768402584768729, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=长江大学石油工程学院, 武汉 430100)])]), Author(id=1207768403843059996, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, orderNo=4, 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=1207768403935334690, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, authorId=1207768403843059996, language=EN, stringName=Wu DENG, firstName=Wu, middleName=null, lastName=DENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Petroleum Engineering, Yangtze University, Wuhan 430100, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1207768404073746728, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, authorId=1207768403843059996, language=CN, stringName=邓悟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=长江大学石油工程学院, 武汉 430100, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1207768402584768729, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, xref=null, ext=[AuthorCompanyExt(id=1207768402593157338, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, companyId=1207768402584768729, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Petroleum Engineering, Yangtze University, Wuhan 430100, China), AuthorCompanyExt(id=1207768402605740251, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, companyId=1207768402584768729, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=长江大学石油工程学院, 武汉 430100)])]), Author(id=1207768404153438511, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, orderNo=5, 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=1207768404321210678, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, authorId=1207768404153438511, language=EN, stringName=Yi-lin LIU, firstName=Yi-lin, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Petroleum Engineering, Yangtze University, Wuhan 430100, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1207768404392513850, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, authorId=1207768404153438511, language=CN, stringName=刘怡麟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=长江大学石油工程学院, 武汉 430100, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1207768402584768729, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, xref=null, ext=[AuthorCompanyExt(id=1207768402593157338, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, companyId=1207768402584768729, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Petroleum Engineering, Yangtze University, Wuhan 430100, China), AuthorCompanyExt(id=1207768402605740251, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, companyId=1207768402584768729, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=长江大学石油工程学院, 武汉 430100)])])], keywords=[Keyword(id=1207768404593840456, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=EN, orderNo=1, keyword=logging evaluation), Keyword(id=1207768404694503758, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=EN, orderNo=2, keyword=curve prediction), Keyword(id=1207768404795167058, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=EN, orderNo=3, keyword=variational mode decomposition), Keyword(id=1207768404887441749, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=EN, orderNo=4, keyword=convolutional neural networks), Keyword(id=1207768405013270878, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=EN, orderNo=5, keyword=bidirectional long short-term memory networks), Keyword(id=1207768405105545574, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=EN, orderNo=6, keyword=attention mechanism), Keyword(id=1207768405185237355, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=CN, orderNo=1, keyword=测井评价), Keyword(id=1207768405306872179, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=CN, orderNo=2, keyword=曲线预测), Keyword(id=1207768405411729787, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=CN, orderNo=3, keyword=变分模态分解), Keyword(id=1207768405516587394, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=CN, orderNo=4, keyword=卷积神经网络), Keyword(id=1207768405608862089, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=CN, orderNo=5, keyword=双向长短时记忆网络), Keyword(id=1207768405671776654, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=CN, orderNo=6, keyword=注意力机制)], refs=[Reference(id=1207768409811554877, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2022, volume=32, issue=6, pageStart=198, pageEnd=202, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=尚福华, 卢玉莹, 曹茂俊, journalName=计算机技术与发展, refType=null, unstructuredReference=尚福华, 卢玉莹, 曹茂俊. 基于改进LSTM神经网络的测井曲线重构方法[J]. 计算机技术与发展, 2022, 32(6): 198-202., articleTitle=基于改进LSTM神经网络的测井曲线重构方法, refAbstract=null), Reference(id=1207768409928995392, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2022, volume=32, issue=6, pageStart=198, pageEnd=202, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Shang Fuhua, Lu Yuying, Cao Maojun, journalName=null, refType=null, unstructuredReference=Shang Fuhua, Lu Yuying, Cao Maojun. Well logging curve reconstruction method based on improved LSTM neural network[J]. 2022, 32(6): 198-202., articleTitle=Well logging curve reconstruction method based on improved LSTM neural network, refAbstract=null), Reference(id=1207768410025464390, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=9, pageStart=38, pageEnd=54, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=范翔宇, 孟凡, 邓娟, journalName=天然气工业, refType=null, unstructuredReference=范翔宇, 孟凡, 邓娟, 等. 基于自动机器学习的测井曲线重构技术[J]. 天然气工业, 2024, 44(9): 38-54., articleTitle=基于自动机器学习的测井曲线重构技术, refAbstract=null), Reference(id=1207768410105156168, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=9, pageStart=38, pageEnd=54, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Fan Xiangyu, Meng Fan, Deng Juan, journalName=Natural Gas Industry, refType=null, unstructuredReference=Fan Xiangyu, Meng Fan, Deng Juan, et al. Logging curve reconstruction technique based on automatic machine learning[J]. Natural Gas Industry, 2024, 44(9): 38-54., articleTitle=Logging curve reconstruction technique based on automatic machine learning, refAbstract=null), Reference(id=1207768410222596683, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2020, volume=55, issue=3, pageStart=510, pageEnd=520, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=王俊, 曹俊兴, 尤加春, journalName=石油地球物理勘探, refType=null, unstructuredReference=王俊, 曹俊兴, 尤加春. 基于GRU神经网络的测井曲线重构[J]. 石油地球物理勘探, 2020, 55(3): 510-520., articleTitle=基于GRU神经网络的测井曲线重构, refAbstract=null), Reference(id=1207768411476693583, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2020, volume=55, issue=3, pageStart=510, pageEnd=520, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=Wang Jun, Cao Junxing, You Jiachun, journalName=Oil Geophysical Prospecting, refType=null, unstructuredReference=Wang Jun, Cao Junxing, You Jiachun. Reconstruction of logging traces based on GRU neural network[J]. Oil Geophysical Prospecting, 2020, 55(3): 510-520., articleTitle=Reconstruction of logging traces based on GRU neural network, refAbstract=null), Reference(id=1207768411577356882, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2025, volume=35, issue=2, pageStart=183, pageEnd=190, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=曹茂俊, 赵宇杰, journalName=计算机技术与发展, refType=null, unstructuredReference=曹茂俊, 赵宇杰. 一种基于预训练语言模型XLNet的测井曲线重构方法[J]. 计算机技术与发展, 2025, 35(2): 183-190., articleTitle=一种基于预训练语言模型XLNet的测井曲线重构方法, refAbstract=null), Reference(id=1207768411678020182, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2025, volume=35, issue=2, pageStart=183, pageEnd=190, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=Cao Maojun, Zhao Yujie, journalName=Computer Technology and Development, refType=null, unstructuredReference=Cao Maojun, Zhao Yujie. A method for logging curve reconstruction based on pre-trained language model XLNet[J]. Computer Technology and Development, 2025, 35(2): 183-190., articleTitle=A method for logging curve reconstruction based on pre-trained language model XLNet, refAbstract=null), Reference(id=1207768411778683481, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=胡家琦, journalName=基于深度学习的测井曲线预测和储层识别方法, refType=null, unstructuredReference=胡家琦. 基于深度学习的测井曲线预测和储层识别方法[D]. 西安: 陕西科技大学, 2020., articleTitle=null, refAbstract=null), Reference(id=1207768411883541086, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=Hu Jiaqi, journalName=Logging curve prediction and reservoir identification method based on deep learning, refType=null, unstructuredReference=Hu Jiaqi. Logging curve prediction and reservoir identification method based on deep learning[D]. Xi'an: Shaanxi University of Science and Technology, 2020., articleTitle=null, refAbstract=null), Reference(id=1207768411980010081, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=李小东, journalName=基于测井数据的储层参数预测, refType=null, unstructuredReference=李小东. 基于测井数据的储层参数预测[D]. 大庆: 东北石油大学, 2021., articleTitle=null, refAbstract=null), Reference(id=1207768412059701861, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=11, authorNames=Li Xiaodong, journalName=Prediction of reservoir parameters based on logging data, refType=null, unstructuredReference=Li Xiaodong. Prediction of reservoir parameters based on logging data[D]. Daqing: Northeast Petroleum University, 2021., articleTitle=null, refAbstract=null), Reference(id=1207768412135199335, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2021, volume=45, issue=4, pageStart=345, pageEnd=356, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=王华, 张雨顺, journalName=测井技术, refType=null, unstructuredReference=王华, 张雨顺. 测井资料人工智能处理解释的现状及展望[J]. 测井技术, 2021, 45(4): 345-356., articleTitle=测井资料人工智能处理解释的现状及展望, refAbstract=null), Reference(id=1207768412214891115, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2021, volume=45, issue=4, pageStart=345, pageEnd=356, url=null, language=null, rfNumber=[7], rfOrder=13, authorNames=Wang Hua, Zhang Yushun, journalName=Well Logging Technology, refType=null, unstructuredReference=Wang Hua, Zhang Yushun. Research status and prospect of artificial intelligence in logging data processing and interpretation[J]. Well Logging Technology, 2021, 45(4): 345-356., articleTitle=Research status and prospect of artificial intelligence in logging data processing and interpretation, refAbstract=null), Reference(id=1207768412319748718, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=19, pageStart=8045, pageEnd=8051, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=张亮, 党海龙, 刘庆海, journalName=科学技术与工程, refType=null, unstructuredReference=张亮, 党海龙, 刘庆海, 等. 考虑地质分层约束的长短期记忆循环神经网络测井曲线重构[J]. 科学技术与工程, 2024, 24(19): 8045-8051., articleTitle=考虑地质分层约束的长短期记忆循环神经网络测井曲线重构, refAbstract=null), Reference(id=1207768412420412021, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=19, pageStart=8045, pageEnd=8051, url=null, language=null, rfNumber=[8], rfOrder=15, authorNames=Zhang Liang, Dang Hailong, Liu Qinghai, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Zhang Liang, Dang Hailong, Liu Qinghai, et al. Reconstruction of logging curves with long and short-term memory recurrent neural network considering geological stratification constraints[J]. Science Technology and Engineering, 2024, 24(19): 8045-8051., articleTitle=Reconstruction of logging curves with long and short-term memory recurrent neural network considering geological stratification constraints, refAbstract=null), Reference(id=1207768412500103799, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2023, volume=35, issue=6, pageStart=43, pageEnd=50, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=牛聪, 王建花, 邬蒙蒙, journalName=中国海上油气, refType=null, unstructuredReference=牛聪, 王建花, 邬蒙蒙, 等. 基于改进的随机森林算法的井曲线填补研究及应用[J]. 中国海上油气, 2023, 35(6): 43-50., articleTitle=基于改进的随机森林算法的井曲线填补研究及应用, refAbstract=null), Reference(id=1207768412676264573, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2023, volume=35, issue=6, pageStart=43, pageEnd=50, url=null, language=null, rfNumber=[9], rfOrder=17, authorNames=Niu Cong, Wang Jianhua, Wu Mengmeng, journalName=China Offshore Oil and Gas, refType=null, unstructuredReference=Niu Cong, Wang Jianhua, Wu Mengmeng, et al. Research and application of well curve filling based on improved random forest algorithm[J]. China Offshore Oil and Gas, 2023, 35(6): 43-50., articleTitle=Research and application of well curve filling based on improved random forest algorithm, refAbstract=null), Reference(id=1207768412760150658, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2023, volume=30, issue=12, pageStart=86, pageEnd=88, url=null, language=null, rfNumber=[10], rfOrder=18, authorNames=芦升彦, journalName=技术与市场, refType=null, unstructuredReference=芦升彦. 基于多层感知器神经网络的测井曲线重构方法研究[J]. 技术与市场, 2023, 30(12): 86-88, 92., articleTitle=基于多层感知器神经网络的测井曲线重构方法研究, refAbstract=null), Reference(id=1207768412852425348, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2023, volume=30, issue=12, pageStart=86, pageEnd=88, url=null, language=null, rfNumber=[10], rfOrder=19, authorNames=Lu Shengyan, journalName=Technology and Market, refType=null, unstructuredReference=Lu Shengyan. Research on logging curve reconstruction method based on multilayer perceptron neural network[J]. Technology and Market, 2023, 30(12): 86-88, 92., articleTitle=Research on logging curve reconstruction method based on multilayer perceptron neural network, refAbstract=null), Reference(id=1207768412940505733, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=20, authorNames=魏佳明, journalName=机器学习在储层参数预测中的应用研究, refType=null, unstructuredReference=魏佳明. 机器学习在储层参数预测中的应用研究[D]. 西安: 西安石油大学, 2019., articleTitle=null, refAbstract=null), Reference(id=1207768413024391816, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=21, authorNames=Wei Jiaming, journalName=Research on the application of machine learning in reservoir parameter prediction, refType=null, unstructuredReference=Wei Jiaming. Research on the application of machine learning in reservoir parameter prediction[D]. Xi'an: Xi'an Shiyou University, 2019., articleTitle=null, refAbstract=null), Reference(id=1207768413133443723, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2022, volume=39, issue=2, pageStart=40, pageEnd=44, url=null, language=null, rfNumber=[12], rfOrder=22, authorNames=方娜, 余俊杰, 李俊晓, journalName=计算机仿真, refType=null, unstructuredReference=方娜, 余俊杰, 李俊晓, 等. 基于CNN-BiGRU-Attention的短期电力负荷预测[J]. 计算机仿真, 2022, 39(2): 40-44, 82., articleTitle=基于CNN-BiGRU-Attention的短期电力负荷预测, refAbstract=null), Reference(id=1207768413229912719, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2022, volume=39, issue=2, pageStart=40, pageEnd=44, url=null, language=null, rfNumber=[12], rfOrder=23, authorNames=Fang Na, Yu Junjie, Li Junxiao, journalName=Computer Simulation, refType=null, unstructuredReference=Fang Na, Yu Junjie, Li Junxiao, et al. Short-term power load forecasting based on CNN-BiGRU-Attention[J]. Computer Simulation, 2022, 39(2): 40-44, 82., articleTitle=Short-term power load forecasting based on CNN-BiGRU-Attention, refAbstract=null), Reference(id=1207768413288632978, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2018, volume=8, issue=7, pageStart=517, pageEnd=525, url=null, language=null, rfNumber=[13], rfOrder=24, authorNames=Thabet S, Thabit T H, journalName=International Journal of Scientific and Research Publications, refType=null, unstructuredReference=Thabet S, Thabit T H. CFD simulation of the airflow around a car model (Ahmed body)[J]. International Journal of Scientific and Research Publications, 2018, 8(7): 517-525., articleTitle=CFD simulation of the airflow around a car model (Ahmed body), refAbstract=null), Reference(id=1207768413380907671, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2019, volume=26, issue=5, pageStart=73, pageEnd=78, url=null, language=null, rfNumber=[14], rfOrder=25, authorNames=宋辉, 陈伟, 李谋杰, journalName=油气地质与采收率, refType=null, unstructuredReference=宋辉, 陈伟, 李谋杰, 等. 基于卷积门控循环单元网络的储层参数预测方法[J]. 油气地质与采收率, 2019, 26(5): 73-78., articleTitle=基于卷积门控循环单元网络的储层参数预测方法, refAbstract=null), Reference(id=1207768413468988058, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2019, volume=26, issue=5, pageStart=73, pageEnd=78, url=null, language=null, rfNumber=[14], rfOrder=26, authorNames=Song Hui, Chen Wei, Li Moujie, journalName=Petroleum Geology and Recovery Efficiency, refType=null, unstructuredReference=Song Hui, Chen Wei, Li Moujie, et al. A method to predict reservoir parameters based on convolutional neural network-gated recurrent unit(CNN-GRU)[J]. Petroleum Geology and Recovery Efficiency, 2019, 26(5): 73-78., articleTitle=A method to predict reservoir parameters based on convolutional neural network-gated recurrent unit(CNN-GRU), refAbstract=null), Reference(id=1207768413569651359, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=1, pageEnd=15, url=http://kns.cnki.net/kcms/detail/11.2982.P.20240905.1408.004.html, language=null, rfNumber=[15], rfOrder=27, authorNames=null, journalName=地球物理学进展, refType=null, unstructuredReference=基于多头注意力机制的TCN-BiGRU密度测井曲线重构方法[J/OL]. 地球物理学进展, 1-15[2025-03-14]. http://kns.cnki.net/kcms/detail/11.2982.P.20240905.1408.004.html., articleTitle=基于多头注意力机制的TCN-BiGRU密度测井曲线重构方法, refAbstract=null), Reference(id=1207768413661926049, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=1, pageEnd=15, url=http://kns.cnki.net/kcms/detail/11.2982.P.20240905.1408.004.html, language=null, rfNumber=[15], rfOrder=28, authorNames=Wang Huanhuan, Zhao Bin, Liu Jianxin, journalName=Advances in Geophysics, refType=null, unstructuredReference=Wang Huanhuan, Zhao Bin, Liu Jianxin, et al. TCN-BiGRU density logging curve reconstruction method based on multi-attention mechanism[J/OL]. Advances in Geophysics, 1-15[2025-03-14]. http://kns.cnki.net/kcms/detail/11.2982.P.20240905.1408.004.html., articleTitle=TCN-BiGRU density logging curve reconstruction method based on multi-attention mechanism, refAbstract=null), Reference(id=1207768413745812133, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2020, volume=44, issue=2, pageStart=445, pageEnd=453, url=null, language=null, rfNumber=[16], rfOrder=29, authorNames=殷豪, 欧祖宏, 陈德, journalName=电网技术, refType=null, unstructuredReference=殷豪, 欧祖宏, 陈德, 等. 基于二次模式分解和级联式深度学习的超短期风电功率预测[J]. 电网技术, 2020, 44(2): 445-453., articleTitle=基于二次模式分解和级联式深度学习的超短期风电功率预测, refAbstract=null), Reference(id=1207768413833892521, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2020, volume=44, issue=2, pageStart=445, pageEnd=453, url=null, language=null, rfNumber=[16], rfOrder=30, authorNames=Yin Hao, Ou Zuhong, Chen De, journalName=Power System Technology, refType=null, unstructuredReference=Yin Hao, Ou Zuhong, Chen De, et al. Ultra-short-term wind power prediction based on two-layer mode decomposition and cascaded deep learning[J]. Power System Technology, 2020, 44(2): 445-453., articleTitle=Ultra-short-term wind power prediction based on two-layer mode decomposition and cascaded deep learning, refAbstract=null), Reference(id=1207768413921972910, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2020, volume=213, issue=null, pageStart=112869, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=31, authorNames=Sinvaldo R M, Ramon Gomes da S, Viviana C M, journalName=Energy Conversion and Management, refType=null, unstructuredReference=Sinvaldo R M, Ramon Gomes da S, Viviana C M, et al. Multi-step wind speed forecasting based on hybrid multi-stage decomposition model and long short-term memory neural network[J]. Energy Conversion and Management, 2020, 213: 112869., articleTitle=Multi-step wind speed forecasting based on hybrid multi-stage decomposition model and long short-term memory neural network, refAbstract=null), Reference(id=1207768413993276080, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2020, volume=207, issue=null, pageStart=118294, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=32, authorNames=Sun W, Huang C C, journalName=Energy, refType=null, unstructuredReference=Sun W, Huang C C, A novel carbon price prediction model combines the secondary decomposition algorithm and the long short-term memory network[J]. Energy, 2020, 207: 118294., articleTitle=A novel carbon price prediction model combines the secondary decomposition algorithm and the long short-term memory network, refAbstract=null), Reference(id=1207768414068773558, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2019, volume=84, issue=null, pageStart=105739, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=33, authorNames=Zhu Q, Zhang F, Liu S, journalName=Applied Soft Computing Journal, refType=null, unstructuredReference=Zhu Q, Zhang F, Liu S, et al. A hybrid VMD-BiGRU model for rubber futures time series forecasting[J]. Applied Soft Computing Journal, 2019, 84: 105739., articleTitle=A hybrid VMD-BiGRU model for rubber futures time series forecasting, refAbstract=null), Reference(id=1207768414177825466, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2014, volume=62, issue=3, pageStart=531, pageEnd=544, url=null, language=null, rfNumber=[20], rfOrder=34, authorNames=Dragomiretskiy K, Zosso D, journalName=IEEE Transactions on Signal Processing, refType=null, unstructuredReference=Dragomiretskiy K, Zosso D. Variational modedecomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544., articleTitle=Variational modedecomposition, refAbstract=null), Reference(id=1207768414282683071, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2019, volume=42, issue=9, pageStart=107, pageEnd=111, url=null, language=null, rfNumber=[21], rfOrder=35, authorNames=吕宏政, 陈仁文, 张祥, journalName=电子测量技术, refType=null, unstructuredReference=吕宏政, 陈仁文, 张祥, 等. 基于VMD交叉样本嫡的旋翼桨叶故障诊断方法[J]. 电子测量技术, 2019, 42 (9): 107-111., articleTitle=基于VMD交叉样本嫡的旋翼桨叶故障诊断方法, refAbstract=null), Reference(id=1207768414366569155, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2019, volume=42, issue=9, pageStart=107, pageEnd=111, url=null, language=null, rfNumber=[21], rfOrder=36, authorNames=Lue Hongzheng, Chen Renwen, Zhang Xiang, journalName=Electronic Measurement Technology, refType=null, unstructuredReference=Lue Hongzheng, Chen Renwen, Zhang Xiang, et al. Fault diagnosis method of rotor blade based on VMD and cross-sample entropy[J]. Electronic Measurement Technology, 2019, 42 (9): 107-111., articleTitle=Fault diagnosis method of rotor blade based on VMD and cross-sample entropy, refAbstract=null), Reference(id=1207768414471426760, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=37, authorNames=陈云天, journalName=基于机器学习的测井曲线补全与生成研究, refType=null, unstructuredReference=陈云天. 基于机器学习的测井曲线补全与生成研究[D]. 北京: 北京大学, 2020., articleTitle=null, refAbstract=null), Reference(id=1207768414580478667, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=38, authorNames=Chen Yuntian, journalName=Research on well log completion and generation based on machine learning, refType=null, unstructuredReference=Chen Yuntian. Research on well log completion and generation based on machine learning[D]. Beijing: Peking University, 2020., articleTitle=null, refAbstract=null), Reference(id=1207768414676947663, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=39, authorNames=隋金城, journalName=基于LSTM神经网络的股票预测研究, refType=null, unstructuredReference=隋金城. 基于LSTM神经网络的股票预测研究[D]. 青岛: 青岛科技大学, 2020., articleTitle=null, refAbstract=null), Reference(id=1207768414765028052, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=40, authorNames=Sui Jincheng, journalName=Research on stock prediction based on LSTM neural network, refType=null, unstructuredReference=Sui Jincheng. Research on stock prediction based on LSTM neural network[D]. Qingdao: Qingdao University of Science and Technology, 2020., articleTitle=null, refAbstract=null), Reference(id=1207768415515808470, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=41, authorNames=陈凯勋, journalName=基于注意力机制的短时交通流速度预测模型研究, refType=null, unstructuredReference=陈凯勋. 基于注意力机制的短时交通流速度预测模型研究[D]. 广州: 华南理工大学, 2019., articleTitle=null, refAbstract=null), Reference(id=1207768415599694551, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=42, authorNames=Chen Kaixun, journalName=Research on short-term traffic flow velocity prediction model based on attention mechanism, refType=null, unstructuredReference=Chen Kaixun. Research on short-term traffic flow velocity prediction model based on attention mechanism[D]. Guangzhou: South China University of Technology, 2019., articleTitle=null, refAbstract=null), Reference(id=1207768415691969247, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=2627, pageEnd=2633, url=null, language=null, rfNumber=[25], rfOrder=43, authorNames=Qin Y, Song D, Cheng H, journalName=Twenty-Sixth International Joint Conference on Artificial Intelligence, refType=null, unstructuredReference=Qin Y, Song D, Cheng H, et al. A dual-stage attention-based recurrent neural network for time series prediction[C]// Twenty-Sixth International Joint Conference on Artificial Intelligence. Melbourne: IEEE, 2017: 2627-2633., articleTitle=A dual-stage attention-based recurrent neural network for time series prediction, refAbstract=null), Reference(id=1207768415796826851, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[26], rfOrder=44, authorNames=郭雅婷, journalName=基于注意力机制的网约车需求短时预测模型研究, refType=null, unstructuredReference=郭雅婷. 基于注意力机制的网约车需求短时预测模型研究[D]. 广州: 华南理工大学, 2020., articleTitle=null, refAbstract=null), Reference(id=1207768415889101543, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[26], rfOrder=45, authorNames=Guo Yating, journalName=Research on short-term prediction model of online car-hailing demand based on attention mechanism, refType=null, unstructuredReference=Guo Yating. Research on short-term prediction model of online car-hailing demand based on attention mechanism[D]. Guangzhou: South China University of Technology, 2020., articleTitle=null, refAbstract=null), Reference(id=1207768415960404713, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2022, volume=57, issue=6, pageStart=1473, pageEnd=1480, url=null, language=null, rfNumber=[27], rfOrder=46, authorNames=周伟, 赵海航, 蒋云凤, journalName=石油地球物理勘探, refType=null, unstructuredReference=周伟, 赵海航, 蒋云凤, 等. 基于串级双向长短时记忆神经网络的测井数据重构[J]. 石油地球物理勘探, 2022, 57(6): 1473-1480., articleTitle=基于串级双向长短时记忆神经网络的测井数据重构, refAbstract=null), Reference(id=1207768416082039530, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, doi=null, pmid=null, pmcid=null, year=2022, volume=57, issue=6, pageStart=1473, pageEnd=1480, url=null, language=null, rfNumber=[27], rfOrder=47, authorNames=Zhou Wei, Zhao Haihang, Jiang Yunfeng, journalName=Oil Geophysical Prospecting, refType=null, unstructuredReference=Zhou Wei, Zhao Haihang, Jiang Yunfeng, et al. Logging data reconstruction based on cascade bidirectional long short-term memory neural network[J]. Oil Geophysical Prospecting, 2022, 57(6): 1473-1480., articleTitle=Logging data reconstruction based on cascade bidirectional long short-term memory neural network, refAbstract=null)], funds=[Fund(id=1207768409555702320, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, awardId=52104020, language=CN, fundingSource=国家自然科学基金青年科学基金(52104020), fundOrder=null, country=null), Fund(id=1207768409622811187, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, awardId=2020CFB377, language=CN, fundingSource=湖北省自然科学基金青年科学基金(2020CFB377), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1207768402584768729, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, xref=null, ext=[AuthorCompanyExt(id=1207768402593157338, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, companyId=1207768402584768729, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Petroleum Engineering, Yangtze University, Wuhan 430100, China), AuthorCompanyExt(id=1207768402605740251, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, companyId=1207768402584768729, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=长江大学石油工程学院, 武汉 430100)])], figs=[ArticleFig(id=1207768406980399518, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=EN, label=Fig.1, caption=The overall framework of the predictive model, figureFileSmall=Owb24M1fupKvIlTsg+jVdw==, figureFileBig=XZHcNY+zFXIsOUUOmBJ/4A==, tableContent=null), ArticleFig(id=1207768407106228645, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=CN, label=图1, caption=预测模型总体框架, figureFileSmall=Owb24M1fupKvIlTsg+jVdw==, figureFileBig=XZHcNY+zFXIsOUUOmBJ/4A==, tableContent=null), ArticleFig(id=1207768407219474860, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=EN, label=Fig.2, caption=The prediction process was based on the CNN-Bi-LSTM-Attention model, figureFileSmall=2981/iGsi3mdT8Ie9WERUA==, figureFileBig=dlm0JwKWpmw4BepR1tEwsQ==, tableContent=null), ArticleFig(id=1207768407286583733, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=CN, label=图2, caption=基于CNN-Bi-LSTM-Attention模型预测流程, figureFileSmall=2981/iGsi3mdT8Ie9WERUA==, figureFileBig=dlm0JwKWpmw4BepR1tEwsQ==, tableContent=null), ArticleFig(id=1207768407370469817, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=EN, label=Fig.3, caption=Schematic diagram of the LSTM model, figureFileSmall=QwplC/rBk1W8NbRJXDaFCA==, figureFileBig=KgYPe5th/daLvvaCwgfDUA==, tableContent=null), ArticleFig(id=1207768407445967295, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=CN, label=图3, caption=LSTM模型示意图, figureFileSmall=QwplC/rBk1W8NbRJXDaFCA==, figureFileBig=KgYPe5th/daLvvaCwgfDUA==, tableContent=null), ArticleFig(id=1207768407521464772, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=EN, label=Fig.4, caption=Schematic diagram of the Bi-LSTM model, figureFileSmall=xeO2/hgdQDXQRP7zyFVdfA==, figureFileBig=ejW3wfkfaKxSBk7K2PXhig==, tableContent=null), ArticleFig(id=1207768407596962251, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=CN, label=图4, caption=Bi-LSTM模型示意图, figureFileSmall=xeO2/hgdQDXQRP7zyFVdfA==, figureFileBig=ejW3wfkfaKxSBk7K2PXhig==, tableContent=null), ArticleFig(id=1207768407697625553, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=EN, label=Fig.5, caption=Weight calculation principle of attention mechanism, figureFileSmall=XKqHoM9V3AOb050B7TukOw==, figureFileBig=U6AkIoBj4d1mimq3BBMHhA==, tableContent=null), ArticleFig(id=1207768407810871765, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=CN, label=图5, caption=注意力机制权值计算原理, figureFileSmall=XKqHoM9V3AOb050B7TukOw==, figureFileBig=U6AkIoBj4d1mimq3BBMHhA==, tableContent=null), ArticleFig(id=1207768407919923676, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=EN, label=Fig.6, caption=VMD decomposed subsequence of the logging sequence, figureFileSmall=fRkM776bg7RMSnAJfim3Og==, figureFileBig=5jD5ca2HXexGe4OpGkZxhg==, tableContent=null), ArticleFig(id=1207768407991226849, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=CN, label=图6, caption=VMD分解的测井序列子序列, figureFileSmall=fRkM776bg7RMSnAJfim3Og==, figureFileBig=5jD5ca2HXexGe4OpGkZxhg==, tableContent=null), ArticleFig(id=1207768408083501543, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=EN, label=Fig.7, caption=VMD exploded renderings, figureFileSmall=nkioPemHic8/QR8XxJW1/w==, figureFileBig=M4X9LdOTgOur6qU3weD+WA==, tableContent=null), ArticleFig(id=1207768408179970538, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=CN, label=图7, caption=VMD分解效果图, figureFileSmall=nkioPemHic8/QR8XxJW1/w==, figureFileBig=M4X9LdOTgOur6qU3weD+WA==, tableContent=null), ArticleFig(id=1207768408255468013, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=EN, label=Fig.8, caption=Correlation coefficient matrix of acoustic time-sensitive parameters, figureFileSmall=HP4wKYPD1N2drXqMmSCgXw==, figureFileBig=CNCOmgV0Reo0WxpFrCyobg==, tableContent=null), ArticleFig(id=1207768408326771186, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=CN, label=图8, caption=声波时差敏感参数相关系数矩阵, figureFileSmall=HP4wKYPD1N2drXqMmSCgXw==, figureFileBig=CNCOmgV0Reo0WxpFrCyobg==, tableContent=null), ArticleFig(id=1207768408398074360, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=EN, label=Fig.9, caption=Descending curve of the loss function during model training, figureFileSmall=2r2bPpZ9uJ1Mo8U3yMMIqg==, figureFileBig=n41VSJOtznh7whC0MWkOVQ==, tableContent=null), ArticleFig(id=1207768408465183227, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=CN, label=图9, caption=模型训练过程损失函数下降曲线, figureFileSmall=2r2bPpZ9uJ1Mo8U3yMMIqg==, figureFileBig=n41VSJOtznh7whC0MWkOVQ==, tableContent=null), ArticleFig(id=1207768408565846527, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=EN, label=Fig.10, caption=Comparison of prediction results of four models, figureFileSmall=+fjkN11KncjvlQB7vNUs8Q==, figureFileBig=qkmrdQXJvp3ODmKKKBrepg==, tableContent=null), ArticleFig(id=1207768408670704130, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=CN, label=图10, caption=4种模型预测结果对比, figureFileSmall=+fjkN11KncjvlQB7vNUs8Q==, figureFileBig=qkmrdQXJvp3ODmKKKBrepg==, tableContent=null), ArticleFig(id=1207768408788144649, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=EN, label=Fig.11, caption=The intersection results of the predicted and measured values of the four models, figureFileSmall=6mlk84NmqKqwK0fJAm8/JA==, figureFileBig=ZvT2BwkcCMFc+4etDVrNrQ==, tableContent=null), ArticleFig(id=1207768408863642123, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=CN, label=图11, caption=4种模型AC曲线预测值与实测值的交会图, figureFileSmall=6mlk84NmqKqwK0fJAm8/JA==, figureFileBig=ZvT2BwkcCMFc+4etDVrNrQ==, tableContent=null), ArticleFig(id=1207768408972694034, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=EN, label=Fig.12, caption=Forecast result logs, figureFileSmall=rIo285lnaM/QFsITW0LIlw==, figureFileBig=zeUNAL+KVG5XBx6Hg9xlmw==, tableContent=null), ArticleFig(id=1207768409035608599, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=CN, label=图12, caption=预测结果测井图, figureFileSmall=rIo285lnaM/QFsITW0LIlw==, figureFileBig=zeUNAL+KVG5XBx6Hg9xlmw==, tableContent=null), ArticleFig(id=1207768409111106075, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=EN, label=Table 1, caption=

Prediction accuracy evaluation table for four models

, figureFileSmall=null, figureFileBig=null, tableContent=
预测模型 MSE R2
CNN 0.021 7 0.813 7
BiLSTM 0.017 2 0.798 0
CNN-BiLSTM-Att 0.007 2 0.906 3
VCBAtt 0.004 5 0.952 6
), ArticleFig(id=1207768409194992161, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=CN, label=表1, caption=

4种模型的预测精度评价表

, figureFileSmall=null, figureFileBig=null, tableContent=
预测模型 MSE R2
CNN 0.021 7 0.813 7
BiLSTM 0.017 2 0.798 0
CNN-BiLSTM-Att 0.007 2 0.906 3
VCBAtt 0.004 5 0.952 6
), ArticleFig(id=1207768409283072552, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=EN, label=Table 2, caption=

Prediction accuracy evaluation table for the two models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 MSE R2
CNN-BiLSTM-Att 0.009 4 0.865 2
VCBAtt 0.006 5 0.920 2
), ArticleFig(id=1207768409379541546, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343638288376680, language=CN, label=表2, caption=

2种模型的预测精度评价表

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 MSE R2
CNN-BiLSTM-Att 0.009 4 0.865 2
VCBAtt 0.006 5 0.920 2
)], 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.1671-1815.2404440, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2404440, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2404440, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2404440, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于模态分解融合机器学习的测井曲线预测
收藏切换
PDF下载
陈雪菲 , 辛显康 * , 喻高明 , 胡砚东 , 邓悟 , 刘怡麟
科学技术与工程 | 论文·石油、天然气工业 2025,25(17): 7132-7141
收起
收藏切换
科学技术与工程 | 论文·石油、天然气工业 2025, 25(17): 7132-7141
基于模态分解融合机器学习的测井曲线预测
全屏
陈雪菲 , 辛显康* , 喻高明, 胡砚东, 邓悟, 刘怡麟
作者信息
  • 长江大学石油工程学院, 武汉 430100
  • 陈雪菲(1999—),女,汉族,陕西西安人,硕士研究生。研究方向:油气田开发,人工智能。E-mail:

通讯作者:

*辛显康(1986—),男,汉族,山东汶上人,博士,副教授。研究方向:数值模拟。E-mail:
Logging Curve Prediction Based on Modal Decomposition Fused with Machine Learning
Xue-fei CHEN , Xian-kang XIN* , Gao-ming YU, Yan-dong HU, Wu DENG, Yi-lin LIU
Affiliations
  • College of Petroleum Engineering, Yangtze University, Wuhan 430100, China
出版时间: 2025-06-18 doi: 10.12404/j.issn.1671-1815.2404440
文章导航
收藏切换

测井数据是油气田开发和评价的基础,然而实际开采过程中因井壁稳定性不佳、设备故障等因素导致测井数据的失真或缺失,针对现有预测模型结果不稳定、精度不高等问题,提出一种基于变分模态分解(variational mode decomposition, VMD)改进的由卷积神经网络(convolutional neural networks, CNN)、双向长短期记忆网络(bidirectional long short-term memory, Bi-LSTM)与注意力机制Attention组合的预测模型对测井曲线缺失段进行预测。以测井序列数据作为输入,利用VMD算法将测井序列分解成一系列调幅调频信号子序列;通过CNN网络提取测井序列的特征并利用Bi-LSTM网络进行训练,训练过程使用Attention机制来动态地学习每个时间步的重要性权重;最后输出测井曲线预测值。将该方法应用于河南泌阳区块测井曲线预测,并与其他常用机器学习预测模型进行对比分析,结果显示,基于VMD改进的CNN-BiLSTM-Att模型的测井曲线预测方法应用效果显著,误差仅10-3数量级,预测精度可达92.02%,研究成果为测井曲线的准确预测提供了新思路。

测井评价  /  曲线预测  /  变分模态分解  /  卷积神经网络  /  双向长短时记忆网络  /  注意力机制

Logging data constitutes the basis for oil and gas field development and evaluation. However, in actual mining, factors like poor wellbore stability and equipment failure give rise to the distortion or loss of logging data. A prediction model based on variational mode decomposition (VMD) was proposed to address the issues of unstable and inaccurate results in existing prediction models. The model combines convolutional neural networks (CNN), bidirectional long short term memory (Bi-LSTM), and attention mechanism to predict missing sections in well logging curves. With logging sequence data as input, the VMD algorithm was employed to decompose the sequence into a series of amplitude-modulated and frequency-modulated signal subsequences. The features were extracted by the CNN network and trained by the Bi-LSTM network. During training, the Attention mechanism was utilized to learn the importance weight of each time step dynamically. Finally, the predicted value of the logging curve was outputted. The method was applied to predict logging curves in the Biyang Block of Henan Province and compared with other common machine learning prediction models. The results show that the application effect of the CNN-BiLSTM-Att model improved based on VMD is remarkable, with an error of only the order of 10-3 and a prediction accuracy of 92.02%. The research results provide new ideas for accurate prediction of logging curves.

logging evaluation  /  curve prediction  /  variational mode decomposition  /  convolutional neural networks  /  bidirectional long short-term memory networks  /  attention mechanism
陈雪菲, 辛显康, 喻高明, 胡砚东, 邓悟, 刘怡麟. 基于模态分解融合机器学习的测井曲线预测. 科学技术与工程, 2025 , 25 (17) : 7132 -7141 . DOI: 10.12404/j.issn.1671-1815.2404440
Xue-fei CHEN, Xian-kang XIN, Gao-ming YU, Yan-dong HU, Wu DENG, Yi-lin LIU. Logging Curve Prediction Based on Modal Decomposition Fused with Machine Learning[J]. Science Technology and Engineering, 2025 , 25 (17) : 7132 -7141 . DOI: 10.12404/j.issn.1671-1815.2404440
测井曲线的适用性和准确性是准确评估储层的基础。在测井过程中,由于井壁稳定性不佳、设备故障或地层条件复杂等原因,导致位于不同深度的多条测井数据失真或缺失,这在一定程度上给测井解释带来了困难,因此预测测井曲线的缺失部分是测井解释的必要过程[1-3]。测井曲线的预测方法可分为基于物理模型和基于数据驱动。基于物理模型的方法是利用地质物理理论构建物理模型,进一步反演得到测井曲线[4-6]。物理模型在构建过程中往往会极度简化地层信息,并且在选择适用于特定地质条件的物理模型过程中易受到人为因素的影响,因此由物理模型反演得到的测井曲线质量难以得到保障[7]。基于数据驱动的方法通过机器学习和统计分析等技术,直接从数据中学习曲线之间的关系并进行预测。数据驱动模型能够处理多维、大规模的测井数据,具有较强的非线性关系建模能力,可最大限度地利用现有地质信息和测井数据,对于复杂的地质条件和曲线预测任务具有优势[8-11]
基于数据驱动的机器学习预测模型主要有单一模型和复合模型。单一模型如卷积神经网络(convolutional neural networks, CNN)、长短期记忆(long short-term memory, LSTM)网络、双向长短时记忆(bidirectional long short-term memory, BiLSTM)网络等。复合模型是对多种模型进行有效组合,有助于结合不同算法的优势,满足项目的实际需要,从而达到更高的预测精度。通常情况下,复合模型的预测精度要高于单一模型[12]。THABETS 等[13]将CNN 和 Bi-LSTM 组合,利用 CNN 提取特征向量并通过 Bi-LSTM 进行双向网络训练,证明了组合模型的最新性能。宋辉等[14]将CNN和循环神经网络相结合,有效地提取了测井数据的特征,提高了储层参数预测的准确性。测井数据受多维输入特征的影响,目前大多数基于CNN和Bi-LSTM融合的方法没有明确地关注每个特征的重要性,因此无法捕捉特征之间的相关性和影响程度。王欢欢等[15]将注意力机制引入到循环神经网络模型,用于密度测井曲线的重构,为进一步提高复合模型的精度提供了有效的思路。引入注意力机制(Attention,Att)机制可以弥补现有方法未考虑特征影响程度的缺陷,优化模型的性能。
由于测井序列具有非平稳性,上述仅着眼于数据预测的模型精度通常不高,因此基于信号分解和数据增强等方法改进的预测模型在实践中得到了广泛应用[16]。经验模态分解(empirical mode decomposition, EMD)、集成经验模态分解(ensemble empirical mode decomposition, EEMD)等算法被认为是数据分解的有效算法,但 EMD 系列算法存在过度分解、模态混叠和计算复杂度高等劣势。变分模态分解(variational mode decomposition, VMD)通过最小化信号的总变分和模式之间的互相关系数来实现分解,能有效处理非平稳和非线性信号,并且能够避免EMD算法中存在的过度分解和模态混叠等问题。国内外学者通过大量实证分析同样证实了VMD模型在挖掘时间序列中隐藏的非线性和非平稳特征方面具有显著优势[17-19]
根据上述分析,现结合变分模态分解、机器学习算法和注意力机制,利用 VMD 对测井序列进行分解,在保留原始序列趋势的基础上分离复杂信号;使用 Bi-LSTM 捕捉测井序列的变化特征,并引入 CNN 和Att 机制增强非平稳性序列的特征提取;建立基于VMD改进的CNN-BiLSTM-Attention测井曲线预测模型,将该方法应用于实际油田测井数据预测过程并分析其适用性和优越性。
地下油气层情况复杂多变,测井数据精度受多种因素影响,完全考虑和收集所有影响因素数据受限,从测井序列变化特征出发,选取油田采集并上传至数据库的测井数据,完成建模分析。设计并实现的基于VMD改进的CNN-Bi-LSTM-Attention模型(以下简称为VCBAtt模型)总体框架如图1所示。
提出VCBAtt预测模型主要设计步骤如下:首先,对原始测井数据进行预处理,删除无效信息,补全缺失值;其次,利用VMD方法将复杂的目标测井序列分解成为N个代表不同频率成分VIMF(vimf1,vimf2,…,vimfn),以降低原始序列的随机波动性,从而使后续预测模型能够更准确地捕捉测井序列变化趋势,对分解得到的VIMF进行归一化处理,确保其在相同的尺度上进行比较和分析;最后,将CNN、Bi-LSTM和Attention机制结合,构建VCBAtt预测模型对VMD分解后的每个信号分量分别进行预测,将N个预测分量重构,以得到最终的预测序列。同时基于均方误差(mean-square error, MSE)和决定系数(r-square, R2)评价提出的VCBAtt模型与对比模型的预测性能。
2014年Dragomiretskiy等[20]提出了变分模态分解算法(VMD),其工作机制是通过数学优化的方式将信号分解成各个模态分量VIMF[21]。这些模态分量贡献了不同的频带和幅度信息,从而可以更好地揭示信号的特征。VMD采用交替方向乘子法对变分模型进行有效优化,使得模型对采样噪声具有更强的鲁棒性。与传统信号分解算法相比,VMD不需要滑动窗口技术,也不受固定频段分析的限制,VMD输出的信号分量具有良好的时频局部性质,更适用于分析非平稳信号。该算法可将单个原始测井序列数据分解为K个中心角频率为的本征模态函数,K为指定的模态分量个数,VMD算法将测井序列的分解问题转化为式(1)结构的变分问题。
$\left\{\begin{array}{l} \min _{\left\{\boldsymbol{u}_{k}\right\},\left|\omega_{k}\right|}\left(\sum_{k=1}^{K}\left\|\partial_{t}\left\{\left[\delta(t)+\frac{\mathrm{j}}{\pi t}\right] \boldsymbol{u}_{k}(t)\right\} \mathrm{e}^{-\mathrm{j} \omega_{k^{t}}}\right\|_{2}^{2}\right) \\ \text { s. t. } \sum_{k=1}^{K} \boldsymbol{u}_{k}=\boldsymbol{f}(t) \end{array}\right.$
式(1)中:δ(t)为单位脉冲函数;f(t)为测井序列数据;uk(t)为原始测井序列分解后第k个模态分量;ωk为各模态分量所对应的中心频率。引入拉格朗日乘子λ和二次惩罚因子α,得到扩展的拉格朗日表达式为
$\begin{array}{l} L\left(\left\{\boldsymbol{u}_{k}\right\},\left\{\omega_{k}\right\}, \lambda\right)= \\ \quad \alpha \sum_{k=1}^{K}\left\|\partial_{t}\left\{\left[\delta(t)+\frac{\mathrm{j}}{\pi t}\right] \boldsymbol{u}_{k}(t)\right\} \mathrm{e}^{-\mathrm{j} \omega_{k} t}\right\|_{2}^{2}+ \\ \quad\left\|\boldsymbol{f}(t)-\sum_{k=1}^{K} \boldsymbol{u}_{k}(t)\right\|_{2}^{2}+\left\langle\lambda(t), \boldsymbol{f}(t)-\sum_{k=1}^{K} \boldsymbol{u}_{k}(t)\right\rangle \end{array}$
式(2)中: ∂t为对时间t的偏微分。采用交替方向乘子法迭代搜索,迭代后的ukωk以及λ的表达式如下。
$\left\{\begin{array}{l} \hat{f}(\omega)-\sum_{i \neq k}^{K} \hat{u}_{i}(\omega)+\hat{\lambda}(\omega) / 2 \\ \hat{u}_{k}^{n+1}(\omega) \leftarrow \frac{1+2 a\left(\omega-\omega_{k}\right)^{2}}{\leftarrow} \\ \hat{\omega}_{k}^{n+1} \leftarrow \frac{\int_{0}^{\infty} \omega\left|\hat{u}_{k}^{n+1}(\omega)\right|^{2} \mathrm{~d} \omega}{\int_{0}^{\infty}\left|\hat{u}_{k}^{n+1}(\omega)\right|^{2} \mathrm{~d} \omega} \\ \hat{\lambda}^{n+1}(\omega) \leftarrow \hat{\lambda}^{n}(\omega)+\gamma\left[\hat{f}(\omega)-\sum_{k=1}^{K} \hat{u}_{k}^{n+1}(\omega)\right] \end{array}\right.$
式(3)中:γ为噪声容限;ω为频率。
VMD分解方法步骤如下。
步骤1 初始化最大迭代次数N${u}_{\mathrm{k}}^{1}$${\omega }_{k}^{1}$λ1
步骤2 根据式(2)、式(3)更新ukωkλ
步骤3 若不满足式(4)且n>N时,则回到步骤2,否则停止迭代。
$\sum_{k=1}^{K}\left\|\hat{\boldsymbol{u}}_{k}^{n+1}-\hat{\boldsymbol{u}}_{k}^{n}\right\|_{2}^{2} /\left\|\hat{\boldsymbol{u}}_{k}^{n}\right\|_{2}^{2}<\varepsilon$
式(4)中:ε为给定精度。经过上述步骤,原始测井序列数据被分解为K个不同频率的子序列。
原始测井序列经过VMD分解后得到的高、低频分量子序列,具有不同频率特征,为此将 CNN、Bi-LSTM 和 Attention 结合,构成 CNN-BiLSTM-Attention 预测模型充分提取由VMD分解得到的子序列的频率特征,结构如图2所示。
CNN的优势主要在于提取局部特征和保留空间结构信息,适合处理静态特征;而Bi-LSTM则擅长建模序列数据中的长期依赖关系,能够捕捉到序列数据的时序信息。使用CNN进行特征提取,弥补Bi-LSTM无法捕获数据空间分量的缺点。CNN中卷积层由多个卷积核组成,通过卷积操作实现特征提取,参数共享和稀疏连接等特性使得CNN能够有效地处理输入中不同位置的局部特征数据,一维卷积公式为
${y}_{t}=\stackrel{K}{\sum _{k=1}}{w}_{k}{x}_{t-k+1}+b$
式(5)中:wk为卷积核;b为偏置;K为数据长度;xt-k+1为输入的数据;yt为输出的特征数据。
LSTM神经网络模型是众多循环神经网络模型(recurrent neural network, RNN)改进模型之一,其交互层记忆区块子网络结构如图3所示,关键门单元包括:输入门、输出门和遗忘门[22]。通过观察LSTM子网络结构数据流向可知,LSTM只能单向处理数据,就测井曲线重构而言,模型无法兼顾当前缺失井段测井序列之前和之后的影响,也无法完全考虑当前井筒曲线之间的相关性,通常会造成模型的预测效果不佳。在实际测井中,取样间隔通常小于0.1 m,然而不同深度地层之间相互作用范围通常为30~50 m,每个测井数据点可辐射到的数据点可达240~400个。这些特点意味着测井曲线预测问题需要考虑双向时空相关性和多层次的影响,解决这种问题,Bi-LSTM更具有适用性和优越性。为此,采用了一个由正向 LSTM 模型和反向 LSTM 模型组成的 Bi-LSTM 网络,正反两向的LSTM输出可以将缺失储层段之前以及之后的储层段信息整合起来,更全面地捕捉测井曲线中时间上的双向依赖关系。Bi-LSTM 由两层 LSTM 网络组成,结构如图4所示。
第一层将左侧即当前缺失测井曲线序列段采样点之前的序列作为初始输入(ht);第二层将右侧作为初始输入,即将当前测井序列采样点之后的序列作为输入(${\stackrel{-}{h}}_{t}$),并在相反方向执行与第一层相同的过程。此时,yt-1ytyt+1为前、后两个LSTM网络共同作用的结果,Bi-LSTM 网络可以完美地解决LSTM网络应用于测井曲线预测过程中只能单向处理数据的局限性。
虽然Bi-LSTM能够捕捉到相对较长范围内的依赖关系,但在处理较长的测井序列时,由于信息在每个时间步都需要经过多次的门控单元传递,可能会导致梯度消失或爆炸的问题,从而限制了其对长期依赖关系的建模能力;在Bi-LSTM中,信息的传递是通过网络内部的隐藏状态进行的,这种顺序传递的方式可能会导致一些重要的信息在传递过程中被模糊化或丢失。为此引入Att机制弥补Bi-LSTM在处理长期序列时的不足,提高模型对长期依赖关系的建模能力和信息传递效率。Att机制中,软注意力机制会充分考虑每个特征输入对输出的影响,对所有输入特征进行加权处理并将其传递给模型进行处理;而硬注意力机制一般会舍弃大部分无关紧要的特征,只保留一个或者极少数重要的特征输入,通常会忽视局部特征对整体的影响,导致模型鲁棒性较差[23-25]。因此考虑将软注意力机制引入模型构建,动态地调整输入的不同部分的注意权重,从而提高模型对输入的关注度和理解能力[26]。Att机制特征权重的计算分为3个阶段,计算原理如图5所示。
部分①中引入注意力打分函数,根据查询向量Q和某个输入特征K使用点积模型计算二者的关联程度Sn
${S}_{n}=\mathrm{Q}{{K}^{\mathrm{T}}}_{n}$
部分②中使用SoftMax对Sn进行归一化处理,计算公式为
${a}_{n}=\mathrm{S}\mathrm{o}\mathrm{f}\mathrm{t}\mathrm{M}\mathrm{a}\mathrm{x}\left({S}_{n}\right)={\mathrm{e}}^{{S}_{n}}/\stackrel{{L}_{x}}{\sum _{j=1}}{\mathrm{e}}^{{S}_{j}}$
部分③将an 与valuen进行加权求和得到注意力值。
$\mathrm{A}\mathrm{t}\mathrm{t}(Q,{S}_{n})=\stackrel{{L}_{x}}{\sum _{j=1}}{a}_{n}\mathrm{v}\mathrm{a}\mathrm{l}\mathrm{u}{\mathrm{e}}_{n}$
式(8)中: Q为查询向量;K为某个输入特征;Sj为索引位置处的关联程度,j∈(1,Lx)为被选择信息的索引位置;an为选择第n个输入向量的概率;valuen为权重系数。利用Att 机制自主学习特征参数与预测数据之间的关联,并与Bi-LSTM 结合,打破了传统阈值设定的限制,同时可以增强 Bi-LSTM中重要时间步的时空关联,进一步降低模型预测误差。
通过 Python 编程建立VCBAtt模型,首先利用VMD算法对目标输出测井信号进行分解并进行归一化处理,将处理后的输入和输出样本数据输入至CNN-BiLSTM-Attention网络模型,不断调试模型参数得到预测值,最后以MSE和R2作为评估参数对模型进行评估。此外,还采用了单一CNN神经网络、Bi-LSTM神经网络和未经过VMD处理的CNN-BiLSTM-Attention作为基准模型与VCBAtt模型预测结果进行对比。为了验证VCBAtt模型的有效性,选择河南泌阳区块A1井区的测井数据进行验证。
VMD 可将目标测井序列分解为k个具有不同特征的模态函数,为了在保留主要信号信息的同时简化信号处理和分析过程,并能够较好地捕获信号的主要频率成分,选择k= 3 来得到3个频率不同的分量VIMF(如图6所示)。
最终VMD部分分解效果如图7所示,可知,vimf1频率较低,基本上剔除了随机干扰噪声的影响,且继承了原始测井数据的变化趋势,而vimf2和 vimf3数据频率较大,幅值较小,属于平稳的时间序列。VMD有效降低了原始测井序列的非平稳性,有利于后续模型迭代训练速度及预测精确度的提升。
为消除测井数据之间的量纲和尺度范围带来偏差,对输入测井数据以及经过VMD分解过后的信号数据进行归一化处理,公式为
$\overline{x}=\frac{x-{x}_{\mathrm{m}\mathrm{i}\mathrm{n}}}{{x}_{\mathrm{m}\mathrm{a}\mathrm{x}}-{x}_{\mathrm{m}\mathrm{i}\mathrm{n}}}$
式(9)中:xminxmax分别为样本数据的最小值和最大值;$\overline{x}$为归一化后的测井数据,取值0~1。
常用于表征数据特征关联关系的方法中,Pearson系数法适用于检测连续型变量之间的线性关系,Spearman系数法适用于检测非线性关系和异常值较多的数据集,研究采用两者结合的方法来优选测井特征敏感参数[27]。以A1井测井数据为例,从井中获得测井曲线有声波时差(AC)、地层真电阻率(RT)、密度(DEN)、中子(CNL)、自然电位(SP)、深侧向电阻率(RD)、浅侧向电阻率(RS)、自然伽马(GR)和中子孔隙度(NPHI)等10条测井曲线。利用Pearson系数法与Spearman系数法得到的测井参数相关性分析矩阵如图8所示,以声波时差为预测目标测井进行分析,Pearson系数法得出的线性关系中,AC与DEN、CNL、GR、RS、PRO关联度高;Spearman系数法得出的非线性关系中,AC与RT、DEN、CNL、RS以及NPHI高。故利用DEN、RT、CNL、RS、GR、NPHI6条曲线预测声波时差AC。
在建立模型之前,首先选择信息较为完整的数据作为样本,将其分别分成 80% 和 20% 的训练集和测试集。将均方误差(mean square error,MSE)和R2作为模型评估指标, A1 井测井数据训练过程中损失函数的下降曲线如图9 所示,可以看出,模型的损失函数在训练过程中快速下降,训练及测试集损失值均趋于收敛,说明模型对测井数据的拟合效果良好, 同时模型对于测试集数据的损失函数最终稳定在0附近,进一步说明模型具有很好的泛化能力。
4种模型CNN、Bi-LSTM、CNN-BiLSTM-Attention、VCBAtt训练集数据预测结果如图10所示,可以看出,4种模型均能够反映出AC曲线随深度变化的趋势。 总体而言,CNN-BiLSTM-Attention和 VCBAtt 模型可以准确预测AC实测曲线,且预测值的大小与实测值更接近。由图10细节可知,当测井曲线出现局部连续周期化波动时(红色阴影区域),VCBAtt 模型的预测结果比 CNN-BiLSTM-Attention模型更接近真实值;曲线的局部不规则突变时(灰色阴影区域),VCBAtt 模型的预测结果也优于CNN-BiLSTM-Attention模型。 由上述分析可知提出的VCBAtt模型不论是在长期预测或短期预测中,其预测结果精度均优于其他模型。
图11的交会结果以及表1的精度评价参数可知,通过CNN-BiLSTM-Attention和VCBAtt模型得到的预测结果与真实AC曲线之间呈现较高的相关性,且MSE较低。将CNN-BiLSTM-Attention和VCBAtt模型用于A2井测井曲线AC的预测,进一步验证模型效果。
分别实现VCBAtt和未经过VMD处理的CNN-BiLSTM-Attention对测井曲线AC的预测,预测结果如图12所示。根据图12中预测结果发现,两个模型在预测效果上都能符合曲线的整体变化趋势。然而,针对细节部分(例如波峰波谷处),VCBAtt模型展现出更高的契合度,与真实曲线更加吻合,这表明VCBAtt模型在细节捕捉和预测精度方面具有优势。根据实验结果,得到模型评估参数MSE和R2的数值如表2所示。VCBAtt模型的 MSE较CNN-BiLSTM-Attention模型降低0.27%,R2上升4.6%。
综合分析模型实验和验证结果可知,VCBAtt模型无论较单一的CNN、Bi-LSTM网络模型以及组合模型CNN-BiLSTM-Attention在测井曲线的预测方面均呈现出更优的表现,具有更高的有效性和适用性。
从测井序列的非线性特征出发,采用基于VMD分解时频分析方法,进一步考虑测井曲线的深度趋势和局部形态,将CNN的强大特征提取能力与Bi-LSTM神经网络优越的记忆能力相融合,并使用Att机制进一步对测井曲线趋势特征进行挖掘,提出了基于VMD改进CNN-BiLSTM-Attention预测模型。将该网络模型应用于测井曲线预测并与其他常用机器学习预测模型进行对比,得到了以下结论。
(1)采用VMD将非平稳的测井数据分解为不同频率的成分,增加了数据的稳定性和可预测性,减少数据中突发性的波动,提升了模型预测精度。
(2)测井特征间存在高度复杂和多样化非线性关系, Att机制可以帮助模型捕捉不同测井曲线之间的变化模式和相互影响,以及充分考虑局部特征对整体模型的影响,提高模型对测井特征的预测能力。
(3)基于VCBAtt模型在测井曲线预测结果的有效性以及适用性,证实了VMD、神经网路以及Att机制融合模型的可行性,为测井曲线预测提供新思路。
  • 国家自然科学基金青年科学基金(52104020)
  • 湖北省自然科学基金青年科学基金(2020CFB377)
参考文献 引证文献
排序方式:
[1]
尚福华, 卢玉莹, 曹茂俊. 基于改进LSTM神经网络的测井曲线重构方法[J]. 计算机技术与发展, 2022, 32(6): 198-202.
Shang Fuhua, Lu Yuying, Cao Maojun. Well logging curve reconstruction method based on improved LSTM neural network[J]. 2022, 32(6): 198-202.
[2]
范翔宇, 孟凡, 邓娟, 等. 基于自动机器学习的测井曲线重构技术[J]. 天然气工业, 2024, 44(9): 38-54.
Fan Xiangyu, Meng Fan, Deng Juan, et al. Logging curve reconstruction technique based on automatic machine learning[J]. Natural Gas Industry, 2024, 44(9): 38-54.
[3]
王俊, 曹俊兴, 尤加春. 基于GRU神经网络的测井曲线重构[J]. 石油地球物理勘探, 2020, 55(3): 510-520.
Wang Jun, Cao Junxing, You Jiachun. Reconstruction of logging traces based on GRU neural network[J]. Oil Geophysical Prospecting, 2020, 55(3): 510-520.
[4]
曹茂俊, 赵宇杰. 一种基于预训练语言模型XLNet的测井曲线重构方法[J]. 计算机技术与发展, 2025, 35(2): 183-190.
Cao Maojun, Zhao Yujie. A method for logging curve reconstruction based on pre-trained language model XLNet[J]. Computer Technology and Development, 2025, 35(2): 183-190.
[5]
胡家琦. 基于深度学习的测井曲线预测和储层识别方法[D]. 西安: 陕西科技大学, 2020.
Hu Jiaqi. Logging curve prediction and reservoir identification method based on deep learning[D]. Xi'an: Shaanxi University of Science and Technology, 2020.
[6]
李小东. 基于测井数据的储层参数预测[D]. 大庆: 东北石油大学, 2021.
Li Xiaodong. Prediction of reservoir parameters based on logging data[D]. Daqing: Northeast Petroleum University, 2021.
[7]
王华, 张雨顺. 测井资料人工智能处理解释的现状及展望[J]. 测井技术, 2021, 45(4): 345-356.
Wang Hua, Zhang Yushun. Research status and prospect of artificial intelligence in logging data processing and interpretation[J]. Well Logging Technology, 2021, 45(4): 345-356.
[8]
张亮, 党海龙, 刘庆海, 等. 考虑地质分层约束的长短期记忆循环神经网络测井曲线重构[J]. 科学技术与工程, 2024, 24(19): 8045-8051.
Zhang Liang, Dang Hailong, Liu Qinghai, et al. Reconstruction of logging curves with long and short-term memory recurrent neural network considering geological stratification constraints[J]. Science Technology and Engineering, 2024, 24(19): 8045-8051.
[9]
牛聪, 王建花, 邬蒙蒙, 等. 基于改进的随机森林算法的井曲线填补研究及应用[J]. 中国海上油气, 2023, 35(6): 43-50.
Niu Cong, Wang Jianhua, Wu Mengmeng, et al. Research and application of well curve filling based on improved random forest algorithm[J]. China Offshore Oil and Gas, 2023, 35(6): 43-50.
[10]
芦升彦. 基于多层感知器神经网络的测井曲线重构方法研究[J]. 技术与市场, 2023, 30(12): 86-88, 92.
Lu Shengyan. Research on logging curve reconstruction method based on multilayer perceptron neural network[J]. Technology and Market, 2023, 30(12): 86-88, 92.
[11]
魏佳明. 机器学习在储层参数预测中的应用研究[D]. 西安: 西安石油大学, 2019.
Wei Jiaming. Research on the application of machine learning in reservoir parameter prediction[D]. Xi'an: Xi'an Shiyou University, 2019.
[12]
方娜, 余俊杰, 李俊晓, 等. 基于CNN-BiGRU-Attention的短期电力负荷预测[J]. 计算机仿真, 2022, 39(2): 40-44, 82.
Fang Na, Yu Junjie, Li Junxiao, et al. Short-term power load forecasting based on CNN-BiGRU-Attention[J]. Computer Simulation, 2022, 39(2): 40-44, 82.
[13]
Thabet S, Thabit T H. CFD simulation of the airflow around a car model (Ahmed body)[J]. International Journal of Scientific and Research Publications, 2018, 8(7): 517-525.
[14]
宋辉, 陈伟, 李谋杰, 等. 基于卷积门控循环单元网络的储层参数预测方法[J]. 油气地质与采收率, 2019, 26(5): 73-78.
Song Hui, Chen Wei, Li Moujie, et al. A method to predict reservoir parameters based on convolutional neural network-gated recurrent unit(CNN-GRU)[J]. Petroleum Geology and Recovery Efficiency, 2019, 26(5): 73-78.
[15]
基于多头注意力机制的TCN-BiGRU密度测井曲线重构方法[J/OL]. 地球物理学进展, 1-15[2025-03-14]. http://kns.cnki.net/kcms/detail/11.2982.P.20240905.1408.004.html. http://kns.cnki.net/kcms/detail/11.2982.P.20240905.1408.004.html
Wang Huanhuan, Zhao Bin, Liu Jianxin, et al. TCN-BiGRU density logging curve reconstruction method based on multi-attention mechanism[J/OL]. Advances in Geophysics, 1-15[2025-03-14]. http://kns.cnki.net/kcms/detail/11.2982.P.20240905.1408.004.html. http://kns.cnki.net/kcms/detail/11.2982.P.20240905.1408.004.html
[16]
殷豪, 欧祖宏, 陈德, 等. 基于二次模式分解和级联式深度学习的超短期风电功率预测[J]. 电网技术, 2020, 44(2): 445-453.
Yin Hao, Ou Zuhong, Chen De, et al. Ultra-short-term wind power prediction based on two-layer mode decomposition and cascaded deep learning[J]. Power System Technology, 2020, 44(2): 445-453.
[17]
Sinvaldo R M, Ramon Gomes da S, Viviana C M, et al. Multi-step wind speed forecasting based on hybrid multi-stage decomposition model and long short-term memory neural network[J]. Energy Conversion and Management, 2020, 213: 112869.
[18]
Sun W, Huang C C, A novel carbon price prediction model combines the secondary decomposition algorithm and the long short-term memory network[J]. Energy, 2020, 207: 118294.
[19]
Zhu Q, Zhang F, Liu S, et al. A hybrid VMD-BiGRU model for rubber futures time series forecasting[J]. Applied Soft Computing Journal, 2019, 84: 105739.
[20]
Dragomiretskiy K, Zosso D. Variational modedecomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.
[21]
吕宏政, 陈仁文, 张祥, 等. 基于VMD交叉样本嫡的旋翼桨叶故障诊断方法[J]. 电子测量技术, 2019, 42 (9): 107-111.
Lue Hongzheng, Chen Renwen, Zhang Xiang, et al. Fault diagnosis method of rotor blade based on VMD and cross-sample entropy[J]. Electronic Measurement Technology, 2019, 42 (9): 107-111.
[22]
陈云天. 基于机器学习的测井曲线补全与生成研究[D]. 北京: 北京大学, 2020.
Chen Yuntian. Research on well log completion and generation based on machine learning[D]. Beijing: Peking University, 2020.
[23]
隋金城. 基于LSTM神经网络的股票预测研究[D]. 青岛: 青岛科技大学, 2020.
Sui Jincheng. Research on stock prediction based on LSTM neural network[D]. Qingdao: Qingdao University of Science and Technology, 2020.
[24]
陈凯勋. 基于注意力机制的短时交通流速度预测模型研究[D]. 广州: 华南理工大学, 2019.
Chen Kaixun. Research on short-term traffic flow velocity prediction model based on attention mechanism[D]. Guangzhou: South China University of Technology, 2019.
[25]
Qin Y, Song D, Cheng H, et al. A dual-stage attention-based recurrent neural network for time series prediction[C]// Twenty-Sixth International Joint Conference on Artificial Intelligence. Melbourne: IEEE, 2017: 2627-2633.
[26]
郭雅婷. 基于注意力机制的网约车需求短时预测模型研究[D]. 广州: 华南理工大学, 2020.
Guo Yating. Research on short-term prediction model of online car-hailing demand based on attention mechanism[D]. Guangzhou: South China University of Technology, 2020.
[27]
周伟, 赵海航, 蒋云凤, 等. 基于串级双向长短时记忆神经网络的测井数据重构[J]. 石油地球物理勘探, 2022, 57(6): 1473-1480.
Zhou Wei, Zhao Haihang, Jiang Yunfeng, et al. Logging data reconstruction based on cascade bidirectional long short-term memory neural network[J]. Oil Geophysical Prospecting, 2022, 57(6): 1473-1480.
2025年第25卷第17期
PDF下载
153
72
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2404440
  • 接收时间:2024-06-14
  • 首发时间:2025-12-15
  • 出版时间:2025-06-18
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-06-14
基金
国家自然科学基金青年科学基金(52104020)
湖北省自然科学基金青年科学基金(2020CFB377)
作者信息
    长江大学石油工程学院, 武汉 430100

通讯作者:

*辛显康(1986—),男,汉族,山东汶上人,博士,副教授。研究方向:数值模拟。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2404440
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