Article(id=1156908299053523829, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156908295593223005, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2308335, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1698163200000, receivedDateStr=2023-10-25, revisedDate=1728316800000, revisedDateStr=2024-10-08, acceptedDate=null, acceptedDateStr=null, onlineDate=1753758032810, onlineDateStr=2025-07-29, pubDate=1736265600000, pubDateStr=2025-01-08, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1753758032810, onlineIssueDateStr=2025-07-29, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1753758032810, creator=13701087609, updateTime=1753758032810, updator=13701087609, issue=Issue{id=1156908295593223005, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='1', pageStart='1', pageEnd='438', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1753758031985, creator=13701087609, updateTime=1765425680602, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1205845960933049001, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156908295593223005, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1205845960933049002, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156908295593223005, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=270, endPage=277, ext={EN=ArticleExt(id=1156908299925939067, articleId=1156908299053523829, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Application of Wavelet Denoising Neural Network in Digital Core, columnId=1156262729162810294, journalTitle=Science Technology and Engineering, columnName=Papers·Automation and Computational Technology, runingTitle=null, highlight=null, articleAbstract=

Based on the sand-mud interlayer core of a block in Ordos Basin, denoising neural network based on wavelet transformation (DWTNet) was used to denoise the core image. The evaluation of this method was carried out by comparing the peak signal-to-noise ratio (PSNR) and the post-denoising image outcomes. The investigation reveals that by applying the DWTNet denoising algorithm to the test sets YX1 and YX2, and contrasting it with other denoising algorithms such as EGDNet, the PSNR values at noise levels of 25, 50, and 75 dB are respectively 0.527, 0.418, and 1.1 dB higher than those achieved by the EGDNet algorithm. The proposed algorithm surpasses others in terms of metrics including peak signal to noise ratio(PSNR), and visually, the resulting images processed by it exhibit enhanced clarity. The introduction of this method holds substantial significance for the calculation of parameters like porosity, mean specific surface area, mean curvature, among other rock properties, thereby advancing the capabilities in digital core technology, CT scanning analysis, and understanding of rock characteristics.

, correspAuthors=Wei LI, 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-su HE, Wei LI, Jing-ming GAI, Lin-hao ZOU, Huan ZHAO, Sheng-jie JIAO, Xiao-rui XIE), CN=ArticleExt(id=1156908414346552175, articleId=1156908299053523829, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于小波去噪神经网络在数字岩心的应用, columnId=1156262729783567290, journalTitle=科学技术与工程, columnName=论文·自动化技术、计算机技术, runingTitle=null, highlight=null, articleAbstract=

以鄂尔多斯盆地某区块的砂泥夹层岩心为研究对象,使用基于小波变换的去噪神经网络(denoising neural network based on wavelet transformation,DWTNet)对于岩心的图像进行去噪研究。该方法的评断结果采用峰值信噪比(peak signal to noise ratio,PSNR)和去噪后的图像结果进行了对比。研究表明,利用DWTNet在测试集YX1、YX2测试所提出的算法,并与EGDNet等去噪算法进行对比,PSNR在噪声为25、50、75 dB时,高于EGDNet算法0.527、0.418、1.1 dB。所提的算法在峰值信噪比等指标均高于其他算法;并在视觉效果上其处理得到的图像也更加清晰。方法的提出对于孔隙度、平均体积比表面积、平均曲率计算等都有着非常重要的意义。

, correspAuthors=李玮, authorNote=null, correspAuthorsNote=
* 李玮(1979—),男,汉族,黑龙江大庆人,博士,教授。研究方向:扭力冲击破岩机理及工具、智能钻井理论与工艺软件。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=qlgdz1wzRtpQACpZIOlPrQ==, magXml=pVUPzCS7+OT8s1L+0+ZhOQ==, pdfUrl=null, pdf=15g5l7sg09y4IH51EIUPQw==, pdfFileSize=14165565, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=VV5sqoQ2dewXlyp3wCFPlg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=BprhRUpMluXIdS4+CO9HQg==, mapNumber=null, authorCompany=null, fund=null, authors=

何田素(1997—),男,汉族,安徽淮南人,硕士研究生。研究方向:计算机视觉。E-mail:

, authorsList=何田素, 李玮, 盖京明, 邹林浩, 赵欢, 焦圣杰, 谢晓蕊)}, authors=[Author(id=1205909364267872722, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=h1803158408@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1205909364339175893, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, authorId=1205909364267872722, language=EN, stringName=Tian-su HE, firstName=Tian-su, middleName=null, lastName=HE, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. School of Petroleum Engineering, Northeast Petroleum University, Daqing 163318, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205909364397896151, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, authorId=1205909364267872722, language=CN, stringName=何田素, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.东北石油大学石油工程学院, 大庆 163318, bio={"content":"

何田素(1997—),男,汉族,安徽淮南人,硕士研究生。研究方向:计算机视觉。E-mail:

"}, bioImg=null, bioContent=

何田素(1997—),男,汉族,安徽淮南人,硕士研究生。研究方向:计算机视觉。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205909364108489161, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, xref=null, ext=[AuthorCompanyExt(id=1205909364112683466, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, companyId=1205909364108489161, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. School of Petroleum Engineering, Northeast Petroleum University, Daqing 163318, China), AuthorCompanyExt(id=1205909364121072075, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, companyId=1205909364108489161, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.东北石油大学石油工程学院, 大庆 163318)])]), Author(id=1205909364473393626, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liwei@nepu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1205909364544696798, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, authorId=1205909364473393626, language=EN, stringName=Wei LI, firstName=Wei, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, *, address=1. School of Petroleum Engineering, Northeast Petroleum University, Daqing 163318, China
2. Oil and Gas Drilling Completion Technology National Engineering Research Center, Daqing 163318, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205909364691497441, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, authorId=1205909364473393626, language=CN, stringName=李玮, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, *, address=1.东北石油大学石油工程学院, 大庆 163318
2.油气钻完技术国家工程研究中心, 大庆 163318, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205909364108489161, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, xref=null, ext=[AuthorCompanyExt(id=1205909364112683466, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, companyId=1205909364108489161, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. School of Petroleum Engineering, Northeast Petroleum University, Daqing 163318, China), AuthorCompanyExt(id=1205909364121072075, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, companyId=1205909364108489161, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.东北石油大学石油工程学院, 大庆 163318)]), AuthorCompany(id=1205909364183986637, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, xref=null, ext=[AuthorCompanyExt(id=1205909364192375246, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, companyId=1205909364183986637, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. Oil and Gas Drilling Completion Technology National Engineering Research Center, Daqing 163318, China), AuthorCompanyExt(id=1205909364196569551, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, companyId=1205909364183986637, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.油气钻完技术国家工程研究中心, 大庆 163318)])]), Author(id=1205909364754412002, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, 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=1205909364829909477, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, authorId=1205909364754412002, language=EN, stringName=Jing-ming GAI, firstName=Jing-ming, middleName=null, lastName=GAI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. School of Petroleum Engineering, Northeast Petroleum University, Daqing 163318, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205909364901212647, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, authorId=1205909364754412002, language=CN, stringName=盖京明, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.东北石油大学石油工程学院, 大庆 163318, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205909364108489161, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, xref=null, ext=[AuthorCompanyExt(id=1205909364112683466, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, companyId=1205909364108489161, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. School of Petroleum Engineering, Northeast Petroleum University, Daqing 163318, China), AuthorCompanyExt(id=1205909364121072075, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, companyId=1205909364108489161, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.东北石油大学石油工程学院, 大庆 163318)])]), Author(id=1205909364964127210, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, 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=1205909365043818988, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, authorId=1205909364964127210, language=EN, stringName=Lin-hao ZOU, firstName=Lin-hao, middleName=null, lastName=ZOU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. School of Petroleum Engineering, Northeast Petroleum University, Daqing 163318, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205909365152870894, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, authorId=1205909364964127210, language=CN, stringName=邹林浩, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.东北石油大学石油工程学院, 大庆 163318, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205909364108489161, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, xref=null, ext=[AuthorCompanyExt(id=1205909364112683466, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, companyId=1205909364108489161, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. School of Petroleum Engineering, Northeast Petroleum University, Daqing 163318, China), AuthorCompanyExt(id=1205909364121072075, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, companyId=1205909364108489161, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.东北石油大学石油工程学院, 大庆 163318)])]), Author(id=1205909365253534191, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, 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=1205909365366780403, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, authorId=1205909365253534191, language=EN, stringName=Huan ZHAO, firstName=Huan, middleName=null, lastName=ZHAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1. School of Petroleum Engineering, Northeast Petroleum University, Daqing 163318, China
2. Oil and Gas Drilling Completion Technology National Engineering Research Center, Daqing 163318, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205909365425500661, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, authorId=1205909365253534191, language=CN, stringName=赵欢, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.东北石油大学石油工程学院, 大庆 163318
2.油气钻完技术国家工程研究中心, 大庆 163318, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205909364108489161, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, xref=null, ext=[AuthorCompanyExt(id=1205909364112683466, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, companyId=1205909364108489161, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. School of Petroleum Engineering, Northeast Petroleum University, Daqing 163318, China), AuthorCompanyExt(id=1205909364121072075, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, companyId=1205909364108489161, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.东北石油大学石油工程学院, 大庆 163318)]), AuthorCompany(id=1205909364183986637, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, xref=null, ext=[AuthorCompanyExt(id=1205909364192375246, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, companyId=1205909364183986637, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. Oil and Gas Drilling Completion Technology National Engineering Research Center, Daqing 163318, China), AuthorCompanyExt(id=1205909364196569551, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, companyId=1205909364183986637, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.油气钻完技术国家工程研究中心, 大庆 163318)])]), Author(id=1205909365492609528, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, 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=1205909365555524090, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, authorId=1205909365492609528, language=EN, stringName=Sheng-jie JIAO, firstName=Sheng-jie, middleName=null, lastName=JIAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. School of Petroleum Engineering, Northeast Petroleum University, Daqing 163318, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205909365610050043, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, authorId=1205909365492609528, language=CN, stringName=焦圣杰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.东北石油大学石油工程学院, 大庆 163318, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205909364108489161, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, xref=null, ext=[AuthorCompanyExt(id=1205909364112683466, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, companyId=1205909364108489161, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. School of Petroleum Engineering, Northeast Petroleum University, Daqing 163318, China), AuthorCompanyExt(id=1205909364121072075, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, companyId=1205909364108489161, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.东北石油大学石油工程学院, 大庆 163318)])]), Author(id=1205909365664575998, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, orderNo=6, 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=1205909365740073473, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, authorId=1205909365664575998, language=EN, stringName=Xiao-rui XIE, firstName=Xiao-rui, middleName=null, lastName=XIE, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. School of Petroleum Engineering, Northeast Petroleum University, Daqing 163318, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205909365811376643, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, authorId=1205909365664575998, language=CN, stringName=谢晓蕊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.东北石油大学石油工程学院, 大庆 163318, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205909364108489161, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, xref=null, ext=[AuthorCompanyExt(id=1205909364112683466, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, companyId=1205909364108489161, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. School of Petroleum Engineering, Northeast Petroleum University, Daqing 163318, China), AuthorCompanyExt(id=1205909364121072075, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, companyId=1205909364108489161, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.东北石油大学石油工程学院, 大庆 163318)])])], keywords=[Keyword(id=1205909365933011462, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=EN, orderNo=1, keyword=digital core technology), Keyword(id=1205909365991731720, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=EN, orderNo=2, keyword=core samples), Keyword(id=1205909366058840586, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=EN, orderNo=3, keyword=CT scanning), Keyword(id=1205909366134338060, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=EN, orderNo=4, keyword=rock properties), Keyword(id=1205909366230807054, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=EN, orderNo=5, keyword=neural network), Keyword(id=1205909366306304528, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=EN, orderNo=6, keyword=noise reduction), Keyword(id=1205909366369219090, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=CN, orderNo=1, keyword=数字岩心技术), Keyword(id=1205909366436327956, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=CN, orderNo=2, keyword=岩心), Keyword(id=1205909366507631126, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=CN, orderNo=3, keyword=CT扫描), Keyword(id=1205909366583128600, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=CN, orderNo=4, keyword=岩石特性), Keyword(id=1205909366633460250, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=CN, orderNo=5, keyword=神经网络), Keyword(id=1205909366708957724, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=CN, orderNo=6, keyword=去噪)], refs=[Reference(id=1205909369712079425, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2022, volume=53, issue=11, pageStart=4412, pageEnd=4424, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=王付勇, 赵久玉, journalName=中南大学学报(自然科学版), refType=null, unstructuredReference=王付勇, 赵久玉. 基于深度学习的数字岩心图像重构及其重构效果评价[J]. 中南大学学报(自然科学版), 2022, 53(11): 4412-4424., articleTitle=基于深度学习的数字岩心图像重构及其重构效果评价, refAbstract=null), Reference(id=1205909369774993986, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2022, volume=53, issue=11, pageStart=4412, pageEnd=4424, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Wang Fuyong, Zhao Jiuyu, journalName=Journal of Central South University (Natural Science Edition), refType=null, unstructuredReference=Wang Fuyong, Zhao Jiuyu. Digital core image reconstruction based on deep learning and its reconstruction effect evaluation[J]. Journal of Central South University (Natural Science Edition), 2022, 53(11): 4412-4424., articleTitle=Digital core image reconstruction based on deep learning and its reconstruction effect evaluation, refAbstract=null), Reference(id=1205909369837908547, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2020, volume=101, issue=null, pageStart=023305, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=Chen H G, He X H, Teng Q Z, journalName=Physical Review E, refType=null, unstructuredReference=Chen H G, He X H, Teng Q Z, et al. Superresolution of real-world rock microcomputed tomography images using cycle-consistent generative adversarial networks[J]. Physical Review E, 2020, 101: 023305., articleTitle=Superresolution of real-world rock microcomputed tomography images using cycle-consistent generative adversarial networks, refAbstract=null), Reference(id=1205909369896628806, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=裴利强, journalName=多分辨率数字岩心的表示与生成, refType=null, unstructuredReference=裴利强. 多分辨率数字岩心的表示与生成[D]. 青岛: 中国石油大学(华东), 2020., articleTitle=null, refAbstract=null), Reference(id=1205909369951154759, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=Pei Lijiang, journalName=Representation and generation of multi-resolution digital cores, refType=null, unstructuredReference=Pei Lijiang. Representation and generation of multi-resolution digital cores[D]. Qingdao: China University of Petroleum (East China), 2020., articleTitle=null, refAbstract=null), Reference(id=1205909370026652234, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=44, pageEnd=53, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=Yan G G, Yan W D, Yuan Y Z, journalName=International Journal of Petroleum Technology, refType=null, unstructuredReference=Yan G G, Yan W D, Yuan Y Z, Research on the method of evaluating the pore throat structure of rock microscopically based on the 3D pore network model of digital core[J]. International Journal of Petroleum Technology, 2022, 44-53., articleTitle=Research on the method of evaluating the pore throat structure of rock microscopically based on the 3D pore network model of digital core, refAbstract=null), Reference(id=1205909370093761102, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2020, volume=32, issue=11, pageStart=1822, pageEnd=1831, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=刘一畅, 马伟, 徐士彪, journalName=计算机辅助设计与图形学学报, refType=null, unstructuredReference=刘一畅, 马伟, 徐士彪, 等. 基于卷积神经网络的边缘保真图像去噪算法[J]. 计算机辅助设计与图形学学报, 2020, 32(11): 1822-1831., articleTitle=基于卷积神经网络的边缘保真图像去噪算法, refAbstract=null), Reference(id=1205909370156675666, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2020, volume=32, issue=11, pageStart=1822, pageEnd=1831, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=Liu Yichang, Ma Wei, Xu Shibiao, journalName=Journal of Computer Aided Design and Graphics, refType=null, unstructuredReference=Liu Yichang, Ma Wei, Xu Shibiao, et al. Edge fidelity image denoising algorithm based on convolutional neural networks[J]. Journal of Computer Aided Design and Graphics, 2020, 32(11): 1822-1831., articleTitle=Edge fidelity image denoising algorithm based on convolutional neural networks, refAbstract=null), Reference(id=1205909370227978836, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=石小涵, journalName=基于卷积神经网络和小波变换的图像去噪算法, refType=null, unstructuredReference=石小涵. 基于卷积神经网络和小波变换的图像去噪算法[D]. 西安: 西安建筑科技大学, 2020., articleTitle=null, refAbstract=null), Reference(id=1205909370286699094, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=Shi Xiaohan, journalName=Image denoising algorithm based on convolutional neural network and wavelet transform, refType=null, unstructuredReference=Shi Xiaohan. Image denoising algorithm based on convolutional neural network and wavelet transform[D]. Xi’an: Xi’an University of Architecture and Technology, 2020., articleTitle=null, refAbstract=null), Reference(id=1205909370358002266, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=1, pageStart=84, pageEnd=90, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=林煌伟, 陈钧荣, 牛玉贞, journalName=小型微型计算机系统, refType=null, unstructuredReference=林煌伟, 陈钧荣, 牛玉贞. 基于循环神经网络的多阶段图像去噪方法[J]. 小型微型计算机系统, 2022, 43(1): 84-90., articleTitle=基于循环神经网络的多阶段图像去噪方法, refAbstract=null), Reference(id=1205909370450276956, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=1, pageStart=84, pageEnd=90, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=Lin Huangwei, Chen Junrong, Niu Yuzhen, journalName=Small Micro Computer System, refType=null, unstructuredReference=Lin Huangwei, Chen Junrong, Niu Yuzhen. A multi-stage image denoising method based on recurrent neural networks[J]. Small Micro Computer System, 2022, 43(1): 84-90., articleTitle=A multi-stage image denoising method based on recurrent neural networks, refAbstract=null), Reference(id=1205909370555134558, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2022, volume=48, issue=5, pageStart=616, pageEnd=626, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=王坤, 叶招君, journalName=光学技术, refType=null, unstructuredReference=王坤, 叶招君. 基于小波空洞残差U-Net的红外图像去条纹噪声方法[J]. 光学技术, 2022, 48(5): 616-626., articleTitle=基于小波空洞残差U-Net的红外图像去条纹噪声方法, refAbstract=null), Reference(id=1205909370609660514, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2022, volume=48, issue=5, pageStart=616, pageEnd=626, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=Wang Kun, Ye Zhaojun, journalName=Optical Technology, refType=null, unstructuredReference=Wang Kun, Ye Zhaojun. Infrared image denoising method based on wavelet cavity residual U-Net[J]. Optical Technology, 2022, 48(5): 616-626., articleTitle=Infrared image denoising method based on wavelet cavity residual U-Net, refAbstract=null), Reference(id=1205909370668380772, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2024, volume=41, issue=1, pageStart=288, pageEnd=295, url=null, language=null, rfNumber=[9], rfOrder=14, authorNames=王力, 李小霞, 秦佳敏, journalName=计算机应用研究, refType=null, unstructuredReference=王力, 李小霞, 秦佳敏, 等. 级联离散小波多频带分解注意力图像去噪方法[J]. 计算机应用研究, 2024, 41(1): 288-295., articleTitle=级联离散小波多频带分解注意力图像去噪方法, refAbstract=null), Reference(id=1205909370722906726, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2024, volume=41, issue=1, pageStart=288, pageEnd=295, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=Wang Li, Li Xiaoxia, Qin Jiamin, journalName=Computer Application Research, refType=null, unstructuredReference=Wang Li, Li Xiaoxia, Qin Jiamin, et al. Cascaded discrete wavelet multi band decomposition attention image denoising method[J]. Computer Application Research, 2024, 41(1): 288-295., articleTitle=Cascaded discrete wavelet multi band decomposition attention image denoising method, refAbstract=null), Reference(id=1205909370781626986, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=9, pageStart=3629, pageEnd=3635, url=null, language=null, rfNumber=[10], rfOrder=16, authorNames=姜旭, 赵荣彩, 刘勇杰, journalName=科学技术与工程, refType=null, unstructuredReference=姜旭, 赵荣彩, 刘勇杰, 等. 基于改进U-Net神经网络的图像去噪算法[J]. 科学技术与工程, 2022, 22(9): 3629-3635., articleTitle=基于改进U-Net神经网络的图像去噪算法, refAbstract=null), Reference(id=1205909370831958636, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=9, pageStart=3629, pageEnd=3635, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=Jiang Xu, Zhao Rongcai, Liu Yongjie, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Jiang Xu, Zhao Rongcai, Liu Yongjie, et al. Image denoising algorithm based on improved U-Net neural network[J]. Science Technology and Engineering, 2022, 22(9): 3629-3635., articleTitle=Image denoising algorithm based on improved U-Net neural network, refAbstract=null), Reference(id=1205909370890678894, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=11, pageStart=4686, pageEnd=4692, url=null, language=null, rfNumber=[11], rfOrder=18, authorNames=吴学礼, 王壮壮, 习炳权, journalName=科学技术与工程, refType=null, unstructuredReference=吴学礼, 王壮壮, 习炳权, 等. 基于小波自适应阈值方法的探地雷达去噪[J]. 科学技术与工程, 2023, 23(11): 4686-4692., articleTitle=基于小波自适应阈值方法的探地雷达去噪, refAbstract=null), Reference(id=1205909370945204849, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=11, pageStart=4686, pageEnd=4692, url=null, language=null, rfNumber=[11], rfOrder=19, authorNames=Wu Xueli, Wang Zhuangzhuang, Xi Bingquan, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Wu Xueli, Wang Zhuangzhuang, Xi Bingquan, et al. Ground penetrating radar denoising based on wavelet adaptive threshold method[J]. Science Technology and Engineering, 2023, 23(11): 4686-4692, articleTitle=Ground penetrating radar denoising based on wavelet adaptive threshold method, refAbstract=null), Reference(id=1205909371003925106, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2013, volume=22, issue=12, pageStart=5226, pageEnd=5237, url=null, language=null, rfNumber=[12], rfOrder=20, authorNames=Liu X, Tanaka M, Okutomi M, journalName=IEEE Transactions on Image Processing, refType=null, unstructuredReference=Liu X, Tanaka M, Okutomi M. Single-image noise level estimation for blind denoising[J]. IEEE Transactions on Image Processing, 2013, 22(12): 5226-5237., articleTitle=Single-image noise level estimation for blind denoising, refAbstract=null), Reference(id=1205909371079422581, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2020, volume=29, issue=null, pageStart=4885, pageEnd=4897, url=null, language=null, rfNumber=[13], rfOrder=21, authorNames=Helou M E, Susstrunk S, journalName=IEEE Transactions on ImageProcessing, refType=null, unstructuredReference=Helou M E, Susstrunk S. Blind universal Bayesian image denoising with Gaussian noise level learning[J]. IEEE Transactions on ImageProcessing, 2020, 29: 4885-4897., articleTitle=Blind universal Bayesian image denoising with Gaussian noise level learning, refAbstract=null), Reference(id=1205909371138142838, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=1410, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=22, authorNames=Dinh L, Krueger D, Bengio Y, journalName=ArXiv Preprint ArXiv, refType=null, unstructuredReference=Dinh L, Krueger D, Bengio Y. NICE: non-linear independent components estimation[J]. ArXiv Preprint ArXiv, 2014: 1410.8516., articleTitle=NICE: non-linear independent components estimation, refAbstract=null), Reference(id=1205909371192668792, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=1605, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=23, authorNames=Dinh L, Sohl-Dickstein J, Bengio S, journalName=ArXiv Preprint ArXiv, refType=null, unstructuredReference=Dinh L, Sohl-Dickstein J, Bengio S, Density estimation using real NVP[J]. ArXiv Preprint ArXiv, 2016: 1605.08803., articleTitle=Density estimation using real NVP, refAbstract=null), Reference(id=1205909371251389050, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=1707, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=24, authorNames=Gomez A N, Ren M, Urtasun R, journalName=ArXiv Preprint ArXiv, refType=null, unstructuredReference=Gomez A N, Ren M, Urtasun R, et al. The reversible residual network: back propagation without storing activations[J]. ArXiv Preprint ArXiv, 2017: 1707.04585., articleTitle=The reversible residual network: back propagation without storing activations, refAbstract=null), Reference(id=1205909371310109308, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=1802, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=25, authorNames=Jacobsen J H, Smeulders A W, Oyallon E, journalName=ArXiv, refType=null, unstructuredReference=Jacobsen J H, Smeulders A W, Oyallon E. I-RevNet: deep invertible networks[J]. ArXiv, 2018: 1802.07088., articleTitle=I-RevNet: deep invertible networks, refAbstract=null), Reference(id=1205909372476125822, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=2005, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=26, authorNames=Xiao M, Zheng S, Liu C, journalName=ArXiv, refType=null, unstructuredReference=Xiao M, Zheng S, Liu C, et al. Invertible image rescaling[J]. ArXiv, 2020: 2005.05650., articleTitle=Invertible image rescaling, refAbstract=null), Reference(id=1205909372539040384, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=1994, volume=81, issue=3, pageStart=239520, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=27, authorNames=Donoho D L, Johnstone I M, journalName=Biometrika, refType=null, unstructuredReference=Donoho D L, Johnstone I M. Ideal spatial adaptation by wavelet shrinkage[J]. Biometrika, 1994, 81(3): 239520., articleTitle=Ideal spatial adaptation by wavelet shrinkage, refAbstract=null), Reference(id=1205909372618732162, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2020, volume=17, issue=4, pageStart=501, pageEnd=512, url=null, language=null, rfNumber=[20], rfOrder=28, authorNames=Wang H T, Wang L, Lai F Q, journalName=Applied Geophysics, refType=null, unstructuredReference=Wang H T, Wang L, Lai F Q, et al. Investigation of image segmentation effect on the accuracy of reconstructed digital core models of coquina carbonate[J]. Applied Geophysics, 2020, 17(4): 501-512., articleTitle=Investigation of image segmentation effect on the accuracy of reconstructed digital core models of coquina carbonate, refAbstract=null), Reference(id=1205909372702618244, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=34, pageStart=15237, pageEnd=15244, url=null, language=null, rfNumber=[21], rfOrder=29, authorNames=周联敏, 周冬明, 杨浩, journalName=科学技术与工程, refType=null, unstructuredReference=周联敏, 周冬明, 杨浩. 结合迁移学习的真实图像去噪算法[J]. 科学技术与工程, 2022, 22(34): 15237-15244., articleTitle=结合迁移学习的真实图像去噪算法, refAbstract=null), Reference(id=1205909372782310022, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=34, pageStart=15237, pageEnd=15244, url=null, language=null, rfNumber=[21], rfOrder=30, authorNames=Zhou Lianmin, Zhou Dongming, Yang Hao, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Zhou Lianmin, Zhou Dongming, Yang Hao. A real image denoising algorithm combining transfer learning[J]. Science Technology and Engineering, 2022, 22(34): 15237-15244., articleTitle=A real image denoising algorithm combining transfer learning, refAbstract=null)], funds=[Fund(id=1205909369561084480, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, awardId=52274005, language=CN, fundingSource=国家自然科学基金(52274005), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1205909364108489161, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, xref=null, ext=[AuthorCompanyExt(id=1205909364112683466, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, companyId=1205909364108489161, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. School of Petroleum Engineering, Northeast Petroleum University, Daqing 163318, China), AuthorCompanyExt(id=1205909364121072075, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, companyId=1205909364108489161, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.东北石油大学石油工程学院, 大庆 163318)]), AuthorCompany(id=1205909364183986637, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, xref=null, ext=[AuthorCompanyExt(id=1205909364192375246, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, companyId=1205909364183986637, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. Oil and Gas Drilling Completion Technology National Engineering Research Center, Daqing 163318, China), AuthorCompanyExt(id=1205909364196569551, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, companyId=1205909364183986637, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.油气钻完技术国家工程研究中心, 大庆 163318)])], figs=[ArticleFig(id=1205909367963054623, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=EN, label=Fig.1, caption=The network framework for DWTNet, figureFileSmall=qGsOYIoyFYVV329/aLZazw==, figureFileBig=Bh6AnTJb7zfEMKwogdn2zg==, tableContent=null), ArticleFig(id=1205909368030163488, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=CN, label=图1, caption=DWTNet网络框架, figureFileSmall=qGsOYIoyFYVV329/aLZazw==, figureFileBig=Bh6AnTJb7zfEMKwogdn2zg==, tableContent=null), ArticleFig(id=1205909368155992609, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=EN, label=Fig.2, caption=The module of enhancing wavelet signal, figureFileSmall=gj7X5sR2axGckhbVEC7dLg==, figureFileBig=s4GWXM95fL28peaXHy/8SA==, tableContent=null), ArticleFig(id=1205909368223101474, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=CN, label=图2, caption=小波信号增强模块, figureFileSmall=gj7X5sR2axGckhbVEC7dLg==, figureFileBig=s4GWXM95fL28peaXHy/8SA==, tableContent=null), ArticleFig(id=1205909368294404643, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=EN, label=Fig.3, caption=The module of wavelet network decomposition, figureFileSmall=JlUTy4s9Cc2lBr49Q0Ya9A==, figureFileBig=RNOprs6bhcT3Iy+xr9n6rA==, tableContent=null), ArticleFig(id=1205909368369902116, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=CN, label=图3, caption=小波网络分解模块, figureFileSmall=JlUTy4s9Cc2lBr49Q0Ya9A==, figureFileBig=RNOprs6bhcT3Iy+xr9n6rA==, tableContent=null), ArticleFig(id=1205909368437010981, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=EN, label=Fig.4, caption=The network of noise estimation, figureFileSmall=xIU+8J9Z9e5Rm7xgz0dHzg==, figureFileBig=b6jYeYdaC+vhoX+G/puvWQ==, tableContent=null), ArticleFig(id=1205909368508314150, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=CN, label=图4, caption=噪声估计网络, figureFileSmall=xIU+8J9Z9e5Rm7xgz0dHzg==, figureFileBig=b6jYeYdaC+vhoX+G/puvWQ==, tableContent=null), ArticleFig(id=1205909368575423015, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=EN, label=Fig.5, caption=The Decomposition, figureFileSmall=qYuuDx+lEkyGGqVcUOHgeg==, figureFileBig=YQOGW0MjTQdPqcpaB2mQCg==, tableContent=null), ArticleFig(id=1205909368642531881, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=CN, label=图5, caption=分解, figureFileSmall=qYuuDx+lEkyGGqVcUOHgeg==, figureFileBig=YQOGW0MjTQdPqcpaB2mQCg==, tableContent=null), ArticleFig(id=1205909368688669226, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=EN, label=Fig.6, caption=Difference between the four methods in YX1 and the benchmark algorithm PSNR, figureFileSmall=BmjpbjSzHdUhzjRbOWKFMA==, figureFileBig=UJnMd2TVSBUHTlC7jL7Tag==, tableContent=null), ArticleFig(id=1205909368772555309, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=CN, label=图6, caption=4种方法在YX1与基准算法PSNR差值, figureFileSmall=BmjpbjSzHdUhzjRbOWKFMA==, figureFileBig=UJnMd2TVSBUHTlC7jL7Tag==, tableContent=null), ArticleFig(id=1205909368839664175, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=EN, label=Fig.7, caption=The core denoising results of five algorithms when the noise level is 50 dB, figureFileSmall=3FdfO6/ahOGNGXUfU3Caww==, figureFileBig=a7e7lREefWLUJmKqjLQF8w==, tableContent=null), ArticleFig(id=1205909368894190129, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=CN, label=图7, caption=噪声等级为50 dB时4种算法岩心去噪结果图

原始图像∶文中图像为1∶10

, figureFileSmall=3FdfO6/ahOGNGXUfU3Caww==, figureFileBig=a7e7lREefWLUJmKqjLQF8w==, tableContent=null), ArticleFig(id=1205909368965493298, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=EN, label=Fig.8, caption=Comparison of CT scan denoising results, figureFileSmall=W5h4hOc517zZILiZv+A4yg==, figureFileBig=prt9aMeek/LkNQeSVro0/Q==, tableContent=null), ArticleFig(id=1205909369040990771, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=CN, label=图8, caption=CT扫描去噪结果对比图

原始图像比例为8∶1

, figureFileSmall=W5h4hOc517zZILiZv+A4yg==, figureFileBig=prt9aMeek/LkNQeSVro0/Q==, tableContent=null), ArticleFig(id=1205909369095516724, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=EN, label=Table 1, caption=

Comparison of PSNR of five algorithms with different noise levels in four test sets

, figureFileSmall=null, figureFileBig=null, tableContent=
数据集 噪声/
dB
小波变
换算法
文献
[5]
算法
文献
[6]
算法
文献
[7]
算法
本文
算法
YX1 25 31.325 33.683 32.223 32.746 34.210
50 29.837 30.705 29.175 30.476 31.123
75 26.014 27.902 26.954 28.476 29.002
YX2 25 30.975 33.157 32.565 33.791 34.063
50 28.983 30.093 28.759 30.138 30.459
75 26.417 27.636 25.834 28.076 28.531
YX3 25 30.249 32.559 30.461 31.646 31.921
50 27.685 29.454 29.045 29.096 29.429
75 26.022 26.720 26.761 26.156 26.828
YX4 25 30.677 34.524 31.792 33.753 35.073
50 27.576 29.997 29.453 29.745 31.442
75 25.014 28.045 27.461 27.124 28.439
), ArticleFig(id=1205909369158431286, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=CN, label=表1, caption=

5种算法在4个测试集不同噪声等级的PSNR比较

, figureFileSmall=null, figureFileBig=null, tableContent=
数据集 噪声/
dB
小波变
换算法
文献
[5]
算法
文献
[6]
算法
文献
[7]
算法
本文
算法
YX1 25 31.325 33.683 32.223 32.746 34.210
50 29.837 30.705 29.175 30.476 31.123
75 26.014 27.902 26.954 28.476 29.002
YX2 25 30.975 33.157 32.565 33.791 34.063
50 28.983 30.093 28.759 30.138 30.459
75 26.417 27.636 25.834 28.076 28.531
YX3 25 30.249 32.559 30.461 31.646 31.921
50 27.685 29.454 29.045 29.096 29.429
75 26.022 26.720 26.761 26.156 26.828
YX4 25 30.677 34.524 31.792 33.753 35.073
50 27.576 29.997 29.453 29.745 31.442
75 25.014 28.045 27.461 27.124 28.439
), ArticleFig(id=1205909369221345849, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=EN, label=Table 2, caption=

The comparison of SSIM of five algorithms with different noise levels in four test sets

, figureFileSmall=null, figureFileBig=null, tableContent=
数据集 噪声/
dB
小波变
换算法
文献
[5]
算法
文献
[6]
算法
文献
[7]
算法
本文
算法
YX1 25 0.683 0.850 0.761 0.749 0.820
50 0.694 0.841 0.812 0.858 0.848
75 0.601 0.853 0.909 0.851 0.905
YX2 25 0.708 0.881 0.842 0.826 0.923
50 0.685 0.930 0.833 0.899 0.912
75 0.628 0.923 0.907 0.651 0.954
YX3 25 0.683 0.956 0.876 0.900 0.902
50 0.620 0.918 0.846 0.845 0.957
75 0.618 0.951 0.891 0.823 0.968
YX4 25 0.673 0.897 0.931 0.862 0.973
50 0.615 0.925 0.839 0.849 0.965
75 0.641 0.970 0.872 0.828 0.964
), ArticleFig(id=1205909369280066107, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=CN, label=表2, caption=

5种算法在4个测试集不同噪声等级的SSIM比较

, figureFileSmall=null, figureFileBig=null, tableContent=
数据集 噪声/
dB
小波变
换算法
文献
[5]
算法
文献
[6]
算法
文献
[7]
算法
本文
算法
YX1 25 0.683 0.850 0.761 0.749 0.820
50 0.694 0.841 0.812 0.858 0.848
75 0.601 0.853 0.909 0.851 0.905
YX2 25 0.708 0.881 0.842 0.826 0.923
50 0.685 0.930 0.833 0.899 0.912
75 0.628 0.923 0.907 0.651 0.954
YX3 25 0.683 0.956 0.876 0.900 0.902
50 0.620 0.918 0.846 0.845 0.957
75 0.618 0.951 0.891 0.823 0.968
YX4 25 0.673 0.897 0.931 0.862 0.973
50 0.615 0.925 0.839 0.849 0.965
75 0.641 0.970 0.872 0.828 0.964
), ArticleFig(id=1205909369342980669, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=EN, label=Table 3, caption=

Comparison of denoising performance in CT images

, figureFileSmall=null, figureFileBig=null, tableContent=
方法 PSNR/dB 平均值/dB
文献[5]
算法
27.651 26.893 28.354 28.257 27.789
27.685 27.189 27.751 28.138 27.691
28.359 27.599 28.034 28.103 28.024
本文
算法
27.970 28.168 27.896 28.376 28.102
28.130 28.451 27.937 28.257 28.193
28.186 28.076 28.032 28.134 28.107
), ArticleFig(id=1205909369410089535, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908299053523829, language=CN, label=表3, caption=

CT图像去噪性能比较

, figureFileSmall=null, figureFileBig=null, tableContent=
方法 PSNR/dB 平均值/dB
文献[5]
算法
27.651 26.893 28.354 28.257 27.789
27.685 27.189 27.751 28.138 27.691
28.359 27.599 28.034 28.103 28.024
本文
算法
27.970 28.168 27.896 28.376 28.102
28.130 28.451 27.937 28.257 28.193
28.186 28.076 28.032 28.134 28.107
)], 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.1671-1815.2308335, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2308335, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2308335, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2308335, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于小波去噪神经网络在数字岩心的应用
收藏切换
PDF下载
何田素 1 , 李玮 1, 2, * , 盖京明 1 , 邹林浩 1 , 赵欢 1, 2 , 焦圣杰 1 , 谢晓蕊 1
科学技术与工程 | 论文·自动化技术、计算机技术 2025,25(1): 270-277
收起
收藏切换
科学技术与工程 | 论文·自动化技术、计算机技术 2025, 25(1): 270-277
基于小波去噪神经网络在数字岩心的应用
全屏
何田素1 , 李玮1, 2, * , 盖京明1, 邹林浩1, 赵欢1, 2, 焦圣杰1, 谢晓蕊1
作者信息
  • 1.东北石油大学石油工程学院, 大庆 163318
  • 2.油气钻完技术国家工程研究中心, 大庆 163318
  • 何田素(1997—),男,汉族,安徽淮南人,硕士研究生。研究方向:计算机视觉。E-mail:

通讯作者:

* 李玮(1979—),男,汉族,黑龙江大庆人,博士,教授。研究方向:扭力冲击破岩机理及工具、智能钻井理论与工艺软件。E-mail:
Application of Wavelet Denoising Neural Network in Digital Core
Tian-su HE1 , Wei LI1, 2, * , Jing-ming GAI1, Lin-hao ZOU1, Huan ZHAO1, 2, Sheng-jie JIAO1, Xiao-rui XIE1
Affiliations
  • 1. School of Petroleum Engineering, Northeast Petroleum University, Daqing 163318, China
  • 2. Oil and Gas Drilling Completion Technology National Engineering Research Center, Daqing 163318, China
出版时间: 2025-01-08 doi: 10.12404/j.issn.1671-1815.2308335
文章导航
收藏切换

以鄂尔多斯盆地某区块的砂泥夹层岩心为研究对象,使用基于小波变换的去噪神经网络(denoising neural network based on wavelet transformation,DWTNet)对于岩心的图像进行去噪研究。该方法的评断结果采用峰值信噪比(peak signal to noise ratio,PSNR)和去噪后的图像结果进行了对比。研究表明,利用DWTNet在测试集YX1、YX2测试所提出的算法,并与EGDNet等去噪算法进行对比,PSNR在噪声为25、50、75 dB时,高于EGDNet算法0.527、0.418、1.1 dB。所提的算法在峰值信噪比等指标均高于其他算法;并在视觉效果上其处理得到的图像也更加清晰。方法的提出对于孔隙度、平均体积比表面积、平均曲率计算等都有着非常重要的意义。

数字岩心技术  /  岩心  /  CT扫描  /  岩石特性  /  神经网络  /  去噪

Based on the sand-mud interlayer core of a block in Ordos Basin, denoising neural network based on wavelet transformation (DWTNet) was used to denoise the core image. The evaluation of this method was carried out by comparing the peak signal-to-noise ratio (PSNR) and the post-denoising image outcomes. The investigation reveals that by applying the DWTNet denoising algorithm to the test sets YX1 and YX2, and contrasting it with other denoising algorithms such as EGDNet, the PSNR values at noise levels of 25, 50, and 75 dB are respectively 0.527, 0.418, and 1.1 dB higher than those achieved by the EGDNet algorithm. The proposed algorithm surpasses others in terms of metrics including peak signal to noise ratio(PSNR), and visually, the resulting images processed by it exhibit enhanced clarity. The introduction of this method holds substantial significance for the calculation of parameters like porosity, mean specific surface area, mean curvature, among other rock properties, thereby advancing the capabilities in digital core technology, CT scanning analysis, and understanding of rock characteristics.

digital core technology  /  core samples  /  CT scanning  /  rock properties  /  neural network  /  noise reduction
何田素, 李玮, 盖京明, 邹林浩, 赵欢, 焦圣杰, 谢晓蕊. 基于小波去噪神经网络在数字岩心的应用. 科学技术与工程, 2025 , 25 (1) : 270 -277 . DOI: 10.12404/j.issn.1671-1815.2308335
Tian-su HE, Wei LI, Jing-ming GAI, Lin-hao ZOU, Huan ZHAO, Sheng-jie JIAO, Xiao-rui XIE. Application of Wavelet Denoising Neural Network in Digital Core[J]. Science Technology and Engineering, 2025 , 25 (1) : 270 -277 . DOI: 10.12404/j.issn.1671-1815.2308335
数字岩心技术是分析微观孔隙结构、岩石物理特性以及研究微观渗流规律的重要方法,已广泛用于非常规油气藏岩石物理特性和微纳米尺度流动规律研究[1]。目前地层油藏孔隙复杂且多样,对开采油气造成了一定的困难,且目前的去噪还存在不适定的问题,造成了很大的挑战性。
近些年来,对于石油开采的要求更加精细,所以对岩心微观孔隙结构、岩石物理特性以及研究微观渗流规律的研究现在已成为一个关键的任务。目前对于复杂的微观裂缝、结构、岩石的物理特性的研究,对于图像的清晰度有着非常高的要求。清晰的图像对于实现数字岩心重构,应用于岩心的微观裂缝研究等有着重要的作用。Chen等[2]研究了CycleGAN模型提高砂岩微米岩心图像的分辨率的性能,研究表明生成对抗神经网络具有较好的提高数字岩心图像效果。裴利强[3]对不同分辨率切片进行去噪平滑等预处理工作后采用最大类间方差法求得最佳阈值,同时根据孔隙度对阈值进行调整得到最终分割阈值对切片进行分割,得到岩心孔隙骨架二值图。Yan等[4]利用CT扫描得到的图像进行滤波处理,可以对于后续的孔隙、孔喉进行三维空间的计算。虽然文献[5-7]的算法都可以进行去噪,但是对于去噪不够彻底,仅仅是“一次性的”,去噪之后便会结束,得到去噪后的图像会残留些许噪声;对于边缘纹理部分不能很好地保留,去噪性能没有“曲线性”,会导致去噪图像过度平滑。这些方法对于分析岩心微观孔隙结构、岩石物理特性以及研究微观渗流规律还达不到标准,很容易导致后续的计算产生误差,数值计算之间会产生差值,无法做到精确性。
目前数字岩心技术采用的去噪方法大多数为滤波函数去除噪声,一般为均值滤波、高斯滤波、中值滤波等方法[5,7-8]。这些方法无法在保留细节的同时去除噪声,而对于小波阈值去噪也存在局限性。硬阈值函数和软阈值函数都无法对于数字岩心技术的CT图像后续的重构提供一个很好的去噪方法,改进的小波阈值函数对于CT图像的真实噪声也不能很好地在兼顾保留边缘细节的同时去除噪声[7,9-11];基于深度学习的图像去噪方法虽然有很多优点,但是去噪会存在“杀死”的现象,且在人工设置超参数和依赖知识对于图像的理解方面需要更多的时间和精力,而对于真实噪声则需要复杂且多样的优化算法。
对于以上问题,现对小波函数和深度学习进行改进,在深度学习神经网络中加入小波变换的思想。由于小波变换是可逆的,且具有多分辨率分析和时域细分的算法,有利于自适应调整软阈值。在去噪方面,使用噪声估计网络从图像的估计噪声水平出发,根据噪声水平自适应地调整去噪网络中的软阈值,并根据噪声结果判断是否进行去噪,对于明确油藏微观孔隙结构特征与渗流机理对油藏的影响有着重要的作用。在岩心边缘部分的处理方面,设计边缘损失函数使得图像在去噪的同时保留更多边缘特征。
基于小波变换的去噪神经网络(DWTNet)结合了卷积神经网络(convolutional neural networks,CNN)学习能力强的特点,此网络的结构采用编码器-子网络-解码器。在设计的网络中包括小波信号增强模块、小波网络分解模块、小波网络重构模块、小波噪声估计网络。在编码器、解码器结构中,用平稳小波和逆平稳小波,在进行分解时采用haar小波基,用以代替U-Nets结构中的上采样和下采样。小波信号增强阶段,可以对于提取后的特征进行信号增强处理,获取的局部特征和全局特征有着明显的关键信息;小波网络分解阶段进行小波分解,并在分解时采用haar作为小波基;小波网络重构阶段将分解后的高频和低频信息进行重构,以获得更加清晰的图像。小波噪声估计子网络则是对于获得的图像进行噪声估计,若是图像存在噪声,则再次进行去噪。
图1所示,DWTNet网络在解码器阶段将输入的噪声图像进行二进小波变换(discrete wavelet transform,DWT)和卷积块操作,还原噪声图像的原始数据,用来获取图像中的高频(CD)和低频(CA)信息。采用小波信号增强模块、小波网络分解模块、小波网络重构模块以及小波噪声估计子网络来对于图像的高频和低频信息进行处理,以防止图像在分解后造成信息丢失和边缘纹理部分没有细致处理。
小波信号增强模块是在提取后的特征进行细节和纹理部分增强处理,在文本中用于增强高频(CD)和低频(CA)信息特征。在DWTNet网络可连续对于去噪图像信息提取特征,该模块类似于一个双支路四层残差密集块,前面的每一层的输出使用链接可对下一层进行跳跃链接,并输出到下一层。在模块高频(CD),采用3×3卷积核以获得更细节信息;在低频(CA)模块,采用5×5卷积核以获得模块中的一些信息,并对于低频有了很好的信息辅助作用。在该模块的所有卷积核都只保留了修正线性单元(rectified linear unit,ReLU)激活函数,所得到的信息具有尺度均匀属性。小波信号增强模块网络结构如图2所示。
图3所示,为了防止在图像重构时,将噪声带入图像,在小波网络分解模块使用haar作为小波基,在分解后得到的高频(CD)和低频(CA)信息进行增强图像中细节纹理部分和减少去噪后的噪声部分。将增强后的水平(LH)、垂直(HL)、对角线(HH)的分量信息插入到小波网络中,在此网络进行边缘纹理和细节部分的处理,构造出LH'、HL'、HH'。最后再与LL分量信息运算来获取新的特征。具体如式(1)所示。
L H ' = L H + L L H H ' = H H + L L H L ' = H L + L L
在小波噪声子网络中,该子网络对于噪声进一步测试,根据噪声水平自适应调整软阈值,用以实现更高水平的去噪。在根据噪声问题,该子网络在通过估计噪声后判断是否进行再次去噪。从U-Nets的图像去噪得到启发[12],提出一个小波噪声估计子网络,用以实现图像去噪。与文献[8]不同的是,迭代算法从输入噪声图像中选择低秩补丁,并将噪声水平估计为所选低秩补丁的协方差矩阵的最小特征值,与用于推断噪声水平的CNN相比[13],这种基于模型的方法可以提供更多可解释的结果和鲁棒的泛化能力。提出的噪声估计网络是在Pytorch中通过奇异值分解(singular value decomposition,SVD)使用反向传播。网络如图4所示,输入图像被划分为多个面片,代替迭代地选择低秩补丁,再使用选择网络(squeeze-and-excitation networks,SENet),用以估计每个贴片的标量权重。SENet做软选择,将学习大权重分配给低秩补丁,反之亦然。
图5所示,对图像进行初步分解,使用P操作做出预测,使用U操作进行更新。而对于在更大尺度上,则是卷积层中的滤波器进行上采样,用以模仿小波理论中用以实现小波变换[14-16];对于分裂算子和冗余可逆线性算子,会导致冗余分解,可以通过对细节系数应用不可逆的去噪网络来实现稀疏性,但是仅仅去除噪声。在预测和更新后通过原始特征和纹理细节部分进行拼接起来,对高频和低频的细节进行增强,可以使图像的细节更加丰富。对于此可以应用稀疏驱动的去噪网络,通过用成对的噪声和干净的图像训练网络,获得网络稀疏细节系数,同时也对于图像保留了粗糙部分的基本信息。对于噪声不一致问题,设计了网络用以估计噪声方差结合图4噪声网络得到的评估出的噪声σ2,对于噪声去噪的问题自适应地调整,用以代替小波变换中的软阈值。
为了更好地处理边缘纹理和图像细节,将分解后的图像信息与网络中的参数结合起来,再通过损失函数进行反向调节[17-19]。将U-Nets与小波去噪的“软阈值”结合用于适应图像中的噪声水平σN,对于具有较大的噪声水平图像,软阈值将会进行调整,从而进行更有效的去噪。通过噪声水平对于调整的软阈值,可以实现更好的效果,与没有偏置项并且表达能力有限的BF-CNN不同,所提出的去噪网络具有相对于噪声水平动态调整软阈值[20-21]。对于单个噪声σ,使用U-Net的参数进以优化训练噪声水平,当测试的噪声水平σT < σN,软阈值进行动态调整,进而让软阈值对U-Net由收缩函数变为扩张函数。因此去噪损失函数设计为
$L_{a}=\frac{1}{A B C} \sum_{a=1}^{A} \sum_{b=1}^{B} \sum_{c=1}^{C}\left\|\boldsymbol{P}_{b, c}^{a}\right\|_{S}+\left\|\boldsymbol{U}_{b, c}^{a}\right\|_{S}$
式(2)中:|| ||S为矩阵的谱范数;abc为各个阶段进行的步骤; P b , c a U b , c a为当软阈值被设置为0时,进行调整的滤波器。
对于岩心的微观孔隙结构,岩心图像对精细特征的依赖性较高,为解决这一问题,提出了一种边缘损失函数。边缘模块Fb的学习过程可以表示为
Fb=eside
式(3)中:eside为边缘模块不同尺度的侧输出边缘图。
在图像边缘图像真值中,大多数的像素点是岩心的像素点,即不是边缘像素点,就无法存在对称性,则边缘模块采用二分类平衡交叉熵损失函数,此函数通过引用∂进行优化不对称性。
Lb=-∂ j e + l g e j-(1-∂) j e - l g e j, e j=1,W,w
式(4)中:W为特征提取网络的权重;w为网络训练权重;e+为样本图像真实标签在像素点j处为边缘值,e- 为样本图像真实标签在像素点j处为非边缘值; e j为网络在j处的预测值;(1-∂)为边缘真值图像中非边缘像素点与总像素点之间的比值。即损失函数Lc
Lc(W,w)= i = 1 Ls(W,ws)+Lf(W,wf)
Ls(W,ws)=l(w,ws)
Lf(W,wf)=l(W,wf)
式中:Ls为不同输出边缘图es与边缘真值e之间的二分类平衡交叉熵损失; Lf为不同尺度侧输出融合后的边缘图像ef与边缘真值e之间的二分类平衡交叉熵损失;ws为不同分支的权重;wf为融合后输出结果的训练权重。
DWTNet算法损失函数定义为去噪损失函数与边缘损失函数之和,即
L=La+Lc
实验训练的数据集为LZR,测试的数据集为PDB,其中用于训练的为400幅,测试的为40幅。用以实验和测试的每幅图像大小为512像素×512像素。采用的测试集和数据集均为富县某区块的岩心,将测试集和数据集命名为YX1,YX2,YX3,YX4。采用ADAM算法优化损失函数,批处理大小设置为16,初始学习率大小为0.001。实验采用的计算机的操作系统为Windows 10,CPU配置为Core i5,GPU为Nvidia GTX1050ti。实验采用的软件为PyCharm,Python版本为3.8,实验的训练和测试的框架为PyTorch。
为了验证模型的泛化能力和实用价值,实验采用峰值信噪比(peak signal to noise ratio,PSNR)和均方误差(mean squared error, MSE)作为评价标准;PSNR是一种评价图像的客观的标准,MSE反映估计量与被估计量之间差异程度的一种度量;结构相似性指数(structure similarity index measure,SSIM)是一种用以衡量两张数位影像相似程度的指标。PSNR、MSE、SSIM被分别定义如下。
$\operatorname{PSNR}=10 \lg \left(\frac{\mathrm{MAX}^{2}}{\mathrm{MSE}}\right)$
$\operatorname{MSE}=\frac{1}{m n} \sum_{i=0}^{m-1} \sum_{j=0}^{n-1}\|\boldsymbol{I}(i, j)-\boldsymbol{K}(i, j)\|^{2}$
SSIM(X,Y)= 2 μ X μ Y + C 1 μ X 2 + μ Y 2 + C 1 2 σ X σ Y + C 2 σ X 2 + σ Y 2 + C 2× μ X Y + C 3 μ X + μ Y + C 3
式中:I为处理后图像;K为真实图像;ij均为像素点;MAX为图像上像素点的最大数值,通常定义为1或者255;μXμY分别为图像中XY的均值;σXσY分别为图像中XY的方差;σxy为两张图像的协方差;C1C2C3为3个常数。
在高斯白噪声环境下进行实验,为了验证DWTNet对于高斯白噪声去除效果,与小波变换算法、文献[5]算法、文献[6]算法和文献[7]算法对比,图像为鄂尔多斯盆地区块的不同井的岩心,数据集分别为LZR表1所示为5种算法在3种数据集上分别添加25、50、75 dB噪声等级时所得去噪的PSNR和MSE指标。可以看出,DWTNet算法在噪声等级下PSNR和MSE均高于对比的算法,且本文的方法在不同的数据集下的对比产生的差值不同。可以看出当噪声为75 dB时,与对比的算法在数据集YX1,PSNR有很好的性能,远高于小波变换的PSNR,高于文献[5]所产生的PSNR,对于文献[6]、文献[7]也有着很好的性能。为了更清楚地表示出与对比算法产生的PSNR差值,因此,做出对比图以更加明确地说明。
图6表1表2可以看出,文献[5]算法、文献[6]算法、文献[7]算法均为近些年去噪效果比较好的算法,本文算法与对比算法相比有着很好的效果,且PSNR和SSIM在大多数情况下为最高,这是因为本文在对于细节处理部分更加显著,且在对比文献[5]中PSNR分别高出0.527、0.418、1.1 dB。当与传统的小波变换算法对比,有着很好的性能。随着噪声增加,本文算法与基准算法的PSNR差值变大,说明本文算法去噪敏感性更高,算法性能更明显;且对于噪声的增加,本文算法有着很好的调整性,说明对于噪声估计网络自适应调整软阈值有着很好的性能。在SSIM比较上,本文算法平均为0.924,与文献[5]算法相比提高了0.015。说明本文算法的去噪网络有着很好的性能,且在去噪后的图像有着很高的相似度,对于细节纹理部分也有着很好的保留。
通过图7可以看出,噪声图像经过文献[5]算法、文献[6]算法、文献[7]算法得到去噪后图像还存在不同程度的噪声残留,对于边缘纹理和细节部分没有做出调整;本文算法在去噪视觉效果要好于所对比的算法,且PSNR(峰值信噪比)略高于文献[5]算法;从视觉效果看,本文算法在岩心的边缘部分去噪有很好的效果。
为了验证本文算法在不同噪声以及对于图像的去噪效果,选用的图像为非测试集中岩心扫描的CT噪声图像,记为1#~4#。由于在CT扫描后每幅图中存在的噪声不同,且真实噪声复杂,没有真值,对比其他图像会存在一定的去噪难度,因为真实的噪声会有依赖性,且在图像上分布没有规律,对比算法的去噪结果如图8所示。
在对比实验中,尽管图像存在真实噪声,但是本文算法得到的去噪效果图仍然有着很好的视觉效果,仍然保留着边缘模块纹理部分,没有过度去除;表3显示了本文方法与目前最好方法的PSNR结果。在数据集平均PSNR比较,本文方法相比其他算法,PSNR分别增益了0.313 、0.502、0.083 dB,本文算法的去噪网络在软阈值调整有着很好的效果。说明本文模型也可以在真实噪声中取得不错的去噪效果,另一方面说明本文算法的去噪网络对于噪声的自适应调整有着不错的能力。
(1)提出了DWTNet对于岩心进行去噪的方法,可以有效地对岩心进行去噪,去噪后的结果可以更好展现出裂缝和岩心面。
(2)基于小波去噪的思想用神经网络中进行改进,使用了噪声去噪网络,对于噪声估计网络“给”出的噪声进行多次去噪,以便还原出清晰的图像。
(3)设计边缘损失函数对于边缘和纹理部分没有“杀死”,保留了细节部分;对于微观裂缝、结构、岩石的物理特性可以做到细致的研究。
(4)对于数字岩心图像的重构给出了一个合适的方法,以便用于对孔隙率、孔的比表面积、平均曲率和连通性的研究。
(5)采用岩石的裂缝面三维重构对水力压裂实验分析时,便于裂缝起裂和扩展规律的研究。
  • 国家自然科学基金(52274005)
参考文献 引证文献
排序方式:
[1]
王付勇, 赵久玉. 基于深度学习的数字岩心图像重构及其重构效果评价[J]. 中南大学学报(自然科学版), 2022, 53(11): 4412-4424.
Wang Fuyong, Zhao Jiuyu. Digital core image reconstruction based on deep learning and its reconstruction effect evaluation[J]. Journal of Central South University (Natural Science Edition), 2022, 53(11): 4412-4424.
[2]
Chen H G, He X H, Teng Q Z, et al. Superresolution of real-world rock microcomputed tomography images using cycle-consistent generative adversarial networks[J]. Physical Review E, 2020, 101: 023305.
[3]
裴利强. 多分辨率数字岩心的表示与生成[D]. 青岛: 中国石油大学(华东), 2020.
Pei Lijiang. Representation and generation of multi-resolution digital cores[D]. Qingdao: China University of Petroleum (East China), 2020.
[4]
Yan G G, Yan W D, Yuan Y Z, Research on the method of evaluating the pore throat structure of rock microscopically based on the 3D pore network model of digital core[J]. International Journal of Petroleum Technology, 2022, 44-53.
[5]
刘一畅, 马伟, 徐士彪, 等. 基于卷积神经网络的边缘保真图像去噪算法[J]. 计算机辅助设计与图形学学报, 2020, 32(11): 1822-1831.
Liu Yichang, Ma Wei, Xu Shibiao, et al. Edge fidelity image denoising algorithm based on convolutional neural networks[J]. Journal of Computer Aided Design and Graphics, 2020, 32(11): 1822-1831.
[6]
石小涵. 基于卷积神经网络和小波变换的图像去噪算法[D]. 西安: 西安建筑科技大学, 2020.
Shi Xiaohan. Image denoising algorithm based on convolutional neural network and wavelet transform[D]. Xi’an: Xi’an University of Architecture and Technology, 2020.
[7]
林煌伟, 陈钧荣, 牛玉贞. 基于循环神经网络的多阶段图像去噪方法[J]. 小型微型计算机系统, 2022, 43(1): 84-90.
Lin Huangwei, Chen Junrong, Niu Yuzhen. A multi-stage image denoising method based on recurrent neural networks[J]. Small Micro Computer System, 2022, 43(1): 84-90.
[8]
王坤, 叶招君. 基于小波空洞残差U-Net的红外图像去条纹噪声方法[J]. 光学技术, 2022, 48(5): 616-626.
Wang Kun, Ye Zhaojun. Infrared image denoising method based on wavelet cavity residual U-Net[J]. Optical Technology, 2022, 48(5): 616-626.
[9]
王力, 李小霞, 秦佳敏, 等. 级联离散小波多频带分解注意力图像去噪方法[J]. 计算机应用研究, 2024, 41(1): 288-295.
Wang Li, Li Xiaoxia, Qin Jiamin, et al. Cascaded discrete wavelet multi band decomposition attention image denoising method[J]. Computer Application Research, 2024, 41(1): 288-295.
[10]
姜旭, 赵荣彩, 刘勇杰, 等. 基于改进U-Net神经网络的图像去噪算法[J]. 科学技术与工程, 2022, 22(9): 3629-3635.
Jiang Xu, Zhao Rongcai, Liu Yongjie, et al. Image denoising algorithm based on improved U-Net neural network[J]. Science Technology and Engineering, 2022, 22(9): 3629-3635.
[11]
吴学礼, 王壮壮, 习炳权, 等. 基于小波自适应阈值方法的探地雷达去噪[J]. 科学技术与工程, 2023, 23(11): 4686-4692.
Wu Xueli, Wang Zhuangzhuang, Xi Bingquan, et al. Ground penetrating radar denoising based on wavelet adaptive threshold method[J]. Science Technology and Engineering, 2023, 23(11): 4686-4692
[12]
Liu X, Tanaka M, Okutomi M. Single-image noise level estimation for blind denoising[J]. IEEE Transactions on Image Processing, 2013, 22(12): 5226-5237.
[13]
Helou M E, Susstrunk S. Blind universal Bayesian image denoising with Gaussian noise level learning[J]. IEEE Transactions on ImageProcessing, 2020, 29: 4885-4897.
[14]
Dinh L, Krueger D, Bengio Y. NICE: non-linear independent components estimation[J]. ArXiv Preprint ArXiv, 2014: 1410.8516.
[15]
Dinh L, Sohl-Dickstein J, Bengio S, Density estimation using real NVP[J]. ArXiv Preprint ArXiv, 2016: 1605.08803.
[16]
Gomez A N, Ren M, Urtasun R, et al. The reversible residual network: back propagation without storing activations[J]. ArXiv Preprint ArXiv, 2017: 1707.04585.
[17]
Jacobsen J H, Smeulders A W, Oyallon E. I-RevNet: deep invertible networks[J]. ArXiv, 2018: 1802.07088.
[18]
Xiao M, Zheng S, Liu C, et al. Invertible image rescaling[J]. ArXiv, 2020: 2005.05650.
[19]
Donoho D L, Johnstone I M. Ideal spatial adaptation by wavelet shrinkage[J]. Biometrika, 1994, 81(3): 239520.
[20]
Wang H T, Wang L, Lai F Q, et al. Investigation of image segmentation effect on the accuracy of reconstructed digital core models of coquina carbonate[J]. Applied Geophysics, 2020, 17(4): 501-512.
[21]
周联敏, 周冬明, 杨浩. 结合迁移学习的真实图像去噪算法[J]. 科学技术与工程, 2022, 22(34): 15237-15244.
Zhou Lianmin, Zhou Dongming, Yang Hao. A real image denoising algorithm combining transfer learning[J]. Science Technology and Engineering, 2022, 22(34): 15237-15244.
2025年第25卷第1期
PDF下载
286
109
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2308335
  • 接收时间:2023-10-25
  • 首发时间:2025-07-29
  • 出版时间:2025-01-08
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2023-10-25
  • 修回日期:2024-10-08
基金
国家自然科学基金(52274005)
作者信息
    1.东北石油大学石油工程学院, 大庆 163318
    2.油气钻完技术国家工程研究中心, 大庆 163318

通讯作者:

* 李玮(1979—),男,汉族,黑龙江大庆人,博士,教授。研究方向:扭力冲击破岩机理及工具、智能钻井理论与工艺软件。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2308335
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