Article(id=1153992996853899594, tenantId=1146029695717560320, journalId=1146123222451335185, issueId=1153992986405888144, articleNumber=1671-1807(2025)07-0009-10, orderNo=null, doi=null, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1726934400000, receivedDateStr=2024-09-22, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1753062970603, onlineDateStr=2025-07-21, pubDate=1744214400000, pubDateStr=2025-04-10, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1753062970603, onlineIssueDateStr=2025-07-21, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1753062970603, creator=13701087609, updateTime=1753062970603, updator=13701087609, issue=Issue{id=1153992986405888144, tenantId=1146029695717560320, journalId=1146123222451335185, year='2025', volume='25', issue='7', pageStart='1', pageEnd='372', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1753062968112, creator=13701087609, updateTime=1753063464821, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1153995069800567734, tenantId=1146029695717560320, journalId=1146123222451335185, issueId=1153992986405888144, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1153995069800567735, tenantId=1146029695717560320, journalId=1146123222451335185, issueId=1153992986405888144, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=9, endPage=18, ext={EN=ArticleExt(id=1153992998569369990, articleId=1153992996853899594, tenantId=1146029695717560320, journalId=1146123222451335185, language=EN, title=Optimization Method and Application of Production Optimization Method for Waterflood Oil Reservoirs Based on an Ensemble Surrogate Model: In Bruges Oilfield as an Example, columnId=1151876674645226399, journalTitle=Science Technology and Industry, columnName=Technology Innovation, runingTitle=null, highlight=null, articleAbstract=

Production optimization is a key component of closed-loop reservoir management, aimed at maximizing economic benefits by fully exploiting reservoir potential through the identification of optimal injection and production parameter schemes. The use of numerical simulators during the search for the optimal solution significantly increases time costs, making it challenging to rapidly determine the best scheme, despite its important engineering implications. An objective function for production optimization in waterflood reservoirs was constructed based on factors such as the reservoir numerical simulation model, optimized time steps, production and injection well control strategies, reservoir responses, and cost and profit parameters. Research was conducted on the method of using surrogate models to replace numerical simulators in production optimization, based on sampling criteria for the surrogate model. In order to address the lack of physical significance in surrogate models and the difficulty in achieving the same precision as numerical simulators during optimization, a relationship for an ensemble surrogate model was established. Validation results on two reservoir models, three-channel and Egg, show that the proposed ensemble surrogate model optimization method improves economic benefits by 4.81% and 4.75% respectively, compared to conventional optimization methods across all tested reservoir models. In order to verify the application effect of the proposed method in the actual oilfield field management scenario, the Bruges oilfield is taken as an example to carry out the test. The proposed integrated agent model optimization method can increase the economic benefit by 2.45% compared with the conventional optimization method. This proves that the proposed method can achieve satisfactory results in solving the problem of injection and production optimization in large-scale reservoirs.

, correspAuthors=null, 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=Mengqi JI, Lei ZHANG, Libin DU, Xiaomei ZHANG, Zitan ZHANG), CN=ArticleExt(id=1153993063769826047, articleId=1153992996853899594, tenantId=1146029695717560320, journalId=1146123222451335185, language=CN, title=基于集成代理模型的水驱油藏注采优化方法及应用——以布鲁日油田为例, columnId=1151876674787832737, journalTitle=科技和产业, columnName=科技创新, runingTitle=null, highlight=null, articleAbstract=

注采优化是闭环油藏管理的重要组成部分,其目的是通过寻找最优的注采参数方案来充分开发油藏潜力,以实现最大的经济效益。在搜索最优方案过程中,数值模拟器的使用极大地增加了时间成本,快速确定最优方案难度大但具有重要工程意义。基于油藏数值模拟模型、优化的时间步数、生产井和注水井控制方式、储层响应以及成本和利润参数等构建水驱油藏注采优化目标函数;根据代理模型采样准则,对代理模型替代数值模拟器参与注采优化的方法进行研究;为解决代理模型缺乏物理意义、寻优过程中难以做到与数值模拟器相同精度的问题,建立集成代理模型关系式。在三通道、Egg两个油藏概念模型上的验证结果表明,提出的集成代理模型优化方法能够在测试的两个概念模型上较常规优化方法经济效益分别提高4.81%、4.75%。为了验证所提方法在实际油田现场管理场景的应用效果,以布鲁日油田为例开展测试。提出的集成代理模型优化方法较常规优化方法经济效益可提高2.45%,可以在解决大规模油藏注采优化问题上取得令人满意的结果。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=H4bYnsVmB6GYx0+jweIrpg==, magXml=WKasnD5PzeAmY2UZ1u1ZTg==, pdfUrl=null, pdf=bu5RqjrTvpy12LRBht5EdA==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=xW+UuLb5PjLai5EmJS+DZQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=e/TxEnNupUPt004u1jmDpg==, mapNumber=null, authorCompany=null, fund=null, authors=

暨梦琪(1990—),女,福建建阳人,工程师,研究方向为智能注水;

张雷(1974—),男,山东威海人,硕士,研究员,研究方向为采油技术;

杜立滨(1974—),男,山东滨州人,副研究员,研究方向为油藏开发;

张小玫(1993—),女,山东东营人,硕士,助理研究员,研究方向为注水工艺技术;

张紫檀(1990—),男,山东东营人,硕士,助理研究员,研究方向为油田注水工艺和智能化井下工具。

, authorsList=暨梦琪, 张雷, 杜立滨, 张小玫, 张紫檀)}, authors=[Author(id=1199769401571505139, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, orderNo=0, 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=1199769401747664904, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, authorId=1199769401571505139, language=EN, stringName=Mengqi JI, firstName=Mengqi, middleName=null, lastName=JI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Sinopec Shengli Oilfield Branch, Petroleum Engineering Technology Research Institute, Dongying 257000, Shandong, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1199769401919631383, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, authorId=1199769401571505139, language=CN, stringName=暨梦琪, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中国石化胜利油田分公司石油工程技术研究院, 山东 东营 257000, bio={"content":"

暨梦琪(1990—),女,福建建阳人,工程师,研究方向为智能注水;

"}, bioImg=null, bioContent=

暨梦琪(1990—),女,福建建阳人,工程师,研究方向为智能注水;

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1199769401319846878, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, xref=null, ext=[AuthorCompanyExt(id=1199769401353401310, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, companyId=1199769401319846878, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Sinopec Shengli Oilfield Branch, Petroleum Engineering Technology Research Institute, Dongying 257000, Shandong, China), AuthorCompanyExt(id=1199769401370178527, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, companyId=1199769401319846878, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国石化胜利油田分公司石油工程技术研究院, 山东 东营 257000)])]), Author(id=1199769403169533993, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1199769403396026435, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, authorId=1199769403169533993, language=EN, stringName=Lei ZHANG, firstName=Lei, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Sinopec Shengli Oilfield Branch, Petroleum Engineering Technology Research Institute, Dongying 257000, Shandong, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1199769403555410002, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, authorId=1199769403169533993, language=CN, stringName=张雷, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中国石化胜利油田分公司石油工程技术研究院, 山东 东营 257000, bio={"content":"

张雷(1974—),男,山东威海人,硕士,研究员,研究方向为采油技术;

"}, bioImg=null, bioContent=

张雷(1974—),男,山东威海人,硕士,研究员,研究方向为采油技术;

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1199769401319846878, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, xref=null, ext=[AuthorCompanyExt(id=1199769401353401310, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, companyId=1199769401319846878, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Sinopec Shengli Oilfield Branch, Petroleum Engineering Technology Research Institute, Dongying 257000, Shandong, China), AuthorCompanyExt(id=1199769401370178527, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, companyId=1199769401319846878, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国石化胜利油田分公司石油工程技术研究院, 山东 东营 257000)])]), Author(id=1199769403685433436, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, 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=1199769403844817000, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, authorId=1199769403685433436, language=EN, stringName=Libin DU, firstName=Libin, middleName=null, lastName=DU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Sinopec Shengli Oilfield Branch, Petroleum Engineering Technology Research Institute, Dongying 257000, Shandong, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1199769403979034739, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, authorId=1199769403685433436, language=CN, stringName=杜立滨, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中国石化胜利油田分公司石油工程技术研究院, 山东 东营 257000, bio={"content":"

杜立滨(1974—),男,山东滨州人,副研究员,研究方向为油藏开发;

"}, bioImg=null, bioContent=

杜立滨(1974—),男,山东滨州人,副研究员,研究方向为油藏开发;

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1199769401319846878, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, xref=null, ext=[AuthorCompanyExt(id=1199769401353401310, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, companyId=1199769401319846878, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Sinopec Shengli Oilfield Branch, Petroleum Engineering Technology Research Institute, Dongying 257000, Shandong, China), AuthorCompanyExt(id=1199769401370178527, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, companyId=1199769401319846878, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国石化胜利油田分公司石油工程技术研究院, 山东 东营 257000)])]), Author(id=1199769404117446779, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, 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=1199769404264247432, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, authorId=1199769404117446779, language=EN, stringName=Xiaomei ZHANG, firstName=Xiaomei, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Sinopec Shengli Oilfield Branch, Petroleum Engineering Technology Research Institute, Dongying 257000, Shandong, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1199769404381687961, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, authorId=1199769404117446779, language=CN, stringName=张小玫, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中国石化胜利油田分公司石油工程技术研究院, 山东 东营 257000, bio={"content":"

张小玫(1993—),女,山东东营人,硕士,助理研究员,研究方向为注水工艺技术;

"}, bioImg=null, bioContent=

张小玫(1993—),女,山东东营人,硕士,助理研究员,研究方向为注水工艺技术;

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1199769401319846878, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, xref=null, ext=[AuthorCompanyExt(id=1199769401353401310, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, companyId=1199769401319846878, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Sinopec Shengli Oilfield Branch, Petroleum Engineering Technology Research Institute, Dongying 257000, Shandong, China), AuthorCompanyExt(id=1199769401370178527, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, companyId=1199769401319846878, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国石化胜利油田分公司石油工程技术研究院, 山东 东营 257000)])]), Author(id=1199769404507517095, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, 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=1199769404671094957, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, authorId=1199769404507517095, language=EN, stringName=Zitan ZHANG, firstName=Zitan, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Sinopec Shengli Oilfield Branch, Petroleum Engineering Technology Research Institute, Dongying 257000, Shandong, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1199769404826284217, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, authorId=1199769404507517095, language=CN, stringName=张紫檀, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中国石化胜利油田分公司石油工程技术研究院, 山东 东营 257000, bio={"content":"

张紫檀(1990—),男,山东东营人,硕士,助理研究员,研究方向为油田注水工艺和智能化井下工具。

"}, bioImg=null, bioContent=

张紫檀(1990—),男,山东东营人,硕士,助理研究员,研究方向为油田注水工艺和智能化井下工具。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1199769401319846878, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, xref=null, ext=[AuthorCompanyExt(id=1199769401353401310, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, companyId=1199769401319846878, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Sinopec Shengli Oilfield Branch, Petroleum Engineering Technology Research Institute, Dongying 257000, Shandong, China), AuthorCompanyExt(id=1199769401370178527, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, companyId=1199769401319846878, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国石化胜利油田分公司石油工程技术研究院, 山东 东营 257000)])])], keywords=[Keyword(id=1199769405153439956, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=EN, orderNo=1, keyword=production optimization), Keyword(id=1199769405392515292, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=EN, orderNo=2, keyword=ensemble surrogate model), Keyword(id=1199769405501567203, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=EN, orderNo=3, keyword=waterflood reservoir), Keyword(id=1199769405639979246, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=EN, orderNo=4, keyword=development strategy), Keyword(id=1199769405853888759, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=CN, orderNo=1, keyword=注采优化), Keyword(id=1199769405992300797, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=CN, orderNo=2, keyword=集成代理模型), Keyword(id=1199769406109741317, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=CN, orderNo=3, keyword=水驱油藏), Keyword(id=1199769406269124880, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=CN, orderNo=4, keyword=开发策略)], refs=[Reference(id=1199769413512688102, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, doi=null, pmid=null, pmcid=null, year=2020, volume=41, issue=3, pageStart=342, pageEnd=347, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=高文君, 殷瑞, 杨静, journalName=石油学报, refType=null, unstructuredReference=高文君, 殷瑞, 杨静. 新型水驱特征曲线的建立及理论基础[J]. 石油学报, 2020, 41(3): 342-347., articleTitle=新型水驱特征曲线的建立及理论基础, refAbstract=null), Reference(id=1199769413583991276, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=2, pageStart=253, pageEnd=260, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=宋来明, 王春秋, 卢川, journalName=石油钻采工艺, refType=null, unstructuredReference=宋来明, 王春秋, 卢川, 等. 数据驱动的复杂油藏注采生产优化技术研究进展[J]. 石油钻采工艺, 2022, 44(2): 253-260., articleTitle=数据驱动的复杂油藏注采生产优化技术研究进展, refAbstract=null), Reference(id=1199769413659488750, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, doi=null, pmid=null, pmcid=null, year=2016, volume=91, issue=null, pageStart=19, pageEnd=32, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=BABAEI M, PAN I, journalName=Computers & Geosciences, refType=null, unstructuredReference=BABAEI M, PAN I. Performance comparison of several response surface surrogate models and ensemble methods for waterinjection optimization under uncertainty[J]. Computers & Geosciences, 2016, 91: 19-32., articleTitle=Performance comparison of several response surface surrogate models and ensemble methods for waterinjection optimization under uncertainty, refAbstract=null), Reference(id=1199769413764346353, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, doi=null, pmid=null, pmcid=null, year=2019, volume=19, issue=26, pageStart=178, pageEnd=185, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=王链, 张亮, 赖枫鹏, journalName=科学技术与工程, refType=null, unstructuredReference=王链, 张亮, 赖枫鹏, 等. 基于替代模型的油藏注采参数多目标优化设计[J]. 科学技术与工程, 2019, 19(26): 178-185., articleTitle=基于替代模型的油藏注采参数多目标优化设计, refAbstract=null), Reference(id=1199769413856621047, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=29, pageStart=12826, pageEnd=12831, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=周志军, 郝玉, journalName=科学技术与工程, refType=null, unstructuredReference=周志军, 郝玉. 春10区块水平井蒸汽吞吐注采参数优化[J]. 科学技术与工程, 2022, 22(29): 12826-12831., articleTitle=春10区块水平井蒸汽吞吐注采参数优化, refAbstract=null), Reference(id=1199769413982450173, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=2, pageStart=524, pageEnd=531, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=李培宇, 黄世军, 柴世超, journalName=科学技术与工程, refType=null, unstructuredReference=李培宇, 黄世军, 柴世超, 等. 断块油藏水平井提液参数优化[J]. 科学技术与工程, 2022, 22(2): 524-531., articleTitle=断块油藏水平井提液参数优化, refAbstract=null), Reference(id=1199769414116667903, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, doi=null, pmid=null, pmcid=null, year=2008, volume=206, issue=1, pageStart=56, pageEnd=69, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=GONG W, CAI Z, JIANG L, journalName=Applied Mathematics and Computation, refType=null, unstructuredReference=GONG W, CAI Z, JIANG L. Enhancing the performance of differential evolution using orthogonal design method[J]. Applied Mathematics and Computation, 2008, 206(1): 56-69., articleTitle=Enhancing the performance of differential evolution using orthogonal design method, refAbstract=null), Reference(id=1199769414213136896, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, doi=null, pmid=null, pmcid=null, year=2022, volume=27, issue=1, pageStart=307, pageEnd=328, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=ZHANG H, SHENG J J, journalName=SPE Journal, refType=null, unstructuredReference=ZHANG H, SHENG J J. Surrogate-assisted multiobjective optimization of a hydraulically fractured well in a naturally fractured shale reservoir with geological uncertainty[J]. SPE Journal, 2022, 27(1): 307-328., articleTitle=Surrogate-assisted multiobjective optimization of a hydraulically fractured well in a naturally fractured shale reservoir with geological uncertainty, refAbstract=null), Reference(id=1199769414313800195, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, doi=null, pmid=null, pmcid=null, year=2012, volume=48, issue=2, pageStart=479, pageEnd=482, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=LEI G, GUO Y, ZHU J, journalName=IEEE Transactions on Magnetics, refType=null, unstructuredReference=LEI G, GUO Y, ZHU J, et al. Sequential subspace optimization method for electromagnetic devices design with orthogonal design technique[J]. IEEE Transactions on Magnetics, 2012, 48(2): 479-482., articleTitle=Sequential subspace optimization method for electromagnetic devices design with orthogonal design technique, refAbstract=null), Reference(id=1199769414406074888, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, doi=null, pmid=null, pmcid=null, year=2000, volume=42, issue=1, pageStart=55, pageEnd=61, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=MCKAY M D, BECKMAN R J, CONOVER W J, journalName=Technometrics, refType=null, unstructuredReference=MCKAY M D, BECKMAN R J, CONOVER W J. A comparison of three methods for selecting values of input variables in the analysis of output from a computer code[J]. Technometrics, 2000, 42(1): 55-61., articleTitle=A comparison of three methods for selecting values of input variables in the analysis of output from a computer code, refAbstract=null), Reference(id=1199769414544486921, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, doi=null, pmid=null, pmcid=null, year=2019, volume=24, issue=2, pageStart=365, pageEnd=379, url=null, language=null, rfNumber=[11], rfOrder=10, authorNames=CAI X, GAO L, LI X, journalName=IEEE Transactions on Evolutionary Computation, refType=null, unstructuredReference=CAI X, GAO L, LI X. Efficient generalized surrogate-assisted evolutionary algorithm for high-dimensional expensive problems[J]. IEEE Transactions on Evolutionary Computation, 2019, 24(2): 365-379., articleTitle=Efficient generalized surrogate-assisted evolutionary algorithm for high-dimensional expensive problems, refAbstract=null), Reference(id=1199769414615790092, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, doi=null, pmid=null, pmcid=null, year=2009, volume=45, issue=1-3, pageStart=50, pageEnd=79, url=null, language=null, rfNumber=[12], rfOrder=11, authorNames=FORRESTER A I, KEANE A J, journalName=Progress in Aerospace Sciences, refType=null, unstructuredReference=FORRESTER A I, KEANE A J. Recent advances in surrogate-based optimization[J]. Progress in Aerospace Sciences, 2009, 45(1-3): 50-79., articleTitle=Recent advances in surrogate-based optimization, refAbstract=null), Reference(id=1199769414703870479, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, doi=null, pmid=null, pmcid=null, year=2021, volume=106, issue=null, pageStart=107380, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=12, authorNames=DONG H, WANG P, CHEN W, journalName=Applied Soft Computing, refType=null, unstructuredReference=DONG H, WANG P, CHEN W, et al. SGOP: surrogate-assisted global optimization using a Pareto-based sampling strategy[J]. Applied Soft Computing, 2021, 106: 107380., articleTitle=SGOP: surrogate-assisted global optimization using a Pareto-based sampling strategy, refAbstract=null), Reference(id=1199769414775173651, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, doi=null, pmid=null, pmcid=null, year=2023, volume=350, issue=null, pageStart=128826, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=13, authorNames=WANG L, YAO Y, LUO X, journalName=Fuel, refType=null, unstructuredReference=WANG L, YAO Y, LUO X, et al. A critical review on intelligent optimization algorithms and surrogate models for conventional and unconventional reservoir production optimization[J]. Fuel, 2023, 350: 128826., articleTitle=A critical review on intelligent optimization algorithms and surrogate models for conventional and unconventional reservoir production optimization, refAbstract=null), Reference(id=1199769414875836950, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, doi=null, pmid=null, pmcid=null, year=2020, volume=90, issue=null, pageStart=103479, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=14, authorNames=PANT M, ZAHEER H, GARCIA-HERNANDEZ L, journalName=Engineering Applications of Artificial Intelligence, refType=null, unstructuredReference=PANT M, ZAHEER H, GARCIA-HERNANDEZ L, et al. Differential evolution: a review of more than two decades of research[J]. Engineering Applications of Artificial Intelligence, 2020, 90: 103479., articleTitle=Differential evolution: a review of more than two decades of research, refAbstract=null), Reference(id=1199769414947140121, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, doi=null, pmid=null, pmcid=null, year=2020, volume=44, issue=3, pageStart=90, pageEnd=97, url=null, language=null, rfNumber=[16], rfOrder=15, authorNames=张凯, 陈国栋, 薛小明, journalName=中国石油大学学报(自然科学版), refType=null, unstructuredReference=张凯, 陈国栋, 薛小明, 等. 基于主成分分析和代理模型的油藏生产注采优化方法[J]. 中国石油大学学报(自然科学版), 2020, 44(3): 90-97., articleTitle=基于主成分分析和代理模型的油藏生产注采优化方法, refAbstract=null), Reference(id=1199769415068774942, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, doi=null, pmid=null, pmcid=null, year=2020, volume=194, issue=null, pageStart=107441, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=16, authorNames=ZHAO X, ZHANG K, CHEN G, journalName=Journal of Petroleum Science and Engineering, refType=null, unstructuredReference=ZHAO X, ZHANG K, CHEN G, et al. Surrogate-assisted differential evolution for production optimization with nonlinear state constraints[J]. Journal of Petroleum Science and Engineering, 2020, 194: 107441., articleTitle=Surrogate-assisted differential evolution for production optimization with nonlinear state constraints, refAbstract=null), Reference(id=1199769415152661023, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, doi=null, pmid=null, pmcid=null, year=2020, volume=185, issue=null, pageStart=106633, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=17, authorNames=CHEN G, ZHANG K, XUE X, journalName=Journal of Petroleum Science and Engineering, refType=null, unstructuredReference=CHEN G, ZHANG K, XUE X, et al. Surrogate-assisted evolutionary algorithm with dimensionality reduction method for water flooding production optimization[J]. Journal of Petroleum Science and Engineering, 2020, 185: 106633., articleTitle=Surrogate-assisted evolutionary algorithm with dimensionality reduction method for water flooding production optimization, refAbstract=null), Reference(id=1199769415240741409, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, doi=null, pmid=null, pmcid=null, year=2021, volume=196, issue=null, pageStart=107988, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=18, authorNames=FARAHI M M, AHMADI M, DABIR B, journalName=Journal of Petroleum Science and Engineering, refType=null, unstructuredReference=FARAHI M M, AHMADI M, DABIR B. Model-based water-flooding optimization using multi-objective approach for efficient reservoir management[J]. Journal of Petroleum Science and Engineering, 2021, 196: 107988., articleTitle=Model-based water-flooding optimization using multi-objective approach for efficient reservoir management, refAbstract=null)], funds=[Fund(id=1199769413302972894, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, awardId=P22023, language=CN, fundingSource=中国石化科技攻关项目(P22023), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1199769401319846878, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, xref=null, ext=[AuthorCompanyExt(id=1199769401353401310, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, companyId=1199769401319846878, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Sinopec Shengli Oilfield Branch, Petroleum Engineering Technology Research Institute, Dongying 257000, Shandong, China), AuthorCompanyExt(id=1199769401370178527, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, companyId=1199769401319846878, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国石化胜利油田分公司石油工程技术研究院, 山东 东营 257000)])], figs=[ArticleFig(id=1199769406545948966, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=EN, label=null, caption=null, figureFileSmall=VYxm1NDCvD0nlZ4nA2DsFQ==, figureFileBig=RhjJYE07L1P/QP6t2yRFrQ==, tableContent=null), ArticleFig(id=1199769407766491444, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=CN, label=图1, caption=LHS示意图, figureFileSmall=VYxm1NDCvD0nlZ4nA2DsFQ==, figureFileBig=RhjJYE07L1P/QP6t2yRFrQ==, tableContent=null), ArticleFig(id=1199769407930069312, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=EN, label=null, caption=null, figureFileSmall=4iQ59p9tH4bjho4uo10SIQ==, figureFileBig=qW5DEmHsxO4solLlIOVXpg==, tableContent=null), ArticleFig(id=1199769408085258565, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=CN, label=图2, caption=RBFN结构示意图, figureFileSmall=4iQ59p9tH4bjho4uo10SIQ==, figureFileBig=qW5DEmHsxO4solLlIOVXpg==, tableContent=null), ArticleFig(id=1199769408194310476, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=EN, label=null, caption=null, figureFileSmall=zadm0rlm7qEnnWyjxIXZTA==, figureFileBig=P76tdsGabzolGU8E+X0kng==, tableContent=null), ArticleFig(id=1199769408307556692, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=CN, label=图3, caption=三通道模型的井位及渗透率场分布

P1~P9为生产井;I1~I4为注水井

, figureFileSmall=zadm0rlm7qEnnWyjxIXZTA==, figureFileBig=P76tdsGabzolGU8E+X0kng==, tableContent=null), ArticleFig(id=1199769408475328856, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=EN, label=null, caption=null, figureFileSmall=Io9ECO+tryWJTK+MsDlDhA==, figureFileBig=g0x7SJGCiKCFcqdNZnoLsg==, tableContent=null), ArticleFig(id=1199769408659878237, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=CN, label=图4, caption=三通道模型实验结果, figureFileSmall=Io9ECO+tryWJTK+MsDlDhA==, figureFileBig=g0x7SJGCiKCFcqdNZnoLsg==, tableContent=null), ArticleFig(id=1199769408810873187, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=EN, label=null, caption=null, figureFileSmall=QzGrCTy4Xs2kOMyOWwTDPQ==, figureFileBig=RyFUxHJhb42+PhwdWpIntg==, tableContent=null), ArticleFig(id=1199769408966062438, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=CN, label=图5, caption=三通道模型生产井的最优井控参数方案, figureFileSmall=QzGrCTy4Xs2kOMyOWwTDPQ==, figureFileBig=RyFUxHJhb42+PhwdWpIntg==, tableContent=null), ArticleFig(id=1199769409083502956, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=EN, label=null, caption=null, figureFileSmall=B7VWT7sv2oqWdoXjPjhlNw==, figureFileBig=Inre/HaDeX6SQDpFluRz9Q==, tableContent=null), ArticleFig(id=1199769409205137775, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=CN, label=图6, caption=三通道模型注水井的最优井控参数方案, figureFileSmall=B7VWT7sv2oqWdoXjPjhlNw==, figureFileBig=Inre/HaDeX6SQDpFluRz9Q==, tableContent=null), ArticleFig(id=1199769409305801075, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=EN, label=null, caption=null, figureFileSmall=UU5Wyz4k15KUK4xKXE19Qw==, figureFileBig=S6oDWtmC/oataoyj8k9DvA==, tableContent=null), ArticleFig(id=1199769409465184634, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=CN, label=图7, caption=三通道模型在最优注采参数下的优化结果, figureFileSmall=UU5Wyz4k15KUK4xKXE19Qw==, figureFileBig=S6oDWtmC/oataoyj8k9DvA==, tableContent=null), ArticleFig(id=1199769409733620099, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=EN, label=null, caption=null, figureFileSmall=G3QUyslpX6W8ESk3tCfx6Q==, figureFileBig=uCqfRwEZmVUH6K6/Njf5hw==, tableContent=null), ArticleFig(id=1199769409888809350, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=CN, label=图8, caption=Egg模型的井位及渗透率场分布, figureFileSmall=G3QUyslpX6W8ESk3tCfx6Q==, figureFileBig=uCqfRwEZmVUH6K6/Njf5hw==, tableContent=null), ArticleFig(id=1199769410043998605, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=EN, label=null, caption=null, figureFileSmall=GKCepbqBfcN4fyWA8m3eKw==, figureFileBig=G0Byv81ybeu37+ppUs9yrw==, tableContent=null), ArticleFig(id=1199769410215965074, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=CN, label=图9, caption=Egg模型实验结果, figureFileSmall=GKCepbqBfcN4fyWA8m3eKw==, figureFileBig=G0Byv81ybeu37+ppUs9yrw==, tableContent=null), ArticleFig(id=1199769410299851159, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=EN, label=null, caption=null, figureFileSmall=4FYr0PtAEkOjLewdYoDkkg==, figureFileBig=+GeCxDPzZcDWnBzb4yZJ9g==, tableContent=null), ArticleFig(id=1199769410392125852, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=CN, label=图10, caption=Egg模型注水井的最优井控参数方案, figureFileSmall=4FYr0PtAEkOjLewdYoDkkg==, figureFileBig=+GeCxDPzZcDWnBzb4yZJ9g==, tableContent=null), ArticleFig(id=1199769410488594848, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=EN, label=null, caption=null, figureFileSmall=DuiCghqAwl7oHN+RwCp5XA==, figureFileBig=o9scxDdYPpWO4zF3kf/0VA==, tableContent=null), ArticleFig(id=1199769410622812579, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=CN, label=图11, caption=Egg模型在最优注采参数下的优化结果, figureFileSmall=DuiCghqAwl7oHN+RwCp5XA==, figureFileBig=o9scxDdYPpWO4zF3kf/0VA==, tableContent=null), ArticleFig(id=1199769410736058795, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=EN, label=null, caption=null, figureFileSmall=hhBHnSOk8tZbYPQ8e/Vazw==, figureFileBig=lqRqbxlFfPXLpcjUf4f4vQ==, tableContent=null), ArticleFig(id=1199769410811556270, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=CN, label=图12, caption=布鲁日模型的井位及渗透率场分布, figureFileSmall=hhBHnSOk8tZbYPQ8e/Vazw==, figureFileBig=lqRqbxlFfPXLpcjUf4f4vQ==, tableContent=null), ArticleFig(id=1199769410899636659, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=EN, label=null, caption=null, figureFileSmall=wbiSXrvKzj0Zg3eLpUnOrw==, figureFileBig=/AhLoVxzWqyk9Naj/M7abw==, tableContent=null), ArticleFig(id=1199769411029660088, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=CN, label=图13, caption=布鲁日模型实验结果, figureFileSmall=wbiSXrvKzj0Zg3eLpUnOrw==, figureFileBig=/AhLoVxzWqyk9Naj/M7abw==, tableContent=null), ArticleFig(id=1199769412162122172, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=EN, label=null, caption=null, figureFileSmall=IslehyY1w2f4kWnXDZbvSA==, figureFileBig=ecK8aFlQs6CTcob47RcfoQ==, tableContent=null), ArticleFig(id=1199769412258591168, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=CN, label=图14, caption=布鲁日模型注水井的最优井控参数方案, figureFileSmall=IslehyY1w2f4kWnXDZbvSA==, figureFileBig=ecK8aFlQs6CTcob47RcfoQ==, tableContent=null), ArticleFig(id=1199769412371837382, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=EN, label=null, caption=null, figureFileSmall=jBOvU88HazuD2BgaR2eAJQ==, figureFileBig=4VmE+luXLNNYW4ZH1CVMBw==, tableContent=null), ArticleFig(id=1199769412464112071, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=CN, label=图15, caption=布鲁日模型生产井的最优井控参数方案, figureFileSmall=jBOvU88HazuD2BgaR2eAJQ==, figureFileBig=4VmE+luXLNNYW4ZH1CVMBw==, tableContent=null), ArticleFig(id=1199769412577358285, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=EN, label=null, caption=null, figureFileSmall=/3Nk4P639a7w7db7NN5Gjg==, figureFileBig=PUvmwIjqE1k6XORCxlpHdg==, tableContent=null), ArticleFig(id=1199769412707381714, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1153992996853899594, language=CN, label=图16, caption=布鲁日模型在最优注采参数下的优化结果, figureFileSmall=/3Nk4P639a7w7db7NN5Gjg==, figureFileBig=PUvmwIjqE1k6XORCxlpHdg==, tableContent=null)], attaches=null, journal=Journal(id=1146119232468656133, delFlag=0, nameCn=科技和产业, nameEn=Science Technology and Industry, nameHistory1=null, nameHistory2=null, issn=1671-1807, eissn=, cn=11-4671/T, coden=null, periodic=3, 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=65omA9nasEwsJtKyya4q2A==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Ind, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1755589264235, createdBy=null, updatedBy=15831073675, firstLetterCn=S, firstLetterEn=S, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=65omA9nasEwsJtKyya4q2A==, picEn=/wwFtLNQXxKpecNSjAf1AQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1164589040427811221, language=CN, name=科技和产业, 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.kjhcy.org/kjycy/home, createdTime=1755589264256, updatedTime=1755589264256, createdBy=15831073675, updatedBy=15831073675, submissionGuidelinesUrl=http://www.kjhcy.org/kjycy/site/menu/20110121105642001, submissionAuthorUrl=http://www.kjhcy.org/kjycy/author/login, submissionEditorUrl=http://www.kjhcy.org/kjycy/editor/login, submissionReviewUrl=http://www.kjhcy.org/kjycy/user/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1164589040473948566, language=EN, name=Science Technology and Industry, 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.kjhcy.org/kjycy/home, createdTime=1755589264267, updatedTime=1755589264267, createdBy=15831073675, updatedBy=15831073675, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.kjhcy.org/kjycy/author/login, submissionEditorUrl=http://www.kjhcy.org/kjycy/editor/login, submissionReviewUrl=http://www.kjhcy.org/kjycy/user/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123222451335185, websiteList=[Website(id=1148243202395595182, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123222451335185, 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/kjhcy/CN, language=CN, createTime=1751692112778, createBy=18614031015, updateTime=1753522130587, updateBy=18614031015, name=科技和产业-中文站点, tplId=1146099689490845704, title=科技和产业, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155919343281103033, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202395595182, code=articleTextType, value=kx, createTime=1753522247381, updateTime=1753522247381, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919343260131510, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202395595182, code=banner, value=null, createTime=1753522247376, updateTime=1753522247376, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919343251742901, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202395595182, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=NeDGaoVSnAwTO5bjjrifjg==, createTime=1753522247374, updateTime=1753522247374, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919343272714424, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202395595182, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753522247379, updateTime=1753522247379, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919343268520119, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202395595182, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753522247378, updateTime=1753522247378, creator=18614031015, updator=18614031015)]), Website(id=1155919131955314719, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123222451335185, 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/kjhcy/EN, language=EN, createTime=1753522197002, createBy=18614031015, updateTime=1753522207756, updateBy=18614031015, name=科技和产业-英文站点, tplId=1146101810881728533, title=Science Technology and Industry, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155919498877194448, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155919131955314719, code=articleTextType, value=kx, createTime=1753522284478, updateTime=1753522284478, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919498860417229, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155919131955314719, code=banner, value=null, createTime=1753522284474, updateTime=1753522284474, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919498852028620, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155919131955314719, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=NeDGaoVSnAwTO5bjjrifjg==, createTime=1753522284472, updateTime=1753522284472, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919498873000143, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155919131955314719, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753522284477, updateTime=1753522284477, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919498864611534, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155919131955314719, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753522284476, updateTime=1753522284476, creator=18614031015, updator=18614031015)])], journalTitle=科技和产业, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Industry, journalPhotoCn=65omA9nasEwsJtKyya4q2A==, journalPhotoEn=/wwFtLNQXxKpecNSjAf1AQ==, 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=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kjhcy/CN/Y2025/V25/I7/9, detailUrlEn=https://castjournals.cast.org.cn/joweb/kjhcy/EN/Y2025/V25/I7/9, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kjhcy/CN/PDF/Y2025/V25/I7/9, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kjhcy/EN/PDF/Y2025/V25/I7/9, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于集成代理模型的水驱油藏注采优化方法及应用——以布鲁日油田为例
收藏切换
PDF下载
暨梦琪 , 张雷 , 杜立滨 , 张小玫 , 张紫檀
科技和产业 | 科技创新 2025,25(7): 9-18
收起
收藏切换
科技和产业 | 科技创新 2025, 25(7): 9-18
基于集成代理模型的水驱油藏注采优化方法及应用——以布鲁日油田为例
全屏
暨梦琪, 张雷, 杜立滨, 张小玫, 张紫檀
作者信息
  • 中国石化胜利油田分公司石油工程技术研究院, 山东 东营 257000
  • 暨梦琪(1990—),女,福建建阳人,工程师,研究方向为智能注水;

    张雷(1974—),男,山东威海人,硕士,研究员,研究方向为采油技术;

    杜立滨(1974—),男,山东滨州人,副研究员,研究方向为油藏开发;

    张小玫(1993—),女,山东东营人,硕士,助理研究员,研究方向为注水工艺技术;

    张紫檀(1990—),男,山东东营人,硕士,助理研究员,研究方向为油田注水工艺和智能化井下工具。

Optimization Method and Application of Production Optimization Method for Waterflood Oil Reservoirs Based on an Ensemble Surrogate Model: In Bruges Oilfield as an Example
Mengqi JI, Lei ZHANG, Libin DU, Xiaomei ZHANG, Zitan ZHANG
Affiliations
  • Sinopec Shengli Oilfield Branch, Petroleum Engineering Technology Research Institute, Dongying 257000, Shandong, China
出版时间: 2025-04-10
文章导航
收藏切换

注采优化是闭环油藏管理的重要组成部分,其目的是通过寻找最优的注采参数方案来充分开发油藏潜力,以实现最大的经济效益。在搜索最优方案过程中,数值模拟器的使用极大地增加了时间成本,快速确定最优方案难度大但具有重要工程意义。基于油藏数值模拟模型、优化的时间步数、生产井和注水井控制方式、储层响应以及成本和利润参数等构建水驱油藏注采优化目标函数;根据代理模型采样准则,对代理模型替代数值模拟器参与注采优化的方法进行研究;为解决代理模型缺乏物理意义、寻优过程中难以做到与数值模拟器相同精度的问题,建立集成代理模型关系式。在三通道、Egg两个油藏概念模型上的验证结果表明,提出的集成代理模型优化方法能够在测试的两个概念模型上较常规优化方法经济效益分别提高4.81%、4.75%。为了验证所提方法在实际油田现场管理场景的应用效果,以布鲁日油田为例开展测试。提出的集成代理模型优化方法较常规优化方法经济效益可提高2.45%,可以在解决大规模油藏注采优化问题上取得令人满意的结果。

注采优化  /  集成代理模型  /  水驱油藏  /  开发策略

Production optimization is a key component of closed-loop reservoir management, aimed at maximizing economic benefits by fully exploiting reservoir potential through the identification of optimal injection and production parameter schemes. The use of numerical simulators during the search for the optimal solution significantly increases time costs, making it challenging to rapidly determine the best scheme, despite its important engineering implications. An objective function for production optimization in waterflood reservoirs was constructed based on factors such as the reservoir numerical simulation model, optimized time steps, production and injection well control strategies, reservoir responses, and cost and profit parameters. Research was conducted on the method of using surrogate models to replace numerical simulators in production optimization, based on sampling criteria for the surrogate model. In order to address the lack of physical significance in surrogate models and the difficulty in achieving the same precision as numerical simulators during optimization, a relationship for an ensemble surrogate model was established. Validation results on two reservoir models, three-channel and Egg, show that the proposed ensemble surrogate model optimization method improves economic benefits by 4.81% and 4.75% respectively, compared to conventional optimization methods across all tested reservoir models. In order to verify the application effect of the proposed method in the actual oilfield field management scenario, the Bruges oilfield is taken as an example to carry out the test. The proposed integrated agent model optimization method can increase the economic benefit by 2.45% compared with the conventional optimization method. This proves that the proposed method can achieve satisfactory results in solving the problem of injection and production optimization in large-scale reservoirs.

production optimization  /  ensemble surrogate model  /  waterflood reservoir  /  development strategy
暨梦琪, 张雷, 杜立滨, 张小玫, 张紫檀. 基于集成代理模型的水驱油藏注采优化方法及应用——以布鲁日油田为例. 科技和产业, 2025 , 25 (7) : 9 -18 .
Mengqi JI, Lei ZHANG, Libin DU, Xiaomei ZHANG, Zitan ZHANG. Optimization Method and Application of Production Optimization Method for Waterflood Oil Reservoirs Based on an Ensemble Surrogate Model: In Bruges Oilfield as an Example[J]. Science Technology and Industry, 2025 , 25 (7) : 9 -18 .
随着中国经济的快速增长,对油气资源的需求也在持续上升。但与此同时,中国油气对外依存度已超过2/3[1],这一现状与不断增长的国内需求形成了尖锐的对立。由于国内油气产量有限,对外依存度高,这不仅对中国的石油安全构成了严重威胁,也极大地制约了中国经济的持续发展。
在这一背景下,大数据与人工智能技术的迅猛发展为油气行业带来了新的机遇。这些技术与工业界的深度融合,为油气工业的智能化转型提供了强有力的支撑。面对新发现油田数量减少和老油田产量下降的双重挑战,通过智能化升级改造建设智能油田,充分挖掘储层潜力,成为当前的研究热点。智能油田的一个显著特征是其能够通过智能优化方法实现精准高效的决策。其中,油藏注采优化是实现智能油田决策的关键手段,旨在通过寻找最优的注采参数方案,最大限度地开发油藏潜力,以实现经济效益的最大化。
然而,注采优化是一个持续的过程,需要不断利用数值模拟器对候选的注采参数方案进行评估,以确定最适合油藏生产需求的开发方案。目前,单次油藏数值模拟可能需要数十分钟甚至数小时[2],对于拥有大量优化井的实际油藏区块而言,这一时间更是漫长。为了降低计算负担,研究人员已经开始采用数据驱动的代理模型来替代数值模拟器,快速评估候选方案[3],如净现值或累计产油量等储层响应。尽管代理模型有助于减少数值模拟器的评估次数,但其在优化过程中仍存在局限性。通常,仅使用单一代理模型进行评估,由于预测偏差,可能会导致搜索方向的偏差。此外,由于代理模型完全基于油藏样本数据构建,缺乏物理意义,其准确表示实际储层的能力受到限制。
为了解决这些问题,在构建油藏注采优化问题模型后,本文利用加权平均方法,根据多个代理模型的性能差异,自适应地构建集成代理模型,替代数值模拟器参与注采优化过程。通过对两个油藏模型的注采优化问题求解,验证了该方法的有效性,并形成了一套具有普适性和高效率的注采优化新方法。
注采优化旨在通过控制生产井和注水井的开发制度(即每口井的压力或者流量)来实现经济效益的最大化。优化的目标函数通常选为经济净现值NPV。对于水驱开发条件下的油藏注采参数优化问题,NPV可表示为式(1)的形式:
$J(x,s)=\sum _{n=1}^{{N}_{t}}\Delta {t}_{n}\frac{{Q}_{o,n}{r}_{o}-{Q}_{w,n}{r}_{w}-{Q}_{i,n}{r}_{i}}{{(1+b)}^{\frac{\Delta {t}_{n}}{365}}}$
式中:J为决策的目标函数,即,经济净现值,元;x为由每口井在每个时间步(也称为控制步)的注采参数组成的向量(注采参数方案);s为数值模拟器计算的储层状态向量;Nt为油藏注采参数优化的总时间步数;Δtn为第n个时间步所经过的时间,d;Qo,n为第n个时间步生产井的产油速率,STB/d,1 STB=158.98 L;Qw,n为第n个时间步生产井的产水速率,STB/d;Qi,n为第n个时间步注水井的注水速率,STB/d;ro为采油收益,元/STB;rw为产水处理成本,元/STB;ri为注水成本,元/STB;b为折现率,%。
考虑到的约束条件为注采参数的边界范围约束,故油藏注采优化问题可定义为式(2)的目标函数以及式(3)的约束条件:
$\underset{x}{max} J(x,s), x\in {R}^{d}$
s.t.xlow≤x≤xup
式中:d=aNt为优化的注采参数的维度,也就是一个开发方案中包含多少注采参数,a为优化井的数量;xup、xlow分别为控制注采参数的上限与下限。
在构建任何类型的代理模型[4]时,首要步骤是在指定的注采参数[5]优化范围内,如式(3)所示,进行样本点的采集。一个高效代理模型的关键特性是其能够精确地模拟油藏数值模拟器的行为[6]。为此,初始采样阶段需要尽可能广泛地覆盖整个参数空间,而不是仅仅集中在某个特定区域。采样点的数量是预先设定的,而采样点分布的广泛性直接影响了代理模型能够学习的油藏信息量。广泛的采样有助于确保代理模型在整个参数空间内都能保持较高的预测精度,避免了在样本密集区域预测准确度高,而在样本稀疏区域预测准确度下降的问题。这样可以确保代理模型在评估不同注采参数方案时,能够提供更加均衡和可靠的预测结果。
代理模型采样技术中最常用的方法有正交试验采样法[7](orthogonal design sampling method,ODS)以及拉丁超立方采样法[8](Latin hypercube sampling,LHS)等。ODS是一种高效快速的代理模型采样方法,其结合了正交阵列和因子分析两种方法[9]。ODS可以生成按行和列分布的分数阶乘数组,其中每行表示每个组合中的变量级别,每列表示可以从每个组合中更改的特定变量。ODS法根据试验的正交性,选取一部分能代表整个试验的点,这些被选中的点均匀地分布在整个试验空间中。然而随着待采样的变量数增长,ODS法面临着试验数激增的问题,需要的计算成本较高。LHS法最早由McKay等[10]提出,用于在计算机测试中进行快速随机取样。LHS法与其他简单的随机抽样技术相比,可以同时对所有的输入维度进行分层处理。LHS法示意图如图1所示。LHS法在面对优化变量较多的注采参数优化问题时表现出良好的稳定性,因此其被选作本论文中的代理模型采样技术。
在获取初始样本点后,就需要选择合适类型的代理模型进行训练。径向基函数网络(radial basis function network,RBFN)是一种具有运算稳定性的代理模型技术,适用于油井数量多、生产寿命长的油藏开发[11]。RBFN是一种人工神经网络,它通过加权基函数的和来逼近目标函数[12]。RBFN由输入层、隐藏层和输出层构成,输入层接收输入数据,即注采参数方案。RBFN的隐藏层通常包含几个神经元,每个神经元都有一个基函数作为其激活函数。RBFN的输出层通常是线性层,用于计算隐藏层神经元输出的加权和。RBFN由注采参数方案以及对应的NPV组成的样本库$\{{x}_{i},{y}_{i}{\}}_{i=1}^{N}$构造,其中xi为样本库中的第i个注采参数方案;yi为数值模拟器计算的第i个注采参数方案所对应的NPV;N为样本库中样本的数量。RBFN的结构示意图如图2所示。RBFN的表达式为
$f\left({x}^{*}\right)=\sum _{i=1}^{N}{w}_{i}\varphi \left(‖{x}^{*}-{x}_{i}‖\right)$
式中:f(x*)为RBFN针对进化算法产生的候选注采参数方案x*的预测值;$\{{w}_{i}{\}}_{i=1}^{N}$为权重系数;$\varphi (·)$为基函数,其类型有三次样条函数、高斯函数以及逆多重二次函数等。当确定基函数以及采集的样本点后,即可求得权重系数构建RBFN代理模型。
多项式响应面(polynomial regression surface,PRS)也是一种在求解油藏注采参数优化问题中经常使用的代理模型,其采用多项式回归分析来研究目标函数与观测变量之间的定量关系[13]。本文中使用的多项式回归是一个二阶多项式模型,其数学表达式为
$f\left({x}^{*}\right)={\beta }_{0}+\sum _{i=1}^{d}{\beta }_{i}{x}_{i}+\sum _{i=1}^{d}{\beta }_{ii}{x}_{i}^{2}+\sum _{i=1}^{d-1}\sum _{j=i+1}^{d}{\beta }_{ij}{x}_{i}{x}_{j}$
式中:f(x*)为PRS的预测值;x*为进化算法产生的候选注采参数方案;d为式(2)中注采参数的维度,因此在式(5)中,xi为样本库中所有注采参数方案的第i维;$\beta =\{{\beta }_{0},{\beta }_{i},{\beta }_{ii},{\beta }_{ij}\}$为多项式系数,可以用最小二乘法计算,即
$\beta ={\Phi }^{-1}y$
式中:y为样本库中的真实NPV;$\Phi $为多项式矩阵,其表达式为
$\Phi =\left\{\begin{array}{llllll}{1}^{\left(1\right)}& {x}_{i}^{\left(1\right)}& {x}_{j}^{\left(1\right)}& {x}_{i}^{2\left(1\right)}& {x}_{j}^{2\left(1\right)}& {x}_{i}{x}_{j}^{\left(1\right)}\\ {1}^{\left(2\right)}& {x}_{i}^{\left(2\right)}& {x}_{j}^{\left(2\right)}& {x}_{i}^{2\left(2\right)}& {x}_{j}^{2\left(2\right)}& {x}_{i}{x}_{j}^{\left(2\right)}\\ ︙& ︙& ︙& ︙& ︙& ︙\\ {1}^{\left(N\right)}& {x}_{i}^{\left(N\right)}& {x}_{j}^{\left(N\right)}& {x}_{i}^{2\left(N\right)}& {x}_{j}^{2\left(N\right)}& {x}_{i}{x}_{j}^{\left(N\right)}\end{array}\right\}$
式中:N为样本库中样本的数量;${x}_{i}^{2\left(N\right)}$为样本库中第N个注采参数方案的第i维的平方;${x}_{i}{x}_{j}^{\left(N\right)}$为样本库中第N个注采参数方案的第i维与第j维相乘。多项式系数确定后,即可快速构建多项式响应面代理模型。
进化算法的作用是基于初始样本点,通过交叉变异等操作生成新的候选注采参数方案。代理模型替代数值模拟器进行筛选的方案正是由进化算法产生。随着计算机和智能计算领域的快速发展,以进化算法为代表的智能方法在油藏注采参数优化领域得到了广泛应用。与基于梯度的算法相比,进化算法能够实现全局优化,并且不需要目标的梯度信息和限制性假设条件,具有广泛的适用性和灵活性,可与各种复杂油藏的注采参数优化问题相结合[14]。差分进化(differential evolution,DE)算法是油藏注采优化领域应用最为广泛的一种进化算法[15]。DE法的基础是确定输入的初始种群。种群是注采参数方案的集合,输入的初始种群一般是由当前样本库中净现值排名靠前的优秀注采参数方案所组成。确定完初始种群后,DE算法主要由3个环节构成:变异、交叉和选择。变异的过程就是基于输入的初始种群,使用变异算子产生变异种群的过程。变异种群是DE算法最终生成的新种群的基础。DE算法的具体理论推导公式可以参考文献[16]得到。
通常,获得开发代理模型所需的数据成本很高,因为需要通过数值模拟器计算NPV。在获取数据后希望从中尽可能多的提取信息构建一个稳健的代理模型预测框架,避免出现上文中提到的只使用单代理模型带来的预测不确定性问题。构建集成代理模型(又称为多代理模型)是一个解决上述问题的有效方法。与获取数据的成本相比,构建多代理模型的成本并不高,并且可以从多个代理模型中提取正确的预测趋势,进而耦合差分进化算法求解注采参数优化问题。基于上文提到的径向基函数网络代理模型与多项式响应面代理模型,构建集成代理模型。根据每一个子代理模型的预测精度分配相应的权重,然后将它们的预测值进行加权求和的基于权重法的多代理模型框架,其最终输出结果为
${f}_{ens}\left({x}^{*}\right)=\sum _{i=1}^{{N}_{m}}{w}_{i}{f}_{i}\left({x}^{*}\right)$
式中:fens(x*)为权重法多代理模型对注采参数方案x*的预测值;fi(x*)为第i个子代理模型对x*的预测值;wi为第i个子代理模型的权重系数;Nm为子代理模型的数量。当建立好每一个子代理模型后,最重要的就是如何确定它们各自的权重系数。在确定权重系数时,一个重要的原则是被认为更准确的模型应该被赋予更大的权重。采用加权聚合法对每个代理模型的权重进行确定。
${w}_{i}=\frac{\sum _{j=1,j\ne i}^{{N}_{m}}{e}_{j}}{({N}_{m}-1)\sum _{j=1}^{{N}_{m}}{e}_{j}}$
$\sum _{i=1}^{{N}_{m}}{w}_{i}=1$
式中:ej为使用样本库中的样本对第j个代理模型经过十折交叉验证后的均方根误差。从式(9)可以看出,当某一代理模型预测精度较高时,其均方根误差较小,相对应的其他代理模型的均方误差较大,这就会使分子较大,最终实现更准确的代理模型拥有更大的权重的目标。本文基于径向基函数网络模型和多项式响应面模型构建集成代理模型优化方法,因此式(8)中的代理模型数量Nm取值为2。在基于权重法的多代理模型框架构建完成后,可以辅助差分进化算法更新种群,形成一套完整的优化方法。
为验证集成代理模型优化方法的有效性,将常规单代理辅助差分进化算法(canonical surrogate assisted evolutionary algorithm,CSAEA)[17]、基于差分进化算法的注采优化方法与集成代理模型优化方法进行了比较。首先在一个二维非均质的三通道储层模型[18]上验证方法的有效性。三通道模型被广泛用于油藏注采优化领域的基准测试实例。三通道模型有25 × 25 × 1个网格块,每个网格块水平和垂直长度为30.5 m,厚度为6.1 m。该油藏采用水驱方式开发,共有9口生产井和4口注水井。三通道模型的渗透率场及井位分布如图3所示,其详细信息可参考文献[18]获得。
在三通道模型的注采优化研究中,生产井通过控制井底流压进行管理,其优化变量范围设定在3 000~6 000 psi(1 psi≈6 895 Pa)。与此同时,注水井则通过控制注水速率进行管理,优化变量范围在0~1 500 STB/d。整个优化周期设定为1 800 d,被均匀划分为10个控制阶段,每个阶段持续180 d。因此,总的优化变量数量等于井的数量乘以控制阶段数,共计130个变量。在经济参数方面,石油收益设定为359.84元/STB,注水成本和产水处理成本均为35.98元/STB,而折现率则设定为0。图4展示了在三通道模型上,3种不同优化方法独立运行10次后的结果。图中的横轴表示数值模拟的评估次数,即优化过程的迭代次数;纵轴显示了随着优化过程的进行,各种方法对三通道模型优化效果的改善。由于优化的目标函数是NPV,这是一个最大化问题,因此,图4中顶部的红色优化曲线代表了集成代理模型优化方法,显示出其在所有方法中的最佳综合性能。具体来说,与基于差分进化算法的注采优化方法相比,集成代理模型优化方法的净现值提高了4.81%;与常规单代理辅助差分进化算法相比,净现值提高了3.63%。这表明集成代理模型优化方法在提高经济效益方面具有显著优势。
图5图6展示了使用差分进化算法、常规单代理算法以及集成代理算法得到的三通道油藏模型中生产井和注水井的最优控制参数方案。在这些图中,每一行代表一口井在优化周期内的最优参数调整方案,而每个方框则指明了该井在特定时间节点的最优参数设置。以图5为例,集成代理算法为生产井提供的最优控制参数方案显示,P1、P7和P9这3口生产井在整个优化期间都保持了相对较低的井底压力。这是因为这些井位于渗透率较低的区域,为了确保这些区域的原油能够有效地被开采出来,需要适当降低井底流压。与此同时,其他位于渗透率较高区域的井,即使设置较高的井底压力,也能够有效地开采原油,并且有助于防止油藏内压力过快下降。这种细致的调整反映了集成代理算法在平衡不同井况和油藏动态方面的优越性,能够根据油藏的具体情况和需要,为每口井定制最优的控制参数方案,以实现整个油藏经济效益的最大化。通过这种方式,集成代理算法能够更精确地模拟油藏行为,为油藏开发提供更有效的决策支持。
图7展示了依据差分进化算法、常规单代理算法以及集成代理算法所制定的最优注采参数方案,在三通道油藏开发过程中对油田累计产油量(field oil production total,FOPT)、油田累计注水量(field water injection total,FWIT)和油田累计产水量(field water production total,FWPT)随时间变化的影响。通过对比这3种方法,可以分析得出以下结果。
从产水量方面来看,如图7(b)图7(c)所示,采用差分进化算法和常规单代理算法得到的注采参数方案,虽然在产水量上存在一定差异,但两者均比集成代理算法得到的方案产水量要大。这表明后两种方法在注水控制上可能不如集成代理算法精确,导致更多的水被注入油藏。
从注水量方面来看,差分进化算法和常规单代理算法得到的方案与集成代理算法得到的方案相接近,说明在注水总量的控制上,这些方法表现相当。
从产油量方面来看,最为关键的是,如图7(a)所示,集成代理算法得到的方案在整个开发周期内能够获得最高的累计产油量。这一结果直接关系到油田的经济效益,因为更多的产油意味着更高的收入。
综合以上分析,集成代理算法在制定注采参数方案时,不仅能够有效控制注水量,避免过多的水进入油藏,从而减少无效循环和提高波及效率,而且还能最大化产油量,这对于提高整个油藏开发的经济效益至关重要。因此,集成代理算法提供的注采参数方案能够在降低投入成本的同时提高产油收益,实现油藏开发的最大化经济效益。这一结果充分证明了集成代理算法在油藏注采优化领域的应用潜力和优势。
为进一步验证方法的有效性,在Egg模型[19]上对3种方法进行验证,其同样被广泛用作注采优化领域的基准油藏测试例子。Egg模型的渗透率场与井位分布如图8所示,其详细属性信息可参考文献[19]获得。Egg模型采用水驱方式开发,共有4口生产井和8口注水井。Egg模型的生产井采用恒定井底流压控制,井底流压为5 729 psi;注水井采用注入速率控制,优化变量的范围在0~500 STB/d。注采优化的周期总计为3 600 d,平均分为20个控制步骤,每个步骤180 d,因此总的优化变量数为160。石油收益为905.38元/STB,注水成本为45.27元/STB,产水处理成本为135.80元/STB,折现率设置为0。
图9展示了对Egg油藏模型进行10次独立的注采参数优化后,3种不同方法得到的平均净现值(NPV)收敛曲线。结果表明,与三通道模型的实验结果相似,集成代理模型优化方法在Egg模型上同样表现出了最佳的优化效果。具体来说,集成代理模型优化方法相比于基于差分进化算法的注采优化方法,净现值提高了4.75%;与常规单代理辅助差分进化算法相比,净现值提升了3.55%。
图10展示了通过差分进化算法、常规单代理算法和集成代理算法得到的Egg模型注水井的最优控制参数方案。如图10(c)所示,集成代理算法为I3、I6和I8这3口注水井设定了较高的注入速率。这是因为这些井并未直接与高渗透通道相连,通过增加这些井的注水量,有助于提高油藏的波及效率,实现更有效的油藏驱替。
图11展示了根据这3种方法所确定的最优注采参数方案,在Egg模型开发过程中累积产油量、累积注水量以及累积产水量随时间的变化情况。结果表明,集成代理算法所提供的最优方案在优化过程中取得了令人满意的成效。与其他两种方法相比,集成代理算法不仅能获得更高的累积产油量,还能实现更少的累积注水量和累积产水量。这表明集成代理算法在提高油藏开发效率和降低开发成本方面具有明显优势,从而为油藏开发带来更高的经济效益。
布鲁日油田是一个合成油藏,其被广泛应用于测试不同闭环油藏管理方法的通用平台。布鲁日油田能够模拟真实的现场管理场景,因此,它是迄今为止最大、最复杂的闭环优化测试用例。为了验证本文提出的集成代理优化算法的优越性,以布鲁日油田作为测试的模型,与常规单代理辅助差分进化算法和基于差分进化算法的注采优化方法进行比较。布鲁日模型是大型边水油藏。Brugge模型的渗透率场和井位分布如图12所示。Brugge模型采用水驱方式开发,共有10口注水井和20口生产井。Brugge模型的注水井采用注入速率控制,优化变量的范围在0~4 000 STB/d;生产井采用产液速度控制,优化变量的范围在0~2 000 STB/d。注采参数优化的周期总计为1 800 d,平均分为5个控制步骤,每个步骤360 d,因此总的优化变量数为150。石油收益为359.84元/STB,注水成本为21.59元/STB,产水处理成本为21.59元/STB,折现率设置为0。
图13为3种方法对布鲁日模型进行10次独立注采参数优化后的平均净现值收敛曲线。集成代理模型优化算法的性能要明显优于其他两种算法。尤其是在优化的早期阶段,集成代理模型可以通过模型之间的相互补充,帮助优化工作朝着正确的方向持续进行,提高最终获得的注采参数方案为最优解的概率。
图14图15为差分进化算法、常规单代理算法和集成代理算法提供的布鲁日模型的最优注采参数方案图。从图15(c)可以看出,集成代理算法通过最大化除P9外的所有生产井的产液速度来充分发挥各口井的开发潜力。图14(c)显示了集成代理算法提供的最优注水井参数方案在最后一个控制步骤中将每口井的注入速率都设置为很小的量。这是因为在之前的控制步骤中注入的水是足够的,并且已经开采出大量的石油。因此在最后一个控制步中,可以根据地层压力进行开发,如果此时再大量注水,则收益无法弥补成本。图16给出了依照3种方法制定的最优注采参数方案对布鲁日油藏开发过程中累计产油量、累计注水量以及累计产水量随时间的变化曲线。与差分进化算法和常规单代理算法相比,集成代理算法的最优注采参数方案可以获得最多的累积产油量、较少的累积注水量以及较少的累积产水量。因此在这种情况下,集成代理算法可以获得最高的经济效益。
(1)在传统的代理模型辅助进化算法求解水驱油藏注采优化问题中,通常只使用一种代理模型来制定最优注采参数方案,这忽视了它们对不同油藏以及优化时期适应性不同的问题。因此,在制定新油藏的注采参数方案时,常常会遇到方法选择的困境,从而限制了求解效率。本文针对上述问题,提出了一种将多种类型的代理模型的优势融合在一起的具有普适性的集成代理模型注采优化方法。该方法能够高效地调整注采参数方案,避免在筛选适合当前油藏开发的代理模型上浪费大量的数值模拟次数,从而提高了方法的性能。
(2)为了验证所提出方法的有效性,首先在两个概念油藏模型上进行了实例测试,并与当前流行的注采优化方法进行比较。实验结果表明,本文所提出的集成代理模型注采优化方法能够在测试的两个油藏模型上均取得最好的优化效果,且获得的注采参数方案较对比方法最大可提高4.81%、4.75%的经济效益。为了充分验证所提方法的优越性,在大规模实际油藏布鲁日模型上进行了注采优化测试。实验结果表明,本文所提出的方法可以较对比方法经济效益最大提高2.45%。这证明了本文提出的方法可以在解决油藏注采优化问题上取得很好的应用效果。
  • 中国石化科技攻关项目(P22023)
参考文献 引证文献
排序方式:
[1]
高文君, 殷瑞, 杨静. 新型水驱特征曲线的建立及理论基础[J]. 石油学报, 2020, 41(3): 342-347.
[2]
宋来明, 王春秋, 卢川, 等. 数据驱动的复杂油藏注采生产优化技术研究进展[J]. 石油钻采工艺, 2022, 44(2): 253-260.
[3]
BABAEI M, PAN I. Performance comparison of several response surface surrogate models and ensemble methods for waterinjection optimization under uncertainty[J]. Computers & Geosciences, 2016, 91: 19-32.
[4]
王链, 张亮, 赖枫鹏, 等. 基于替代模型的油藏注采参数多目标优化设计[J]. 科学技术与工程, 2019, 19(26): 178-185.
[5]
周志军, 郝玉. 春10区块水平井蒸汽吞吐注采参数优化[J]. 科学技术与工程, 2022, 22(29): 12826-12831.
[6]
李培宇, 黄世军, 柴世超, 等. 断块油藏水平井提液参数优化[J]. 科学技术与工程, 2022, 22(2): 524-531.
[7]
GONG W, CAI Z, JIANG L. Enhancing the performance of differential evolution using orthogonal design method[J]. Applied Mathematics and Computation, 2008, 206(1): 56-69.
[8]
ZHANG H, SHENG J J. Surrogate-assisted multiobjective optimization of a hydraulically fractured well in a naturally fractured shale reservoir with geological uncertainty[J]. SPE Journal, 2022, 27(1): 307-328.
[9]
LEI G, GUO Y, ZHU J, et al. Sequential subspace optimization method for electromagnetic devices design with orthogonal design technique[J]. IEEE Transactions on Magnetics, 2012, 48(2): 479-482.
[10]
MCKAY M D, BECKMAN R J, CONOVER W J. A comparison of three methods for selecting values of input variables in the analysis of output from a computer code[J]. Technometrics, 2000, 42(1): 55-61.
[11]
CAI X, GAO L, LI X. Efficient generalized surrogate-assisted evolutionary algorithm for high-dimensional expensive problems[J]. IEEE Transactions on Evolutionary Computation, 2019, 24(2): 365-379.
[12]
FORRESTER A I, KEANE A J. Recent advances in surrogate-based optimization[J]. Progress in Aerospace Sciences, 2009, 45(1-3): 50-79.
[13]
DONG H, WANG P, CHEN W, et al. SGOP: surrogate-assisted global optimization using a Pareto-based sampling strategy[J]. Applied Soft Computing, 2021, 106: 107380.
[14]
WANG L, YAO Y, LUO X, et al. A critical review on intelligent optimization algorithms and surrogate models for conventional and unconventional reservoir production optimization[J]. Fuel, 2023, 350: 128826.
[15]
PANT M, ZAHEER H, GARCIA-HERNANDEZ L, et al. Differential evolution: a review of more than two decades of research[J]. Engineering Applications of Artificial Intelligence, 2020, 90: 103479.
[16]
张凯, 陈国栋, 薛小明, 等. 基于主成分分析和代理模型的油藏生产注采优化方法[J]. 中国石油大学学报(自然科学版), 2020, 44(3): 90-97.
[17]
ZHAO X, ZHANG K, CHEN G, et al. Surrogate-assisted differential evolution for production optimization with nonlinear state constraints[J]. Journal of Petroleum Science and Engineering, 2020, 194: 107441.
[18]
CHEN G, ZHANG K, XUE X, et al. Surrogate-assisted evolutionary algorithm with dimensionality reduction method for water flooding production optimization[J]. Journal of Petroleum Science and Engineering, 2020, 185: 106633.
[19]
FARAHI M M, AHMADI M, DABIR B. Model-based water-flooding optimization using multi-objective approach for efficient reservoir management[J]. Journal of Petroleum Science and Engineering, 2021, 196: 107988.
2025年第25卷第7期
PDF下载
292
151
引用本文
BibTeX
文章信息
  • 接收时间:2024-09-22
  • 首发时间:2025-07-21
  • 出版时间:2025-04-10
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-09-22
基金
中国石化科技攻关项目(P22023)
作者信息
    中国石化胜利油田分公司石油工程技术研究院, 山东 东营 257000
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kjhcy/CN/1153992996853899594
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