Article(id=1156983784999575765, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156983783787421903, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2402208, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1711555200000, receivedDateStr=2024-03-28, revisedDate=1731859200000, revisedDateStr=2024-11-18, acceptedDate=null, acceptedDateStr=null, onlineDate=1753776030063, onlineDateStr=2025-07-29, pubDate=1739808000000, pubDateStr=2025-02-18, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1753776030063, onlineIssueDateStr=2025-07-29, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1753776030063, creator=13701087609, updateTime=1753776030063, updator=13701087609, issue=Issue{id=1156983783787421903, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='5', pageStart='1753', pageEnd='2192', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1753776029774, creator=13701087609, updateTime=1769691857141, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1223739602251436918, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156983783787421903, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1223739602251436919, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156983783787421903, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=1870, endPage=1877, ext={EN=ArticleExt(id=1156983785532252377, articleId=1156983784999575765, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Hybrid Model for Annular Pressure Prediction Based on Time Series Data, columnId=1156264152168518571, journalTitle=Science Technology and Engineering, columnName=Papers·Mining and Metallurgical Engineering, runingTitle=null, highlight=null, articleAbstract=

In order to avoid wellbore failure caused by abnormal annulus band pressure and resulting safety accidents, the annulus band pressure value is accurately predicted, and preventive measures are taken in advance when it exceeds the control value. An autoregressive integrated moving average-long short term memory (ARMI-LSTM) model was proposed. The model was trained to predict the annular band pressure of example wells based on actual annular band pressure time series data and feature capture data sets, and compared with a single model and recurrent neural network (RNN) model. The results show that the model has a good performance in error, fitting accuracy and overall performance after training with actual data, which can provide a reference for improving the prediction accuracy and efficiency of annular band pressure value, and is helpful to well integrity design.

, correspAuthors=Zhi ZHANG, 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=Yang-jie ZHANG, Zhi ZHANG, Yang WANG, Hao-yun DENG), CN=ArticleExt(id=1156983945612059248, articleId=1156983784999575765, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于时序数据的环空带压预测混合模型, columnId=1156262729603207500, journalTitle=科学技术与工程, columnName=论文·石油、天然气工业, runingTitle=null, highlight=null, articleAbstract=

为避免异常环空带压导致井筒失效,进而造成安全事故,准确预测环空带压值,在其超过控制值时提前采取预防和解决措施。提出自回归差分移动平均-长短期记忆模型(autoregressive integrated moving average-long short-term memory,ARIMA-LSTM),该模型针对实际环空带压时序数据和特征捕捉的数据集训练预测实例井的环空带压值,并与单一模型、循环神经网络(recurrent neural network,RNN)模型进行对比。研究结果显示:通过实际数据训练后,该模型在误差、拟合精度和整体性能上有着良好表现,可为提高环空带压值的预测精度和效率提供参考,对井筒完整性设计有一定帮助。

, correspAuthors=张智, authorNote=null, correspAuthorsNote=
*张智(1976—),男,汉族,四川南充人,博士,教授。研究方向:油气井工程、井筒完整性与环空带压管控、材料腐蚀与防腐。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=pQQLvI5xGOzmYRUU0oXo2g==, magXml=RFAAdcn6RBwvnPT3CkP+nw==, pdfUrl=null, pdf=rDXWSgsrY777xo4HgffH+A==, pdfFileSize=7016918, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=B248Nf0OzyovDyCk4DqDAg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=GZ6v2SbdMCTxELyLYZUwQw==, mapNumber=null, authorCompany=null, fund=null, authors=

张阳杰(2000—),男,汉族,四川成都人,硕士研究生。研究方向:人工智能。E-mail:

, authorsList=张阳杰, 张智, 王杨, 邓皓匀)}, authors=[Author(id=1225467182944010347, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=youngjay_zhang@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1225467183128559750, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, authorId=1225467182944010347, language=EN, stringName=Yang-jie ZHANG, firstName=Yang-jie, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu 610500, China
2 School of Computer Science and Software Engineering, Southwest Petroleum University, Chengdu 610500, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225467183363440797, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, authorId=1225467182944010347, language=CN, stringName=张阳杰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 西南石油大学油气藏地质及开发工程国家重点实验室, 成都 610500
2 西南石油大学计算机与软件学院, 成都 610500, bio={"content":"

张阳杰(2000—),男,汉族,四川成都人,硕士研究生。研究方向:人工智能。E-mail:

"}, bioImg=null, bioContent=

张阳杰(2000—),男,汉族,四川成都人,硕士研究生。研究方向:人工智能。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225467182436499502, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, xref=1, ext=[AuthorCompanyExt(id=1225467182482636855, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, companyId=1225467182436499502, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu 610500, China), AuthorCompanyExt(id=1225467182503608378, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, companyId=1225467182436499502, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西南石油大学油气藏地质及开发工程国家重点实验室, 成都 610500)]), AuthorCompany(id=1225467182776238167, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, xref=2, ext=[AuthorCompanyExt(id=1225467182793015387, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, companyId=1225467182776238167, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Computer Science and Software Engineering, Southwest Petroleum University, Chengdu 610500, China), AuthorCompanyExt(id=1225467182830764127, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, companyId=1225467182776238167, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 西南石油大学计算机与软件学院, 成都 610500)])]), Author(id=1225467183552184492, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wisezh@126.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1225467183761899708, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, authorId=1225467183552184492, language=EN, stringName=Zhi ZHANG, firstName=Zhi, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, *, address=1 State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu 610500, China
2 School of Computer Science and Software Engineering, Southwest Petroleum University, Chengdu 610500, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225467184084861140, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, authorId=1225467183552184492, language=CN, stringName=张智, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, *, address=1 西南石油大学油气藏地质及开发工程国家重点实验室, 成都 610500
2 西南石油大学计算机与软件学院, 成都 610500, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225467182436499502, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, xref=1, ext=[AuthorCompanyExt(id=1225467182482636855, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, companyId=1225467182436499502, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu 610500, China), AuthorCompanyExt(id=1225467182503608378, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, companyId=1225467182436499502, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西南石油大学油气藏地质及开发工程国家重点实验室, 成都 610500)]), AuthorCompany(id=1225467182776238167, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, xref=2, ext=[AuthorCompanyExt(id=1225467182793015387, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, companyId=1225467182776238167, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Computer Science and Software Engineering, Southwest Petroleum University, Chengdu 610500, China), AuthorCompanyExt(id=1225467182830764127, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, companyId=1225467182776238167, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 西南石油大学计算机与软件学院, 成都 610500)])]), Author(id=1225467184269410533, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, 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=1225467184458154237, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, authorId=1225467184269410533, language=EN, stringName=Yang WANG, firstName=Yang, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 School of Computer Science and Software Engineering, Southwest Petroleum University, Chengdu 610500, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225467184651092239, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, authorId=1225467184269410533, language=CN, stringName=王杨, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 西南石油大学计算机与软件学院, 成都 610500, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225467182776238167, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, xref=2, ext=[AuthorCompanyExt(id=1225467182793015387, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, companyId=1225467182776238167, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Computer Science and Software Engineering, Southwest Petroleum University, Chengdu 610500, China), AuthorCompanyExt(id=1225467182830764127, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, companyId=1225467182776238167, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 西南石油大学计算机与软件学院, 成都 610500)])]), Author(id=1225467184839835934, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, 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=1225467185146020155, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, authorId=1225467184839835934, language=EN, stringName=Hao-yun DENG, firstName=Hao-yun, middleName=null, lastName=DENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu 610500, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225467185297015117, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, authorId=1225467184839835934, language=CN, stringName=邓皓匀, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 西南石油大学油气藏地质及开发工程国家重点实验室, 成都 610500, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225467182436499502, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, xref=1, ext=[AuthorCompanyExt(id=1225467182482636855, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, companyId=1225467182436499502, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu 610500, China), AuthorCompanyExt(id=1225467182503608378, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, companyId=1225467182436499502, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西南石油大学油气藏地质及开发工程国家重点实验室, 成都 610500)])])], keywords=[Keyword(id=1225467186857296241, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=EN, orderNo=1, keyword=annular pressure prediction), Keyword(id=1225467187075400070, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=EN, orderNo=2, keyword=time series data), Keyword(id=1225467187285115281, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=EN, orderNo=3, keyword=neural network), Keyword(id=1225467187545162154, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=EN, orderNo=4, keyword=hybrid model), Keyword(id=1225467187712934329, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=CN, orderNo=1, keyword=环空带压预测), Keyword(id=1225467187855540683, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=CN, orderNo=2, keyword=时序数据), Keyword(id=1225467188019118558, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=CN, orderNo=3, keyword=神经网络), Keyword(id=1225467188165919214, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=CN, orderNo=4, keyword=混合模型)], refs=[Reference(id=1225467198605541456, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2012, volume=null, issue=1, pageStart=2061, pageEnd=2064, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Zhang Z, Xiao T P, Chen Z M, journalName=Advanced Materials and Engineering Technology, refType=null, unstructuredReference=Zhang Z, Xiao T P, Chen Z M, et al. Sustained casing pressure calculation of a annulus induced by downhole operation load[J]. Advanced Materials and Engineering Technology, 2012(1): 2061-2064., articleTitle=Sustained casing pressure calculation of a annulus induced by downhole operation load, refAbstract=null), Reference(id=1225467198848811110, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=34, pageStart=14574, pageEnd=14580, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=张智, 赵苑瑾, 郑钰山, journalName=科学技术与工程, refType=null, unstructuredReference=张智, 赵苑瑾, 郑钰山, 等. 储气库井环空带压预测与影响因素分析[J]. 科学技术与工程, 2023, 23(34): 14574-14580., articleTitle=储气库井环空带压预测与影响因素分析, refAbstract=null), Reference(id=1225467199167578229, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=34, pageStart=14574, pageEnd=14580, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=Zhang Zhi, Zhao Yuanjin, Zheng Yushan, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Zhang Zhi, Zhao Yuanjin, Zheng Yushan, et al. Prediction and analysis of influencing factors of annular pressure in gas storage wells[J]. Science Technology and Engineering, 2023, 23(34): 14574-14580., articleTitle=Prediction and analysis of influencing factors of annular pressure in gas storage wells, refAbstract=null), Reference(id=1225467200455229580, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2015, volume=37, issue=1, pageStart=56, pageEnd=59, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=张百灵, 杨进, 黄小龙, journalName=石油钻采工艺, refType=null, unstructuredReference=张百灵, 杨进, 黄小龙, 等. 深水井筒环空压力计算模型适应性评价[J]. 石油钻采工艺, 2015, 37(1): 56-59., articleTitle=深水井筒环空压力计算模型适应性评价, refAbstract=null), Reference(id=1225467200656556177, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2015, volume=37, issue=1, pageStart=56, pageEnd=59, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=Zhang Bailing, Yang Jin, Huang Xiaolong, journalName=Oil Drilling & Production Technology, refType=null, unstructuredReference=Zhang Bailing, Yang Jin, Huang Xiaolong, et al. Adaptability evaluation of calculation model of annular pressure of deepwater wellhole[J]. Oil Drilling & Production Technology, 2015, 37(1): 56-59., articleTitle=Adaptability evaluation of calculation model of annular pressure of deepwater wellhole, refAbstract=null), Reference(id=1225467200782385299, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2017, volume=9, issue=1, pageStart=756, pageEnd=763, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=Zeng D Z, He Q Y, Yu Z M, journalName=Petroleum Science Journal of Natural Gas Science and Engineering, refType=null, unstructuredReference=Zeng D Z, He Q Y, Yu Z M, et al. Risk assessment of sustained casing pressure in gas wells based on the fuzzy comprehensive evaluation method[J]. Petroleum Science Journal of Natural Gas Science and Engineering, 2017, 9(1): 756-763., articleTitle=Risk assessment of sustained casing pressure in gas wells based on the fuzzy comprehensive evaluation method, refAbstract=null), Reference(id=1225467200945963169, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2018, volume=41, issue=4, pageStart=16, pageEnd=18, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=何汉平, journalName=钻采工艺, refType=null, unstructuredReference=何汉平. 油气井环空允许带压值的计算方法探讨[J]. 钻采工艺, 2018, 41(4): 16-18., articleTitle=油气井环空允许带压值的计算方法探讨, refAbstract=null), Reference(id=1225467201143095473, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2018, volume=41, issue=4, pageStart=16, pageEnd=18, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=He Hanping, journalName=Drilling & Production Technology, refType=null, unstructuredReference=He Hanping. Probe on calculation methods for allowed annulus pressure in oil and gas wells[J]. Drilling & Production Technology, 2018, 41(4): 16-18., articleTitle=Probe on calculation methods for allowed annulus pressure in oil and gas wells, refAbstract=null), Reference(id=1225467201340227776, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2018, volume=41, issue=5, pageStart=38, pageEnd=41, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=王兆会, 陈俊, 李军鹏, journalName=钻采工艺, refType=null, unstructuredReference=王兆会, 陈俊, 李军鹏, 等. 储气库井环空带压相对风险评估[J]. 钻采工艺, 2018, 41(5): 38-41., articleTitle=储气库井环空带压相对风险评估, refAbstract=null), Reference(id=1225467201528971472, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2018, volume=41, issue=5, pageStart=38, pageEnd=41, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=Wang Zhaohui, Chen Jun, Li Junpeng, journalName=Drilling and Production Technology, refType=null, unstructuredReference=Wang Zhaohui, Chen Jun, Li Junpeng, et al. To assess relative risk of casing pressure sustained gas storage wells[J]. Drilling and Production Technology, 2018, 41(5): 38-41., articleTitle=To assess relative risk of casing pressure sustained gas storage wells, refAbstract=null), Reference(id=1225467201747075293, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2021, volume=49, issue=2, pageStart=104, pageEnd=109, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=张琳琳, 王鹏, 张红, journalName=石油机械, refType=null, unstructuredReference=张琳琳, 王鹏, 张红, 等. 双封隔器间环空压力计算模型研究[J]. 石油机械, 2021, 49(2): 104-109., articleTitle=双封隔器间环空压力计算模型研究, refAbstract=null), Reference(id=1225467201910653160, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2021, volume=49, issue=2, pageStart=104, pageEnd=109, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=Zhang Linlin, Wang Peng, Zhang Hong, journalName=China Petroleum Machinery, refType=null, unstructuredReference=Zhang Linlin, Wang Peng, Zhang Hong, et al. A model for calculating the annulus pressure between double packer[J]. China Petroleum Machinery, 2021, 49(2): 104-109., articleTitle=A model for calculating the annulus pressure between double packer, refAbstract=null), Reference(id=1225467202116174066, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=2, pageStart=175, pageEnd=181, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=张智, 黄熠, 李炎军, journalName=西南石油大学学报(自然科学版), refType=null, unstructuredReference=张智, 黄熠, 李炎军, 等. 考虑腐蚀的环空带压井生产套管安全评价[J]. 西南石油大学学报(自然科学版), 2014(2): 175-181., articleTitle=考虑腐蚀的环空带压井生产套管安全评价, refAbstract=null), Reference(id=1225467202292334850, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=2, pageStart=175, pageEnd=181, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=Zhang Zhi, Huang Yi, Li Yanjun, journalName=Journal of Southwest Petroleum University (Science & Technology Edition), refType=null, unstructuredReference=Zhang Zhi, Huang Yi, Li Yanjun, et al. Safety evaluation of production casing considering corrosion in gas well with sustained casing pressure[J]. Journal of Southwest Petroleum University (Science & Technology Edition), 2014(2): 175-181., articleTitle=Safety evaluation of production casing considering corrosion in gas well with sustained casing pressure, refAbstract=null), Reference(id=1225467202502050062, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=20, pageStart=8642, pageEnd=8649, url=null, language=null, rfNumber=[9], rfOrder=14, authorNames=丁亮亮, 代先涛, 李帅, journalName=科学技术与工程, refType=null, unstructuredReference=丁亮亮, 代先涛, 李帅, 等. 考虑环空液体热力学特征的持续环空带压预测模型研究[J]. 科学技术与工程, 2023, 23(20): 8642-8649., articleTitle=考虑环空液体热力学特征的持续环空带压预测模型研究, refAbstract=null), Reference(id=1225467202741125408, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=20, pageStart=8642, pageEnd=8649, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=Ding Liangliang, Dai Xiantao, Li Shuai, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Ding Liangliang, Dai Xiantao, Li Shuai, et al. Prediction model of sustained annular pressure considering thermodynamic characteristics of annular liquid[J]. Science Technology and Engineering, 2023, 23(20): 8642-8649., articleTitle=Prediction model of sustained annular pressure considering thermodynamic characteristics of annular liquid, refAbstract=null), Reference(id=1225467202871148839, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=12, pageStart=4959, pageEnd=4968, url=null, language=null, rfNumber=[10], rfOrder=16, authorNames=刘书杰, 罗鸣, 马传华, journalName=科学技术与工程, refType=null, unstructuredReference=刘书杰, 罗鸣, 马传华, 等. 深水高温高压气井环空圈闭压力下油管柱安全评价方法[J]. 科学技术与工程, 2024, 24(12): 4959-4968., articleTitle=深水高温高压气井环空圈闭压力下油管柱安全评价方法, refAbstract=null), Reference(id=1225467203085058360, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=12, pageStart=4959, pageEnd=4968, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=Liu Shujie, Luo Ming, Ma Chuanhua, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Liu Shujie, Luo Ming, Ma Chuanhua, et al. Safety evaluation method for tubing strings under annular trapping pressure in deep water high temperature and high pressure gas wells[J]. Science Technology and Engineering, 2024, 24(12): 4959-4968., articleTitle=Safety evaluation method for tubing strings under annular trapping pressure in deep water high temperature and high pressure gas wells, refAbstract=null), Reference(id=1225467203219276098, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2021, volume=18, issue=1, pageStart=30, pageEnd=35, url=null, language=null, rfNumber=[11], rfOrder=18, authorNames=刘和兴, 刘金铭, 孟文波, journalName=装备环境工程, refType=null, unstructuredReference=刘和兴, 刘金铭, 孟文波, 等. 考虑环空压力的生产套管CO2腐蚀速率预测[J]. 装备环境工程, 2021, 18(1): 30-35., articleTitle=考虑环空压力的生产套管CO2腐蚀速率预测, refAbstract=null), Reference(id=1225467203349299531, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2021, volume=18, issue=1, pageStart=30, pageEnd=35, url=null, language=null, rfNumber=[11], rfOrder=19, authorNames=Liu Hexing, Liu Jinming, Meng Wenbo, journalName=Equipment Environmental Engineering, refType=null, unstructuredReference=Liu Hexing, Liu Jinming, Meng Wenbo, et al. Prediction of CO2 corrosion rate of production casing considering annular pressure[J]. Equipment Environmental Engineering, 2021, 18(1): 30-35., articleTitle=Prediction of CO2 corrosion rate of production casing considering annular pressure, refAbstract=null), Reference(id=1225467203496100181, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=6, pageStart=83, pageEnd=88, url=null, language=null, rfNumber=[12], rfOrder=20, authorNames=张智, 蔡楠, 赵苑瑾, journalName=天然气工业, refType=null, unstructuredReference=张智, 蔡楠, 赵苑瑾, 等. 控制地下储气库强采强注井环空超压的氮气柱长度计算方法[J]. 天然气工业, 2021, 41(6): 83-88., articleTitle=控制地下储气库强采强注井环空超压的氮气柱长度计算方法, refAbstract=null), Reference(id=1225467204850860381, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=6, pageStart=83, pageEnd=88, url=null, language=null, rfNumber=[12], rfOrder=21, authorNames=Zhang Zhi, Cai Nan, Zhao Yuanjin, journalName=Natural Gas Industry, refType=null, unstructuredReference=Zhang Zhi, Cai Nan, Zhao Yuanjin, et al. A calculation method of nitrogen column length for controlling annular overpressure in underground gas storage(UGS) wells with intensive production and injection[J]. Natural Gas Industry, 2021, 41(6): 83-88., articleTitle=A calculation method of nitrogen column length for controlling annular overpressure in underground gas storage(UGS) wells with intensive production and injection, refAbstract=null), Reference(id=1225467205182210406, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2012, volume=36, issue=3, pageStart=192, pageEnd=196, url=null, language=null, rfNumber=[13], rfOrder=22, authorNames=杨磊, 王化增, 陈子凌, journalName=中国石油大学学报(自然科学版), refType=null, unstructuredReference=杨磊, 王化增, 陈子凌. 基于支持向量机的油气储量价值等级评价[J]. 中国石油大学学报(自然科学版), 2012, 36(3): 192-196., articleTitle=基于支持向量机的油气储量价值等级评价, refAbstract=null), Reference(id=1225467205295456624, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2012, volume=36, issue=3, pageStart=192, pageEnd=196, url=null, language=null, rfNumber=[13], rfOrder=23, authorNames=Yang Lei, Wang Huazeng, Chen Ziling, journalName=Journal of China University of Petroleum (Edition of Natural Science), refType=null, unstructuredReference=Yang Lei, Wang Huazeng, Chen Ziling. Assessing value classification of oil and gas reserve based on support vector machine[J]. Journal of China University of Petroleum (Edition of Natural Science), 2012, 36(3): 192-196., articleTitle=Assessing value classification of oil and gas reserve based on support vector machine, refAbstract=null), Reference(id=1225467205433868665, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2015, volume=43, issue=2, pageStart=84, pageEnd=89, url=null, language=null, rfNumber=[14], rfOrder=24, authorNames=王杰祥, 陈征, 靖伟, journalName=石油钻探技术, refType=null, unstructuredReference=王杰祥, 陈征, 靖伟, 等. 基于支持向量机的二氧化碳非混相驱效果预测[J]. 石油钻探技术, 2015, 43(2): 84-89., articleTitle=基于支持向量机的二氧化碳非混相驱效果预测, refAbstract=null), Reference(id=1225467205572280703, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2015, volume=43, issue=2, pageStart=84, pageEnd=89, url=null, language=null, rfNumber=[14], rfOrder=25, authorNames=Wang Jiexiang, Chen Zheng, Jing Wei, journalName=Petroleum Drilling Techniques, refType=null, unstructuredReference=Wang Jiexiang, Chen Zheng, Jing Wei, et al. Prediction of the effect CO2 immiscible flooding based on support vector machine[J]. Petroleum Drilling Techniques, 2015, 43(2): 84-89., articleTitle=Prediction of the effect CO2 immiscible flooding based on support vector machine, refAbstract=null), Reference(id=1225467205698109832, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2020, volume=47, issue=5, pageStart=1009, pageEnd=1015, url=null, language=null, rfNumber=[15], rfOrder=26, authorNames=王洪亮, 穆龙新, 时付更, journalName=石油勘探与开发, refType=null, unstructuredReference=王洪亮, 穆龙新, 时付更, 等. 基于循环神经网络的油田特高含水期产量预测方法[J]. 石油勘探与开发, 2020, 47(5): 1009-1015., articleTitle=基于循环神经网络的油田特高含水期产量预测方法, refAbstract=null), Reference(id=1225467205974933900, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2020, volume=47, issue=5, pageStart=1009, pageEnd=1015, url=null, language=null, rfNumber=[15], rfOrder=27, authorNames=Wang Hongliang, Mu Longxin, Shi Fugeng, journalName=Petroleum Exploration and Development, refType=null, unstructuredReference=Wang Hongliang, Mu Longxin, Shi Fugeng, et al. Production prediction at ultra-high water cut stage via recurrent neural network[J]. Petroleum Exploration and Development, 2020, 47(5): 1009-1015., articleTitle=Production prediction at ultra-high water cut stage via recurrent neural network, refAbstract=null), Reference(id=1225467206071402900, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2018, volume=45, issue=4, pageStart=598, pageEnd=607, url=null, language=null, rfNumber=[16], rfOrder=28, authorNames=张东晓, 陈云天, 孟晋, journalName=石油勘探与开发, refType=null, unstructuredReference=张东晓, 陈云天, 孟晋. 基于循环神经网络的测井曲线生成方法[J]. 石油勘探与开发, 2018, 45(4): 598-607., articleTitle=基于循环神经网络的测井曲线生成方法, refAbstract=null), Reference(id=1225467206188843419, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2018, volume=45, issue=4, pageStart=598, pageEnd=607, url=null, language=null, rfNumber=[16], rfOrder=29, authorNames=Zhang Dongxiao, Chen Yuntian, Meng Jin, journalName=Petroleum Exploration and Development, refType=null, unstructuredReference=Zhang Dongxiao, Chen Yuntian, Meng Jin. Method of logging curve generation based on recurrent neural network[J]. Petroleum Exploration and Development, 2018, 45(4): 598-607., articleTitle=Method of logging curve generation based on recurrent neural network, refAbstract=null), Reference(id=1225467206268535202, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2022, volume=52, issue=6, pageStart=1086, pageEnd=1099, url=null, language=null, rfNumber=[17], rfOrder=30, authorNames=于红岩, 丁帅伟, 高彦芳, journalName=西北大学学报(自然科学版), refType=null, unstructuredReference=于红岩, 丁帅伟, 高彦芳, 等. 人工智能在提高油气田勘探开发效果中的应用[J]. 西北大学学报(自然科学版), 2022, 52(6): 1086-1099., articleTitle=人工智能在提高油气田勘探开发效果中的应用, refAbstract=null), Reference(id=1225467206352421289, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2022, volume=52, issue=6, pageStart=1086, pageEnd=1099, url=null, language=null, rfNumber=[17], rfOrder=31, authorNames=Yu Hongyan, Ding Shuaiwei, Gao Yanfang, journalName=Journal of Northwest University(Natural Science Edition), refType=null, unstructuredReference=Yu Hongyan, Ding Shuaiwei, Gao Yanfang, et al. Application of artificial intelligence in improving the effectiveness of oil and gas field exploration and development[J]. Journal of Northwest University(Natural Science Edition), 2022, 52(6): 1086-1099., articleTitle=Application of artificial intelligence in improving the effectiveness of oil and gas field exploration and development, refAbstract=null), Reference(id=1225467206453084592, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2023, volume=46, issue=5, pageStart=27, pageEnd=34, url=null, language=null, rfNumber=[18], rfOrder=32, authorNames=蔡君懿, 李琪林, 严平, journalName=四川电力技术, refType=null, unstructuredReference=蔡君懿, 李琪林, 严平. 基于联合模型的短期电力负荷预测方法[J]. 四川电力技术, 2023, 46(5): 27-34., articleTitle=基于联合模型的短期电力负荷预测方法, refAbstract=null), Reference(id=1225467206641828281, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2023, volume=46, issue=5, pageStart=27, pageEnd=34, url=null, language=null, rfNumber=[18], rfOrder=33, authorNames=Cai Junyi, Li Qilin, Yan Ping, journalName=Sichuan Electric Power Technology, refType=null, unstructuredReference=Cai Junyi, Li Qilin, Yan Ping. Short-term load forecasting method based on combined model[J]. Sichuan Electric Power Technology, 2023, 46(5): 27-34., articleTitle=Short-term load forecasting method based on combined model, refAbstract=null), Reference(id=1225467206784434624, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=34, authorNames=朱丹青, journalName=基于数据挖掘的供应链需求预测模型研究, refType=null, unstructuredReference=朱丹青. 基于数据挖掘的供应链需求预测模型研究[D]. 武汉: 华中科技大学, 2022., articleTitle=null, refAbstract=null), Reference(id=1225467206901875144, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=35, authorNames=Zhu Danqing, journalName=Research on demand forecasting model of supply chain based on data mining, refType=null, unstructuredReference=Zhu Danqing. Research on demand forecasting model of supply chain based on data mining[D]. Wuhan: Huazhong University of Science and Technology, 2022., articleTitle=null, refAbstract=null)], funds=[Fund(id=1225467198014144541, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, awardId=U22A20164, language=CN, fundingSource=国家自然科学基金(U22A20164), fundOrder=null, country=null), Fund(id=1225467198148362277, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, awardId=52074234, language=CN, fundingSource=国家自然科学基金(52074234), fundOrder=null, country=null), Fund(id=1225467198265802802, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, awardId=PLN201925, language=CN, fundingSource=油气藏地质及开发工程国家重点实验室2019年开放基金(PLN201925), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1225467182436499502, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, xref=1, ext=[AuthorCompanyExt(id=1225467182482636855, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, companyId=1225467182436499502, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu 610500, China), AuthorCompanyExt(id=1225467182503608378, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, companyId=1225467182436499502, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西南石油大学油气藏地质及开发工程国家重点实验室, 成都 610500)]), AuthorCompany(id=1225467182776238167, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, xref=2, ext=[AuthorCompanyExt(id=1225467182793015387, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, companyId=1225467182776238167, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Computer Science and Software Engineering, Southwest Petroleum University, Chengdu 610500, China), AuthorCompanyExt(id=1225467182830764127, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, companyId=1225467182776238167, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 西南石油大学计算机与软件学院, 成都 610500)])], figs=[ArticleFig(id=1225467188635681301, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=EN, label=Fig.1, caption=LSTM temporal network structure, figureFileSmall=V7GPudRBF0yL348j3xXt7g==, figureFileBig=vXgB8tfqcwaxuM6KVef42A==, tableContent=null), ArticleFig(id=1225467188795064871, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=CN, label=图1, caption=LSTM网络时序结构

kt为隐藏层在t时刻的状态;Att时刻的输出值

, figureFileSmall=V7GPudRBF0yL348j3xXt7g==, figureFileBig=vXgB8tfqcwaxuM6KVef42A==, tableContent=null), ArticleFig(id=1225467189063500359, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=EN, label=Fig.2, caption=LSTM memory cell structure, figureFileSmall=6aGW3iasYPkY+6AW2uEFAQ==, figureFileBig=PoNJ5y90QTkFGQgGmKeBEA==, tableContent=null), ArticleFig(id=1225467189420016224, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=CN, label=图2, caption=LSTM记忆细胞结构

Xtt时刻的输入值;Atkt为细胞单元在t时刻的状态和LSTM的输出值;ftitot分别为遗忘门、输入门、输出门的输出结果

, figureFileSmall=6aGW3iasYPkY+6AW2uEFAQ==, figureFileBig=PoNJ5y90QTkFGQgGmKeBEA==, tableContent=null), ArticleFig(id=1225467189575205484, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=EN, label=Fig.3, caption=Comparison of raw data with processed data, figureFileSmall=gXAjm7oElaygMs+OHfsfTQ==, figureFileBig=3l21NkkfD0Zcbb6kZ8pOMQ==, tableContent=null), ArticleFig(id=1225467189688451707, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=CN, label=图3, caption=原始数据与处理后数据对比, figureFileSmall=gXAjm7oElaygMs+OHfsfTQ==, figureFileBig=3l21NkkfD0Zcbb6kZ8pOMQ==, tableContent=null), ArticleFig(id=1225467189793309316, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=EN, label=Fig.4, caption=ACF map, PACF map and BIC heat map, figureFileSmall=EZnEw5p8zZeT3IwbTUQTbg==, figureFileBig=9WIjsHL/wf9iM4q/b5GZGA==, tableContent=null), ArticleFig(id=1225467189940109978, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=CN, label=图4, caption=ACF图、PACF图和BIC热力图, figureFileSmall=EZnEw5p8zZeT3IwbTUQTbg==, figureFileBig=9WIjsHL/wf9iM4q/b5GZGA==, tableContent=null), ArticleFig(id=1225467191345201836, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=EN, label=Fig.5, caption=Schematic diagram of the LSTM model, figureFileSmall=+JF3cbZfZU+q3N64FHAuJA==, figureFileBig=8fvZESIkH94Nr7pGQsFGSQ==, tableContent=null), ArticleFig(id=1225467191584277185, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=CN, label=图5, caption=LSTM模型示意图, figureFileSmall=+JF3cbZfZU+q3N64FHAuJA==, figureFileBig=8fvZESIkH94Nr7pGQsFGSQ==, tableContent=null), ArticleFig(id=1225467192154702565, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=EN, label=Fig.6, caption=Annular pressure prediction hybrid model, figureFileSmall=NRMY9W/YssMFL26JYUkaMQ==, figureFileBig=Pklhv+TORANv7EcRMTVqTA==, tableContent=null), ArticleFig(id=1225467192842568457, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=CN, label=图6, caption=环空带压预测混合模型, figureFileSmall=NRMY9W/YssMFL26JYUkaMQ==, figureFileBig=Pklhv+TORANv7EcRMTVqTA==, tableContent=null), ArticleFig(id=1225467193001952016, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=EN, label=Fig.7, caption=Pressure and fluid production data, figureFileSmall=K3dvQGYWrhUI4QhjxLlq9Q==, figureFileBig=8x+tuJWQJPtzrQwR60mWDw==, tableContent=null), ArticleFig(id=1225467193320719136, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=CN, label=图7, caption=压力和产液量数据, figureFileSmall=K3dvQGYWrhUI4QhjxLlq9Q==, figureFileBig=8x+tuJWQJPtzrQwR60mWDw==, tableContent=null), ArticleFig(id=1225467193597543219, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=EN, label=Fig.8, caption=Loss function curve, figureFileSmall=yHewJBOepyUbGf9iUvGoSQ==, figureFileBig=DYFQuW5TnQE8INqZJXCYYA==, tableContent=null), ArticleFig(id=1225467193777898302, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=CN, label=图8, caption=损失函数曲线, figureFileSmall=yHewJBOepyUbGf9iUvGoSQ==, figureFileBig=DYFQuW5TnQE8INqZJXCYYA==, tableContent=null), ArticleFig(id=1225467193920504648, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=EN, label=Fig.9, caption=The comparison between the predicted results and the measured data, figureFileSmall=xLP1cJzNkeGfToLpMS86OA==, figureFileBig=O3ujAGZcMvcoQfBBoD2JsA==, tableContent=null), ArticleFig(id=1225467194159579994, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=CN, label=图9, caption=预测结果与实测数据对比, figureFileSmall=xLP1cJzNkeGfToLpMS86OA==, figureFileBig=O3ujAGZcMvcoQfBBoD2JsA==, tableContent=null), ArticleFig(id=1225467194516095852, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=EN, label=Fig.10, caption=Residual Q-Q map, figureFileSmall=RoV5aFdvbDsH+aXodFFm2Q==, figureFileBig=C9u4Mjyxi8LXZP3QGj/GDg==, tableContent=null), ArticleFig(id=1225467195996685190, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=CN, label=图10, caption=残差Q-Q, figureFileSmall=RoV5aFdvbDsH+aXodFFm2Q==, figureFileBig=C9u4Mjyxi8LXZP3QGj/GDg==, tableContent=null), ArticleFig(id=1225467196130902930, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=EN, label=Fig.11, caption=Autocorrelation plot of the residual sequence, figureFileSmall=0ls0ff6s9GrXYuzjOrlFPQ==, figureFileBig=i63uVNUSdt7Kzs3SJp8pxw==, tableContent=null), ArticleFig(id=1225467196277703584, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=CN, label=图11, caption=残差序列自相关图, figureFileSmall=0ls0ff6s9GrXYuzjOrlFPQ==, figureFileBig=i63uVNUSdt7Kzs3SJp8pxw==, tableContent=null), ArticleFig(id=1225467196533556154, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=EN, label=Table 1, caption=

Annular pressure ADF test table

, figureFileSmall=null, figureFileBig=null, tableContent=
差分阶数 ADF检验结果
1 P=0.203 4
2 P=0.005 9
), ArticleFig(id=1225467196655190980, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=CN, label=表1, caption=

环空带压ADF检验表

, figureFileSmall=null, figureFileBig=null, tableContent=
差分阶数 ADF检验结果
1 P=0.203 4
2 P=0.005 9
), ArticleFig(id=1225467196768437197, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=EN, label=Table 2, caption=

Pearson coefficient of annular pressure-related characteristics

, figureFileSmall=null, figureFileBig=null, tableContent=
特征 皮尔逊系数
流温 0.46
流压 0.54
油压 0.59
汽油比 -0.67
产液量 0.59
产油量 0.58
产水量 0.30
产气量 0.25
), ArticleFig(id=1225467196973958105, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=CN, label=表2, caption=

环空带压相关特征皮尔逊系数

, figureFileSmall=null, figureFileBig=null, tableContent=
特征 皮尔逊系数
流温 0.46
流压 0.54
油压 0.59
汽油比 -0.67
产液量 0.59
产油量 0.58
产水量 0.30
产气量 0.25
), ArticleFig(id=1225467197158507493, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=EN, label=Table 3, caption=

Comparison of evaluation indexes of different models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 MAE MAPE
RNN 5.782 29.104
LSTM 2.395 12.892
ARIMA 1.651 8.585
ARIMA+LSTM 1.206 3.107
), ArticleFig(id=1225467197422748655, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983784999575765, language=CN, label=表3, caption=

不同模型评价指标对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 MAE MAPE
RNN 5.782 29.104
LSTM 2.395 12.892
ARIMA 1.651 8.585
ARIMA+LSTM 1.206 3.107
)], 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.1671-1815.2402208, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2402208, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2402208, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2402208, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于时序数据的环空带压预测混合模型
收藏切换
PDF下载
张阳杰 1, 2 , 张智 1, 2, * , 王杨 2 , 邓皓匀 1
科学技术与工程 | 论文·石油、天然气工业 2025,25(5): 1870-1877
收起
收藏切换
科学技术与工程 | 论文·石油、天然气工业 2025, 25(5): 1870-1877
基于时序数据的环空带压预测混合模型
全屏
张阳杰1, 2 , 张智1, 2, * , 王杨2, 邓皓匀1
作者信息
  • 1 西南石油大学油气藏地质及开发工程国家重点实验室, 成都 610500
  • 2 西南石油大学计算机与软件学院, 成都 610500
  • 张阳杰(2000—),男,汉族,四川成都人,硕士研究生。研究方向:人工智能。E-mail:

通讯作者:

*张智(1976—),男,汉族,四川南充人,博士,教授。研究方向:油气井工程、井筒完整性与环空带压管控、材料腐蚀与防腐。E-mail:
Hybrid Model for Annular Pressure Prediction Based on Time Series Data
Yang-jie ZHANG1, 2 , Zhi ZHANG1, 2, * , Yang WANG2, Hao-yun DENG1
Affiliations
  • 1 State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu 610500, China
  • 2 School of Computer Science and Software Engineering, Southwest Petroleum University, Chengdu 610500, China
出版时间: 2025-02-18 doi: 10.12404/j.issn.1671-1815.2402208
文章导航
收藏切换

为避免异常环空带压导致井筒失效,进而造成安全事故,准确预测环空带压值,在其超过控制值时提前采取预防和解决措施。提出自回归差分移动平均-长短期记忆模型(autoregressive integrated moving average-long short-term memory,ARIMA-LSTM),该模型针对实际环空带压时序数据和特征捕捉的数据集训练预测实例井的环空带压值,并与单一模型、循环神经网络(recurrent neural network,RNN)模型进行对比。研究结果显示:通过实际数据训练后,该模型在误差、拟合精度和整体性能上有着良好表现,可为提高环空带压值的预测精度和效率提供参考,对井筒完整性设计有一定帮助。

环空带压预测  /  时序数据  /  神经网络  /  混合模型

In order to avoid wellbore failure caused by abnormal annulus band pressure and resulting safety accidents, the annulus band pressure value is accurately predicted, and preventive measures are taken in advance when it exceeds the control value. An autoregressive integrated moving average-long short term memory (ARMI-LSTM) model was proposed. The model was trained to predict the annular band pressure of example wells based on actual annular band pressure time series data and feature capture data sets, and compared with a single model and recurrent neural network (RNN) model. The results show that the model has a good performance in error, fitting accuracy and overall performance after training with actual data, which can provide a reference for improving the prediction accuracy and efficiency of annular band pressure value, and is helpful to well integrity design.

annular pressure prediction  /  time series data  /  neural network  /  hybrid model
张阳杰, 张智, 王杨, 邓皓匀. 基于时序数据的环空带压预测混合模型. 科学技术与工程, 2025 , 25 (5) : 1870 -1877 . DOI: 10.12404/j.issn.1671-1815.2402208
Yang-jie ZHANG, Zhi ZHANG, Yang WANG, Hao-yun DENG. Hybrid Model for Annular Pressure Prediction Based on Time Series Data[J]. Science Technology and Engineering, 2025 , 25 (5) : 1870 -1877 . DOI: 10.12404/j.issn.1671-1815.2402208
井筒完整性被破坏会对环境、经济收益和生产安全带来严重的负面影响,在井筒全生命周期设计中保证井筒完整性是至关重要的一环,非常有必要采取一种经济且有效的方法来保证井筒安全。井下复杂情况容易导致环空压力现象,对井筒完整性带来巨大威胁。但目前尚未形成有效根除环空带压的措施,当环空压力超过控制值时会引发井筒失效风险,极端情况下可能引发灾难性后果,因此准确预测环空带压变化,对实现安全稳产具有重要意义。
井筒完整性下的环空带压模块的研究拥有自身的一套理论体系和预测方法,涉及了多个领域。Zhang等[1]提供了一种计算环空压力的思想理论,该理论的核心是将井筒视作薄壁外形的圆柱筒,利用此理论研究了环空带压;张智等[2]、张百灵等[3]和Zeng等[4]通过数学模型和现场实例提出了适用性较高的环空带压模型;何汉平[5]、王兆会等[6]和张琳琳等[7]综合考虑不同因素对环空带压的影响,提出了环空带压预测计算模型;张智等[8]通过模拟计算对环空带压展开研究;丁亮亮等[9]充分考虑温压场耦合作用,建立了持续环空压力预测模型;刘书杰等[10]综合考虑热膨胀和鼓胀效应,建立了深水高温高压气井圈闭压力预测模型。
刘和兴等[11]通过计算发现,环空压力和产量呈正相关,但产量增长到一定值后,环空压力变化变得不明显;张智等[12]通过研究发现温度变化对环空压力影响很大,温度会导致环空带压现象十分明显;因此可以将环空带压值视为时序数据,且温度对预测准确性影响较大。
近年来机器学习在石油领域实际应用也逐渐增加,杨磊等[13]、王杰祥等[14]用过向量机模型对油产量和油日增量进行了预测;王洪亮等[15]基于循环神经网络(recurrent neural network,RNN)和长短期记忆(long short-term memory,LSTM)模型构建油田产量预测模型;张东晓等[16]提出一种基于RNN神经网络和LSTM神经网络的现场数据预处理技术;于红岩等[17]从人工智能油气田勘探中的多个领域中的应用,验证了人工智能解决油田勘探开发中复杂难题的优越性。
目前传统的环空带压预测模型通常在考虑温度压力场的情况下依赖于物理方程或经验公式,这些模型在特定条件下能够提供合理的预测结果,但面对复杂的地质条件和生产环境时,由于其基于稳态或准稳态的假设,难以使用一个模型来适应不同的井况和生产策略;随着油田数据采集技术的进步,现场产生的数据量急剧增加,传统模型也无法充分利用大量实时数据来优化预测。现代油田丰富的数据为机器学习提供了基础,目前机器学习多在测井领域、管道腐蚀,产量预测等方面有实际应用,其使用的模型多为向量机模型或单一模型。
长短时记忆(LSTM)[18]能够捕捉和记忆不同输入特征数据间的依赖关系,并且通过内部的存储单元在模型中长期维护数据的依赖性。自回归差分移动平均模型(autoregressive integrated moving average model,ARIMA)模型对于时间序列数据的分析和预测非常有效[18]。它的优势在于考虑了时间序列的自相关性、趋势和季节性,针对时间序列的环空带压数据ARIMA模型可以只考虑环空带压随时间变化数据本身的特征,而不考虑外在因素的影响。
目前尚未出现机器学习在环空带压领域的应用,且环空带压相关数据多为时间跨度、数据维度都较大的时序数据,存在明显的趋势性和周期性。现提出的ARIMA-LSTM混合模型神经网络特别适合处理和学习大规模的、高维度的、非线性的数据关系。因此基于混合模型利用BZ3-16H井2020—2023年的历史数据,选择温度和产量等几个参数作为输入特征,环空压力作为输出特征,从大量的历史生产数据中学习复杂的输入与输出间的依赖关系,从而捕捉环空带压的动态变化,可以在多变的生产环境中提供更精准的预测,并与多种单一神经网络模型的预测结果进行对比,验证模型的可靠性,从而实现对环空压力的快速、准确预测,帮助操作者提前做出决策,优化生产操作,防止可能的风险,为井筒完整性中环空带压问题提供参考。
自回归差分移动平均模型(ARIMA),主要由3个部分构成:自回归模型(AR)、差分过程(I)、移动平均模型(MA)[19]
AR模型对时间点之间的关系进行建模:一个时间点的标签值可以被过去某个时间段内的所有标签值线性组合表示,表达式为
$x_{t}=c+\sum_{i=1}^{p} \varphi_{i} x_{t-i}+\xi_{t}$
式(1)中:xt为时间点t的时间序列;c为模型的常数项;p为有多少个时间点;ϕi为滞后项的系数;ξt为时间点t的误差项。
MA模型描述的是当前时间点的数据与过去噪声的关系,表达式为
$x_{t}=\mu+\sum_{i=0}^{q} \theta_{i} \omega_{t-i}$
式(2)中:μ为时间序列的均值或期望值;q为过去的白噪声数量;θi为模型参数,表示白噪声对当前时间点的影响程度;ωt-i为白噪声项。
如果暂时不考虑差分,那么ARIMA模型可以看作是AR模型和MA模型的简单结合,表达式为
$x_{t}=c+\sum_{i=1}^{p} \varphi_{i} x_{t-i}+\sum_{i=0}^{q} \theta_{i} \omega_{t-i}+\xi_{t}$
式(1)~式(3)没有考虑差分,即假设模型处理的时间序列是平稳的,如果时间序列是非平稳的,那么就要考虑模型中的第1个部分,即差分处理,一阶差分公式为
$\Delta X_{t}=X_{t}-X_{t-1}$
二阶差分公式为
$\Delta^{2} X_{t}=\Delta\left(X_{t}-X_{t-1}\right)$
利用差分运算,将一个非平稳序列转化为平稳序列,消除时间序列的趋势和季节性变化,使ARIMA模型可以对时间序列进行正确的预测。通常使用ARIMA(p,d,q)模型,其表达式如下。
$X(B) \nabla^{d} y_{t}=Y(B) e(t)$
$X(B)=1-\alpha_{1} B-\alpha_{2} B^{2}-\cdots-\alpha_{p} B^{p}$
$Y(B)=1-\beta_{1} B-\beta_{2} B^{2}-\cdots-\beta_{q} B^{q}$
$B^{n} y(t)=y(t-n), n=1,2, \cdots, t-1$
$\nabla^{d}=(1-B)^{d}$
式中:yt为原序列;e(t)为白噪声;B为定义的线性后移算子;d为差分阶次。
长短期记忆(LSTM)模型可视为一类特殊的循环神经网络(RNN),相较于一般的RNN模型,LSTM更适用于处理和预测时间序列中相隔较长的事件。LSTM模型通过引入记忆细胞、输入门、输出门和遗忘门的概念,有效地解决了传统RNN处理长序列会出现的梯度爆炸问题[19],图1为LSTM网络时序结构。
对于一个给定的输入序列X=[x1,x2,…,xt],有
$\boldsymbol{A}_{t}=\operatorname{sigmoid}\left(V \boldsymbol{k}_{t}\right)$
$\boldsymbol{k}_{t}=\operatorname{sigmoid}\left(U \boldsymbol{x}_{t}+W \boldsymbol{k}_{t-1}\right)$
式中:sigmoid为激励函数,简写为σ;V为输出权重;U为输入权重;W为输入层到隐藏层传输的权重。
记忆细胞(memory cell)中有3个门结构,依次为遗忘门(forget gate)、输入门(input gate)、输出门(output gate),记忆细胞负责保存重要的信息,遗忘门负责决定是否遗忘记忆细胞中的信息,输入门负责决定是否将当前输入传入记忆细胞,输出门负责决定是否将记忆细胞的信息输出,图2为LSTM记忆细胞结构,相关计算公式如下。
$\boldsymbol{f}_{t}=\sigma\left(\boldsymbol{W}_{\mathrm{f}}\left[\boldsymbol{k}_{t-1}, \boldsymbol{x}_{t}\right]+\boldsymbol{b}_{\mathrm{f}}\right)$
$\boldsymbol{i}_{t}=\sigma\left(\boldsymbol{W}_{\mathrm{i}}\left[\boldsymbol{k}_{t-1}, \boldsymbol{x}_{t}\right]+\boldsymbol{b}_{\mathrm{i}}\right)$
$\boldsymbol{o}_{t}=\sigma\left(\boldsymbol{W}_{\mathrm{o}}\left[\boldsymbol{k}_{t-1}, \boldsymbol{x}_{t}\right]+\boldsymbol{b}_{\mathrm{o}}\right)$
式中:WfWiWo为3个门结构的权重;bfbibo为3个门结构的偏置,最后由输出门和记忆细胞决定LSTM的输出。
$\tilde{\boldsymbol{A}}_{t}=\tanh \left(\boldsymbol{W}_{\mathrm{A}}\left[\boldsymbol{k}_{t-1}, \boldsymbol{x}_{t}\right]+\boldsymbol{b}_{\mathrm{A}}\right)$
$\boldsymbol{A}_{t}=\boldsymbol{f}_{t} * \boldsymbol{A}_{t-1}+\boldsymbol{i}_{t} * \tilde{\boldsymbol{A}}_{t}$
$\boldsymbol{k}_{t}=\boldsymbol{o}_{t} * \tanh \left(\boldsymbol{A}_{t}\right)$
式中:Ãtt时刻的输入状态;WA为输入状态权重;bA为输入的偏置;tanh为激活函数;*表示对应元素相乘的运算。
通过以上3种门结构来控制记忆细胞中信息的写入、遗忘、输出功能,从而使LSTM模型能够长久维护一个状态,实现了保存历史信息并将其应用于未来预测的功能。
ARIMA适用于平稳序列的单元预测,因此需要先对数据进行平稳性检测,若是非平稳则需要利用差分转换成平稳数据,利用ADF检验原始数据和差分后数据的平稳性,检测结果如表1所示。
如果P较小(一般小于0.05)则有足够的证据证明拒绝原假设,即数据是平稳时间序列。ADF的序列检验结果显示,该实例井环空带压数据在二阶差分时P为0.005 9,可以认为二阶差分之后序列平稳,绘制原始数据、平滑处理趋势数据、一阶差分和二阶差分数据,如图3所示。由图3(b)可以看出,数据存在明显的先上升后下降趋势,二阶差分过后数据趋于平稳如图3(d)所示。因此可以确定下来ARIMA(p,d,q)模型中的d=2。
然后对平稳数据求出自相关系数(autocorrelation function,ACF)和偏自相关系数(partial autocorrelation function,PACF),绘制自相关(ACF)图,如图4(a)所示,自相关系数在滞后2阶后值趋于0,认为自相关系数拖尾;和偏自相关(PACF)图,如图4(b)所示,发现偏自相关系数在滞后3阶后逐渐衰减至0且始终处在蓝色置信区间内,因此认为偏自相关系数也拖尾,数据符合ARIMA模型使用条件。利用网格搜索计算贝叶斯信息量准则(Bayesian information criterion,BIC)值并绘制热力图如图4(c)所示,可知在(2,3)处BIC最小,最终可以确定模型为ARIMA(2,2,3)。
LSTM可以进行多元预测,捕获数据的线性和非线性趋势,通过如表2所示环空带压相关特征皮尔逊系数分析出相关性较大的油压、流压、流温、汽油比和产液作为LSTM模型输入特征,套压作为标签值即环空带压值作为预测结果。
然后对所有输入特征进行归一化处理使数据能够用于模型训练,最后通过调参确定LSTM的隐藏神经元个数,堆叠两个LSTM层,并添加Dropout层避免过拟合,最后通过一个全连接Dense层将模型输出整合成一个值输出,LSTM模型示意图如图5所示。
根据两个模型的各自参数以及输入输出权重,选用最小二乘法分配两个模型的预测结果,得到混合模型预测结果,与实测数据以及单一模型预测结果进行对比,以确定混合模型的性能以及准确性。混合模型建模流程如图6所示。
原始数据是BZ3-16H井2020—2023年实测数据,井口井底压力和产液量数据如图7所示,该井油压与环空带压、流压与环空带压以及产液量与环空带压趋势基本一致。
按照7∶1.5∶1.5的比例将数据划分为训练集、验证集和测试集,设置LSTM网络神经元为50,网络层数为5层,批样本数116。使用平均绝对误差(mean absolute error,MAE)和平均绝对百分比误差(mean absolute percentage error,MAPE)度量模型性能,均方误差(mean square error,MSE)作为损失函数,模型损失曲线如图8所示,经过10轮左右训练模型损失已下降至接近0,训练效果较好。
为验证混合模型的精确度和性能,使用循环神经网络(RNN),单一LSTM和单一ARIMA模型预测结果、实测数据与本混合模型预测结果对比,结果如表3所示。
可以看出,传统RNN模型由于不能捕获数据间的依赖关系,导致预测误差较大;LSTM模型和ARIMA模型对于时间序列预测有着不错的表现,MAE分别为2.395和1.651,但由于各自的局限性导致MAPE还是较高;ARIMA+LSTM混合模型将二者优势结合,MAE下降至1.206,MAPE下降至3.107,模型性能较单一模型提升了5%,预测准确率较高。
将以上4种模型对实例井的预测结果与实际环空带压数据对比,选取了从2023年5月25日—6月23日共30个数据点,对比结果如图9所示。ARIMA-LSTM混合模型的预测结果与实测数据吻合更好,且较单一模型预测准确率更高。
求出ARIMA-LSTM混合模型的预测值与实测数据之间的残差,并绘制Q-Q图(Q表示分位数)如图10所示,残差分布近似正态分布,说明模型能够充分捕捉环空带压数据中的相关性,能够较好地拟合数据,对环空带压的预测值可信度较高;残差自相关图如图11所示,残差基本落在置信区间内,残差序列已完全随机为白噪声,说明模型能够充分捕捉原数据的特征,预测性能较好。
根据混合模型的预测结果得到以下结论。
(1)基于ARIMA-LSTM混合模型对于环空带压值的预测比单一模型和传统模型更有效且性能更优秀,预测结果更接近真实值。
(2)环空带压实测数据中存在许多与环空带压预测不相关的变量,在训练模型前需要筛除掉这些变量,以进一步提高模型的训练效率。
(3)环空带压预测领域缺少使用神经网络模型的先例,提出的混合模型在准确性和效率上有良好表现,可为后续研究提供一定的参考。
  • 国家自然科学基金(U22A20164)
  • 国家自然科学基金(52074234)
  • 油气藏地质及开发工程国家重点实验室2019年开放基金(PLN201925)
参考文献 引证文献
排序方式:
[1]
Zhang Z, Xiao T P, Chen Z M, et al. Sustained casing pressure calculation of a annulus induced by downhole operation load[J]. Advanced Materials and Engineering Technology, 2012(1): 2061-2064.
[2]
张智, 赵苑瑾, 郑钰山, 等. 储气库井环空带压预测与影响因素分析[J]. 科学技术与工程, 2023, 23(34): 14574-14580.
Zhang Zhi, Zhao Yuanjin, Zheng Yushan, et al. Prediction and analysis of influencing factors of annular pressure in gas storage wells[J]. Science Technology and Engineering, 2023, 23(34): 14574-14580.
[3]
张百灵, 杨进, 黄小龙, 等. 深水井筒环空压力计算模型适应性评价[J]. 石油钻采工艺, 2015, 37(1): 56-59.
Zhang Bailing, Yang Jin, Huang Xiaolong, et al. Adaptability evaluation of calculation model of annular pressure of deepwater wellhole[J]. Oil Drilling & Production Technology, 2015, 37(1): 56-59.
[4]
Zeng D Z, He Q Y, Yu Z M, et al. Risk assessment of sustained casing pressure in gas wells based on the fuzzy comprehensive evaluation method[J]. Petroleum Science Journal of Natural Gas Science and Engineering, 2017, 9(1): 756-763.
[5]
何汉平. 油气井环空允许带压值的计算方法探讨[J]. 钻采工艺, 2018, 41(4): 16-18.
He Hanping. Probe on calculation methods for allowed annulus pressure in oil and gas wells[J]. Drilling & Production Technology, 2018, 41(4): 16-18.
[6]
王兆会, 陈俊, 李军鹏, 等. 储气库井环空带压相对风险评估[J]. 钻采工艺, 2018, 41(5): 38-41.
Wang Zhaohui, Chen Jun, Li Junpeng, et al. To assess relative risk of casing pressure sustained gas storage wells[J]. Drilling and Production Technology, 2018, 41(5): 38-41.
[7]
张琳琳, 王鹏, 张红, 等. 双封隔器间环空压力计算模型研究[J]. 石油机械, 2021, 49(2): 104-109.
Zhang Linlin, Wang Peng, Zhang Hong, et al. A model for calculating the annulus pressure between double packer[J]. China Petroleum Machinery, 2021, 49(2): 104-109.
[8]
张智, 黄熠, 李炎军, 等. 考虑腐蚀的环空带压井生产套管安全评价[J]. 西南石油大学学报(自然科学版), 2014(2): 175-181.
Zhang Zhi, Huang Yi, Li Yanjun, et al. Safety evaluation of production casing considering corrosion in gas well with sustained casing pressure[J]. Journal of Southwest Petroleum University (Science & Technology Edition), 2014(2): 175-181.
[9]
丁亮亮, 代先涛, 李帅, 等. 考虑环空液体热力学特征的持续环空带压预测模型研究[J]. 科学技术与工程, 2023, 23(20): 8642-8649.
Ding Liangliang, Dai Xiantao, Li Shuai, et al. Prediction model of sustained annular pressure considering thermodynamic characteristics of annular liquid[J]. Science Technology and Engineering, 2023, 23(20): 8642-8649.
[10]
刘书杰, 罗鸣, 马传华, 等. 深水高温高压气井环空圈闭压力下油管柱安全评价方法[J]. 科学技术与工程, 2024, 24(12): 4959-4968.
Liu Shujie, Luo Ming, Ma Chuanhua, et al. Safety evaluation method for tubing strings under annular trapping pressure in deep water high temperature and high pressure gas wells[J]. Science Technology and Engineering, 2024, 24(12): 4959-4968.
[11]
刘和兴, 刘金铭, 孟文波, 等. 考虑环空压力的生产套管CO2腐蚀速率预测[J]. 装备环境工程, 2021, 18(1): 30-35.
Liu Hexing, Liu Jinming, Meng Wenbo, et al. Prediction of CO2 corrosion rate of production casing considering annular pressure[J]. Equipment Environmental Engineering, 2021, 18(1): 30-35.
[12]
张智, 蔡楠, 赵苑瑾, 等. 控制地下储气库强采强注井环空超压的氮气柱长度计算方法[J]. 天然气工业, 2021, 41(6): 83-88.
Zhang Zhi, Cai Nan, Zhao Yuanjin, et al. A calculation method of nitrogen column length for controlling annular overpressure in underground gas storage(UGS) wells with intensive production and injection[J]. Natural Gas Industry, 2021, 41(6): 83-88.
[13]
杨磊, 王化增, 陈子凌. 基于支持向量机的油气储量价值等级评价[J]. 中国石油大学学报(自然科学版), 2012, 36(3): 192-196.
Yang Lei, Wang Huazeng, Chen Ziling. Assessing value classification of oil and gas reserve based on support vector machine[J]. Journal of China University of Petroleum (Edition of Natural Science), 2012, 36(3): 192-196.
[14]
王杰祥, 陈征, 靖伟, 等. 基于支持向量机的二氧化碳非混相驱效果预测[J]. 石油钻探技术, 2015, 43(2): 84-89.
Wang Jiexiang, Chen Zheng, Jing Wei, et al. Prediction of the effect CO2 immiscible flooding based on support vector machine[J]. Petroleum Drilling Techniques, 2015, 43(2): 84-89.
[15]
王洪亮, 穆龙新, 时付更, 等. 基于循环神经网络的油田特高含水期产量预测方法[J]. 石油勘探与开发, 2020, 47(5): 1009-1015.
Wang Hongliang, Mu Longxin, Shi Fugeng, et al. Production prediction at ultra-high water cut stage via recurrent neural network[J]. Petroleum Exploration and Development, 2020, 47(5): 1009-1015.
[16]
张东晓, 陈云天, 孟晋. 基于循环神经网络的测井曲线生成方法[J]. 石油勘探与开发, 2018, 45(4): 598-607.
Zhang Dongxiao, Chen Yuntian, Meng Jin. Method of logging curve generation based on recurrent neural network[J]. Petroleum Exploration and Development, 2018, 45(4): 598-607.
[17]
于红岩, 丁帅伟, 高彦芳, 等. 人工智能在提高油气田勘探开发效果中的应用[J]. 西北大学学报(自然科学版), 2022, 52(6): 1086-1099.
Yu Hongyan, Ding Shuaiwei, Gao Yanfang, et al. Application of artificial intelligence in improving the effectiveness of oil and gas field exploration and development[J]. Journal of Northwest University(Natural Science Edition), 2022, 52(6): 1086-1099.
[18]
蔡君懿, 李琪林, 严平. 基于联合模型的短期电力负荷预测方法[J]. 四川电力技术, 2023, 46(5): 27-34.
Cai Junyi, Li Qilin, Yan Ping. Short-term load forecasting method based on combined model[J]. Sichuan Electric Power Technology, 2023, 46(5): 27-34.
[19]
朱丹青. 基于数据挖掘的供应链需求预测模型研究[D]. 武汉: 华中科技大学, 2022.
Zhu Danqing. Research on demand forecasting model of supply chain based on data mining[D]. Wuhan: Huazhong University of Science and Technology, 2022.
2025年第25卷第5期
PDF下载
422
190
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2402208
  • 接收时间:2024-03-28
  • 首发时间:2025-07-29
  • 出版时间:2025-02-18
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-03-28
  • 修回日期:2024-11-18
基金
国家自然科学基金(U22A20164)
国家自然科学基金(52074234)
油气藏地质及开发工程国家重点实验室2019年开放基金(PLN201925)
作者信息
    1 西南石油大学油气藏地质及开发工程国家重点实验室, 成都 610500
    2 西南石油大学计算机与软件学院, 成都 610500

通讯作者:

*张智(1976—),男,汉族,四川南充人,博士,教授。研究方向:油气井工程、井筒完整性与环空带压管控、材料腐蚀与防腐。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2402208
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