spe-218841-ms数据驱动的液体载荷检测和预测之旅.pdfVIP

SPE-218841-MS

AData-DrivenJourneyintoLiquidLoadingDetectionandPrediction

UtkarshSinha,PrithviSinghChauhan,HardikkumarZalavadia,ArsalanAdil,andSathishSankaran,XectaDigital

Labs,Houston,Texas,USA

Copyright2024,SocietyofPetroleumEngineersDOI10.2118/218841-MS

ThispaperwaspreparedforpresentationattheSPEWesternRegionalMeetingheldinPaloAlto,California,USA,16-18April2024.

ThispaperwasselectedforpresentationbyanSPEprogramcommitteefollowingreviewofinformationcontainedinanabstractsubmittedbytheauthor(s).Contents

ofthepaperhavenotbeenreviewedbytheSocietyofPetroleumEngineersandaresubjecttocorrectionbytheauthor(s).Thematerialdoesnotnecessarilyreflect

anypositionoftheSocietyofPetroleumEngineers,itsofficers,ormembers.Electronicreproduction,distribution,orstorageofanypartofthispaperwithoutthewritten

consentoftheSocietyofPetroleumEngineersisprohibited.Permissiontoreproduceinprintisrestrictedtoanabstractofnotmorethan300words;illustrationsmay

notbecopied.TheabstractmustcontainconspicuousacknowledgmentofSPEcopyright.

Abstract

Liquidloadingisapersistentchallengeencounteredinonshoreandoffshoregaswells,particularly

atlowgasrates,wheretheaccumulationofwellboreliquidsleadstoflowinstabilities,operational

disruptions,prolongedshut-insleadingtoearlywellabandonmentandreducedoverallrecovery.Typical

liquidloadingmitigationstrategiessuchasvelocitystrings,wellcycling,intermittentorpermanentartificial

lift,surfactants/soapsetc.involveadditionalcostandtherefore,theiroperationalsuccessreliesonselecting

therightwellswithproperunderstandingofexpectedcriticalratesattherighttime.Modelsbasedondroplet,

filmormultiphasetransientflowcanbeusedtomodelliquidloadingphenomenon.However,empirical

correlationsareus