METHODS AND SYSTEMS FOR MACHINE-LEARNING BASED SIM

专利名称：METHODS AND SYSTEMS FOR MACHINE-LEARNING BASED SIMULATION OF FLOW

发明人：USADI, Adam,LI, Dachang,PARASHKEVOV,

Rossen,TEREKHOV, Sergey, A.,WU, Xiao-hui,YANG, Yahan

申请号：EP118123.3申请日：20110519公开号：EP2599023A2公开日：20130605

摘要：There is provided a method for modeling a hydrocarbon reservoir that includesgenerating a reservoir model that has a plurality of coarse grid cells. A plurality of finegrid models is generated, wherein each fine grid model corresponds to one of theplurality of coarse grid cells that surround a flux interface. The method also includessimulating the plurality of fine grid models using a training simulation to obtain a set oftraining parameters, including a potential at each coarse grid cell surrounding the fluxinterface and a flux across the flux interface. A machine learning algorithm is used togenerate a constitutive relationship that provides a solution to fluid flow through the fluxinterface. The method also includes simulating the hydrocarbon reservoir using theconstitutive relationship and generating a data representation of a physical hydrocarbonreservoir in a non-transitory, computer-readable medium based on the results of thesimulation.

申请人：ExxonMobil Upstream Research Company

地址：3120 Buffalo Speedway Houston TX 77252-21 US

国籍：US

代理机构：Troch, Geneviève

更多信息请下载全文后查看