Institutional Repository
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Machine learning methods to speed up compositional reservoir simulation

Gaganis Vasileios, Varotsis Nikolaos

Simple record


URIhttp://purl.tuc.gr/dl/dias/459B7618-2758-4AF8-B9E0-8F391F853538-
Identifierhttps://doi.org/10.2118/154505-MS-
Identifierhttps://www.onepetro.org/conference-paper/SPE-154505-MS-
Languageen-
Extent11 pagesen
TitleMachine learning methods to speed up compositional reservoir simulationen
CreatorGaganis Vasileiosen
CreatorΓαγανης Βασιλειοςel
CreatorVarotsis Nikolaosen
CreatorΒαροτσης Νικολαοςel
PublisherSociety of Petroleum Engineersen
Content SummaryCompositional reservoir simulation is the most powerful tool available to the reservoir engineer upon which, nowadays, most reservoir development decisions rely on. According to the number of components used to describe the fluids, there is a very high demand for computational power due to the complexity and to the iterative nature of the phase behavior problem solution process. Phase stability and phase split computations often consume more than 50% of the simulation's total CPU time as both problems need to be solved repeatedly for each discretization block at each iteration of the non-linear solver. Therefore, the speeding up of these calculations is a challenge of great interest. In this work, machine learning methods are proposed for the solving of the phase equilibrium problem. It is shown that by using proper transformations, the unknown closed-form solution of the Equation-of-State based formulation can be emulated by proxy models. The phase stability problem is treated by classifiers which label the fluid's state in each block as either stable or unstable. For the phase-split problem, regression models provide the prevailing equilibrium coefficients values given the feed composition, pressure and temperature. The development of both models is performed rapidly and offline in an automated way, by utilizing the fluid's tuned-EoS model, prior to running the reservoir simulator. During the simulation run, the proxy models are called to provide direct answers of the phase equilibrium problem at a very small CPU charge instead of solving iteratively the phase behavior problem. The proposed approach is presented in two-phase equilibria formulation but it can be extended to multi-phase equilibria applications. Examples demonstrate the accuracy of the calculations and the very significant CPU time reduction achieved with respect to currently used methods.1. Introduction Phase equilibrium calculations have been attracting significant research interest due to the broad range of applications in which they are involved such as separation processes, pipeline flow, compositional reservoir simulation, etc. For compositional reservoir simulation it has been reported that the phase equilibrium calculations may consume up to 70% of the CPU time of a run depending on the space and time discretization as well as on the fluid EoS model complexity, thus rendering computations acceleration as of major importance. At each grid block and for each time step, one needs to know the number and type of the coexisting equilibrium phases for a given feed composition and thermodynamic conditions and firstly a phase stability test should be conducted to be followed, whenever required, by a phase split calculation for providing the molar fraction and composition of each equilibrium phase. Evidently, the quality of the results bear direct impact on the accuracy of the simulation as they provide PVT and physical properties data input to the flow, mass and energy equations. en
Type of ItemΠλήρης Δημοσίευση σε Συνέδριοel
Type of ItemConference Full Paperen
Licensehttp://creativecommons.org/licenses/by/4.0/en
Date of Item2015-11-07-
Date of Publication2012-
SubjectLearning, Machineen
Subjectmachine learningen
Subjectlearning machineen
Bibliographic CitationV. Gaganis and N. Varotsis, “Machine learning methods to speed up compositional reservoir simulation”, in SPE Europec/EAGE Annual Conference, 2012. doi: 10.2118/154505-MSen

Services

Statistics