Fast Modelling of Gas Reservoirs Using POD-RBF Non-Intrusive ReducedOrder Modelling

摘要

We demonstrate that the non-intrusive reduced order model (NIROM) based on proper orthogonaldecomposition and radial basis function interpolation is capable of gas reservoir simulation predictions withcomputational speed-ups of at least an order of magnitude and potentially many orders of magnitude. It canestimate 3-dimensional spatial pressure and saturation distributions as well as production data for unseengas reservoir simulation scenarios produced at constant bottom hole pressure or gas rate control. The NIROM is created from a series of training simulations performed using a commercial simulator.These simulations produce "snapshots" of the pressure and saturation distributions at equally spacedtime intervals. Proper Orthogonal Decomposition (POD) is then used to project these data into a higherdimensional hyperspace. Radial basis functions (RBF) are then used to both estimate the dynamics of thesystem and the behaviour for unseen inputs (such as well BHP or rate). The approach is demonstrated using3 different reservoir models, including a realistic reservoir model using data taken from the Norne field. The NIROM simulations produce satisfactory predictions when compared to a commercial simulator,provided the unseen inputs are within the range of training parameters and time scale covered by thesimulation. On average, these results were obtained using 10 training runs. The overall improvement inspeed is insensitive to reservoir model complexities, such as local grid refinement, water coning or thepresence of aquifers. Reservoir models with significant water production require more NIROM simulationsubspace vectors to estimate performance, compared with cases without water production. Furthermore,we show that although NIROM works well for constant well controls over time it is less accurate whenestimating behaviour when the imposed well rate changes quickly at different times in the simulation. This is the first time that POD-RBF NIROM has been applied and evaluated for pressure depletionproblems, such as occur in gas reservoir performance prediction.