| الوصف: |
In this work, we study a waterflood field containing over 1,000 wells and the modern field management techniques with full-fidelity 3D geo-cellular reservoir models become computationally prohibitive. To overcome the difficulty, we developed a novel flow-network data-driven model, GPSNet, and used it for rapid history matching and optimization. GPSNet includes physics, such as mass conservation, multiphase flow, phase changes, etc., while maintaining a good level of efficiency. To build such a model, a cluster of 1-D connections among well completion points are constructed and form a flow network. Multi-phase fluid flow is assumed to occur in each 1-D connection and the flow in the whole network is simulated by our in-house general-purpose simulator. Next, to effectively reduce the uncertainty, a hierarchical history-matching workflow is adopted to match the production data. Ensemble Smoother with Multiple Data Assimilation (ESMDA) is utilized to reduce the error at each step of the history matching. Next, a best-matched candidate is selected for numerical optimization to maximize oil production rates with constraints satisfying field conditions. Excellent history-matching results have been achieved on the field level and good matches have also been observed for key producers. In addition, the history matching consumes mere 4 hours to finish 1,100 simulation jobs. The successful application of the GPSNet to this waterflood field demonstrates a promising workflow that can be used as a fast and reliable decision-making tool for reservoir management. |
