Automatic Fracture Network Model Update Using Smart Well Data and Artificial Neural Networks (SPE-113282)

摘要

This paper presents a new methodology to continuously update and improve fracture network system. We begin with a hypothetical model whose fracture network parameters and geological information are known. After generating the "exact" fracture network with known characteristics, the data were exported to a reservoir simulator and simulations were run over a period of time. Intelligent wells equipped with downhole multiple pressure and flow sensors were placed throughout the reservoir and put on production. These producers were completed in different fracture zones to create a representative pressure and production response. We then constructed the fracture network of the reservoir employing the initially available static data and updated it as more real-time data is acquired through smart wells. Simulated field performance is sequentially compared to that of the static model generated using available well-core data and real time dynamic data acquired up to that point.As the time period increases, more real-time data will be provided as well as more well data if additional wells are drilled. The process was continued until a good match of the original field performance is obtained.Ahighly sensitive input data were selected through forward selection scheme to trainArtificial Neural Network. Once the relationship between fracture network parameters and well performance data has been established, theANN model was used to predict fracture density at newly drilled locations and fracture network can be continuously updated. Finally, error analysis was performed to examine the accuracy of the proposed methodology. It was shown that fracture dominated production performance data collected from smart wells allow automatically updating the fracture network model. The technique proposed helps in generating another - readily available at no cost- data source for fracture characterization to be used as supplementary to limited 1-D data obtained from well logs and cores.