Dynamic engine for a cognitive reservoir system
AssigneeBeyond Limits, Inc.
InventorShahram Farhadi Nia
Life of this patent
Estimating the term…
Abstract
Implementations described and claimed herein provide systems and methods for developing a reservoir. In one implementation, a static model of the reservoir is received. The static model has one or more clusters of rock types. A reservoir graph is generated from the static model. The reservoir graph represents each of the one or more clusters as a vertex. A graph connectivity of the reservoir graph is defined through a nodal connectivity of neighboring vertices. Pressure values are propagated across three-dimensional space of the reservoir graph using the connectivity. A dynamic model of the reservoir is generated using the pressure values and fluid saturation values.
Claims17
A method for developing a reservoir, the method comprising:
- receiving a static model of the reservoir, the static model having one or more clusters of rock types;
- generating a reservoir graph from the static model, the reservoir graph representing each of the one or more clusters as a vertex, wherein each cluster has at most one pressure observation point, one perforation passes through each cluster, and each cluster contains a spatially continuous voxel set;
- post-processing on the one or more clusters in the reservoir graph to break discontinuous clusters into continuous blobs;
- defining a graph connectivity of the reservoir graph through a nodal connectivity of neighboring vertices;
- propagating pressure values across three-dimensional space of the reservoir graph using the nodal connectivity;
- and
- transforming the static model into a dynamic model of the reservoir based on the pressure values and fluid saturation values.
One or more non-transitory tangible computer-readable storage media storing computer-executable instructions for performing a computer process on a computing system, the computer process comprising:
- receiving a static model of a reservoir, the static model having one or more clusters of rock types;
- generating a reservoir graph from the static model, the reservoir graph representing each of the one or more clusters as a vertex, wherein each cluster has at most one pressure observation point, one perforation passes through each cluster, and each cluster contains a spatially continuous voxel set;
- post-processing on the one or more clusters in the reservoir graph to break discontinuous clusters into continuous blobs;
- defining a graph connectivity of the reservoir graph through a nodal connectivity of neighboring vertices;
- propagating pressure values across three-dimensional space of the reservoir graph using the nodal connectivity;
- and
- transforming the static model into a dynamic model of the reservoir based on the pressure values and fluid saturation values.
A system for developing a model of a reservoir, the system comprising:
- one or more processors configured to execute:
- a static modeler comprising one or more neural networks configured to generate a static model of the reservoir, the static model having one or more clusters of rock types;
- and
- a dynamic modeler in communication with the static modeler, the dynamic modeler using artificial intelligence to:
- generate a reservoir graph from the static model, the reservoir graph representing each of the one or more clusters as a vertex, wherein each cluster has at most one pressure observation point, one perforation passes through each cluster;
- and each cluster contains a spatially continuous voxel set;
- post-process the one or more clusters in the reservoir graph to break discontinuous clusters into continuous blobs;
- define a graph connectivity through a nodal connectivity of neighboring vertices,
- propagate pressure values across three-dimensional space of the reservoir graph using the nodal connectivity;
- and
- transform the static model into a dynamic model of the reservoir based on the pressure values and fluid saturation values.
Dependencies are inferred from the claim text.