Dynamic Surrogate Reservoir Model with well constraints
Reservoir flow calculation is a significant aspect in oil and gas industries to calculate the results of a reservoir. Due to the large number of grid blocks and heterogeneity in reservoir models, extensive simulations are required to reduce the risk in reservoir's productivity. In order to miti...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Published: |
Institute of Electrical and Electronics Engineers Inc.
2016
|
| Online Access: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85010289418&doi=10.1109%2fICCOINS.2016.7783290&partnerID=40&md5=8b8f492e230867c7d782142fc0d880ca http://eprints.utp.edu.my/30525/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Reservoir flow calculation is a significant aspect in oil and gas industries to calculate the results of a reservoir. Due to the large number of grid blocks and heterogeneity in reservoir models, extensive simulations are required to reduce the risk in reservoir's productivity. In order to mitigate this problem, Surrogate Reservoir Model (SRM) is used as a prime outcome to reduce the simulation time. However, this paper work presents the dynamic well SRM, that extracts the data from a conventional reservoir simulator, Black Oil Applied Simulation Tool (BOAST). The well SRM with two dynamic constraints(bottom-hole flowing pressure and production rate) is built with random switch on/off of well with discrete time steps. The prime input parameters, porosity, permeability and saturation are identified from the reservoir model using principal component analysis (PCA) technique. The Artificial Neural Network (RBNN) technique is adopted to build the well SRM with dynamic constraints. The trained model from the dynamic well SRM is validated with the output from BOAST. The dynamic SRM is flexible in handling different types of modeling with changeable constraints. It was found that the simulated results of the proposed dynamic well SRM is effective in producing the outputs as predicted by the conventional simulator. © 2016 IEEE. |
|---|