Prediction of Formation Damage During Fluid Injection into Fractured, Low Permeability Reservoirs via Neural Networks
- M. Nikravesh (Lawrence Berkeley National Laboratory) | A.R. Kovscek (Lawrence Berkeley National Laboratory) | R.M. Johnston (CalResources, LLC) | T.W. Patzek (University of California at Berkeley and Lawrence Berkeley National Laboratory)
- Document ID
- Society of Petroleum Engineers
- SPE Formation Damage Control Symposium, 14-15 February, Lafayette, Louisiana
- Publication Date
- Document Type
- Conference Paper
- Copyright 1996, Society of Petroleum Engineers Inc.
- 5.4.1 Waterflooding, 5.5.8 History Matching, 5.5 Reservoir Simulation, 5.1.1 Exploration, Development, Structural Geology, 1.8 Formation Damage, 6.1.5 Human Resources, Competence and Training, 5.4.6 Thermal Methods
- 1 in the last 30 days
- 323 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 8.50|
|SPE Non-Member Price:||USD 25.00|
The coupled, nonlinear and dynamic mechanisms that affect fluid injection for pressure maintenance or displacement, and oil production, are not well understood in low permeability fractured reservoirs. Thus, it is difficult to select an injection policy which maximizes oil recovery while minimizing formation damage caused by fluid injection and withdrawal. Here, we show that neural network models can be developed and used to predict, on a well-by-well basis, the dynamics of low permeability, fractured reservoirs undergoing fluid injection. The networks are trained using historical data from field operations.
We present an example from (i) a water and (ii) a steam injection project where over-pressurization has lead to unwanted extensions of fractures. First, using data from a waterflood project in the South Belridge Diatomite (Kern County, CA), we have built a neural network to predict wellhead pressure as a function of injection rate, and vice versa. The resulting model provides an excellent correlation between the inputs and outputs and recognizes major patterns in the input data structure, even though the behavior of the waterflood is complex. Second, using data from a dual injector steamdrive pilot in the same field, we have created neural networks which correlate the injection pressures and rates, and temperature responses in seven observation wells. Assuming a future injection pressure policy, the neural networks predict the injection rate and growth of heated reservoir volume. These predictions are then combined with a history-matching reservoir simulator to demonstrate how predictive simulation can be achieved even when mechanisms of steam injection and oil displacement into a tight fractured rock are not fully understood.
Injection of water, CO2, or steam into low permeability fractured rocks such as diatomite, chalks, or carbonates for either pressure maintenance or oil displacement is problematic. On one hand, injection rates must be low enough to prevent reservoir damage from over pressuring and inducing unwanted fractures. On the other hand, these rates must be high enough to make the costly fluid injection process economic. Historically, the conflict between prudent reservoir management and meeting injection targets has resulted in significant reservoir and well damage, injectant recirculation and irreversibly lost oil production. Much effort has been expended in recent years to develop models and theories for predicting tight rock behavior during fluid injection. However, the outcome has been less than satisfactory, and we still cannot tell reservoir engineers how to best produce low permeability, fractured reservoirs without incurring extensive formation damage.
|File Size||1 MB||Number of Pages||15|