Application of Neural Network for Two-Phase Flow through Chokes
- Mohammed A. Al-Khalifa (Saudi Aramco) | Muhammad A. Al-Marhoun (King Fahd University of Petroleum and Minerals)
- Document ID
- Society of Petroleum Engineers
- SPE Saudi Arabia Section Technical Symposium and Exhibition, 19-22 May, Al-Khobar, Saudi Arabia
- Publication Date
- Document Type
- Conference Paper
- 2013. Society of Petroleum Engineers
- , 6.1.5 Human Resources, Competence and Training, 4.2 Pipelines, Flowlines and Risers, 5.3.2 Multiphase Flow, 5.6.4 Drillstem/Well Testing, 4.5 Offshore Facilities and Subsea Systems, 4.1.2 Separation and Treating, 5.5 Reservoir Simulation, 5.8.8 Gas-condensate reservoirs, 5.1 Reservoir Characterisation, 4.1.5 Processing Equipment, 5.2.1 Phase Behavior and PVT Measurements, 7.6.6 Artificial Intelligence
- 1 in the last 30 days
- 241 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 8.50|
|SPE Non-Member Price:||USD 25.00|
This study shows the utilization of the Artificial Neural Network (ANN) as a practical engineering tool for estimating the flow rate and selecting the optimal choke size. In this study, the existing choke correlations available in the literature were reviewed, evaluated and compared with the newly derived ANN. The new method can be used to predict the required choke size and can also be used to provide a quick and accurate evaluation of the well performance, by considering wellhead conditions and pressure-volume-temperature (PVT) parameters.
Two models were developed based on 4,031 data points: 80% for training, 10% for validation and 10% for testing. The new models were found to outperform all the existing correlations and have provided the lowest error, with an average absolute percent error of 3.7% for the choke size prediction and 6.7% for the flow rate estimation. The new models can estimate with a higher accuracy the optimal choke size and flow rate. Therefore, the new models can help advance reservoir management and production operations in the following ways: producing the reservoir at the optimal rate; preventing water or gas coning; maintaining back pressure; and protecting formation and surface equipment from unusual pressure fluctuation.
Accurate correlation for estimating multiphase flow rate is important for quick evaluation of well performance. The behaviors of oil and gas flow through chokes are of two types, critical and subcritical. Critical flow occurs when the velocity is equal or greater than the velocity of sound for this condition to exist, downstream or line pressure must be typically 55% of the tubing or upstream pressure. In critical flow the rate depends on the upstream pressure, gas-oil ratio (GOR), and choke opening only, therefore, the changes in the flow line pressure doesn't impact the flow rate.
Several studies on (liquid gas) two phase flow through chokes were conducted to find the relationship between choke size, flow rate and other wellhead parameters. These theories and correlations describe two phase flow through restrictions and are used to determine the most optimum choke size or to estimate flow rate using wellhead parameters. These empirical correlations were based on a certain range of parameters involved in developing the correlation. To determine the strength and weakness of these correlations, statistical analyses are usually utilized.
In recent years, neural network, which is a parallel distributed information processing model that can recognize highly complex patterns within available data, has gained popularity in petroleum applications. Many authors discussed the applications of neural network in different petroleum engineering subjects, such as pressure-volume-temperature (PVT), reservoir characterization, reservoir simulation and others. Nevertheless, none of the researchers studied the application of neural networks for two phase flow through chokes.
The purpose of this study is to review theories and correlations available in the literature and to develop new Artificial Neural Network (ANN) for two phase flow through chokes, using data from several fields and reservoirs.
|File Size||1 MB||Number of Pages||17|