Abstract
Installation of down-hole gauges in oil wells to determine Flowing Bottom-Hole Pressure is a dominant process especially in wells lifted with electrical submersible pumps. However intervening a well is occasionally an exhaustive task, associated with production risk, and interruption. The empirical correlations and mechanistic models failed to provide a satisfactory and reliable tool for estimating pressure drop in multiphase flowing wells. This paper proposes Feed- Forward Neural Network with back-propagation algorithm to predict the flowing bottom-hole pressure in vertical oil wells using real measured data from different oil fields. Intensive experiments have been conducted and the standard statistical analysis has been accomplished on the achieved results to validate the models' prediction accuracy. The obtained results show that the proposed artificial neural network is capable of estimating the Flowing Bottom-Hole Pressure with high accuracy.
| Original language | English |
|---|---|
| Title of host publication | 6th International Conference on Industrial Engineering and Operations Management in Kuala Lumpur, IEOM 2016 |
| Publisher | IEOM Society |
| Pages | 3007-3017 |
| Number of pages | 11 |
| Volume | 8-10 March 2016 |
| ISBN (Print) | 9780985549749 |
| Publication status | Published - 2016 |
| Event | 6th International Conference on Industrial Engineering and Operations Management in Kuala Lumpur, IEOM 2016 - Kuala Lumpur, Malaysia Duration: Mar 8 2016 → Mar 10 2016 |
Other
| Other | 6th International Conference on Industrial Engineering and Operations Management in Kuala Lumpur, IEOM 2016 |
|---|---|
| Country/Territory | Malaysia |
| City | Kuala Lumpur |
| Period | 3/8/16 → 3/10/16 |
Keywords
- Back-propagation algorithm
- Flowing bottom-hole pressure
- Forward neural network
ASJC Scopus subject areas
- Strategy and Management
- Management Science and Operations Research
- Control and Systems Engineering
- Industrial and Manufacturing Engineering