| 000 | 02038nmc a2200193 4500 | ||
|---|---|---|---|
| 005 | 20260520010333.0 | ||
| 008 | 260224s xxu | ||
| 082 | _aPD I116 3 0015570 | ||
| 245 | 0 | 0 | _aEsp optimization using real-time simulation |
| 270 | _a5/6/2019 ; 21/11/2016 | ||
| 300 | _a15 p. | ||
| 520 | _aElectric submersible pump (ESP) systems are effective artificial lift methods to pump production fluids to the surface; however, running these pumps outside of their specified ranges is both inefficient and causes equipment damage. Additionally, many failure tracking systems used to monitor ESP run life only track basic failure attributes. Predictive analytics is a data mining technique that extracts information from data and uses it to predict trends and behavior patterns that can be applied to the past, present, and future. Predictive analytics—combined with highly accurate, dynamic models used for real-time simulation and optimization—provide an effective method to visually represent and analyze equipment performance degradation. This analysis in turn allows for planning, scheduling, and dynamic batch optimization. Operators and decisions makers alike may view the information generated through predictive analytics via a dynamic web interface. This paper describes how real-time modeling, auto-tuning, and simulation may be used to track basic ESP attributes, optimize operation, and allow for a more holistic view of the system. Additionally, information about how this solution is currently being applied to a site with 1800 wells is provided. This solution helps reduce costs, extend the life cycle, and improve ESP availability and reliability | ||
| 773 | _g | ||
| 942 | _cCONGTP | ||
| 100 | 1 |
_aYoungblood, Lawrence _955845 |
|
| 111 | 2 |
_aCongreso de Producción y desarrollo de reservas de hidrocarburos (6to : 2016 oct. 24 al 27: Bariloche, Argentina) _955815 |
|
| 999 |
_c189865 _d189865 |
||
| 856 | _uhttps://biblioteca.iapg.org.ar/ArchivosAdjuntos/Congreso-de-produccion/6to/643.pdf | ||