Fault Detection System in Gas Lift Well based on Artificial Immune System

When the natural energy of an oil field is not enough to fluid lift, we need a secondary recovery procedure on the well (normally, this is called artificial lift) [I]. For this case, we can use different techniques such as artificial lift by gas (ALG) [I ] . The idea of the ALG is to inject gas, and in this way to lighten the fluid. The design of this system must be made very carefully. One of the aspects to consider is the fault detection [ I , 21. On the other hand, the immune system is a collection of cells and organs able to perform tasks with characteristics such as pattern recognition, learning, noise tolerance, distributed detection, and memory, with the purpose of maintaining the physical integrity of an individual [6] . The problem that the immune system solves may be described as the distinction between self and non-self entities, being the self entities the internal cells and molecules produced by the body, while the non-self entities correspond to potentially harmful foreign entities such. as viruses, parasites and bacteria. In recent years, some immunity based computational models have been successfully developed [2, 4, 6, 7, 81, showing an enormous potential for practical applications to other fields 14, 51. In this paper we discuss an immunocomputational framework to define a fault detection system for a gas lift oil well.