Expert System for Selection of Optimum Artificial Lift Method

Abstract

Artificial lift is used worldwide in approximately 85% of the wells, thus its impact in overall efficiency and profitability of production operations can not be overemphasized. Selection of a particular lift method for a given application is carried out, to a large extent, by production engineers utilizing the method more readily available to them both in terms of their past experience and current access to knowledge and technology. It has been recognized for a long time, that this is a shortcoming of most engineering disciplines and results, more often than not, in sub-optimal designs. Expert systems can help engineers in quickly selecting, from updated technology, the best options available to them for the problem at hand. The work presented here describes knowledge gathering and coding techniques, general program structure, program validation runs, and field verification of SEDLA, an expert system developed to help in the selection of the best lift method for a well or group of wells.1

Selection of Artificial Lift Methods: A Brief Review and New Model Based on Fuzzy Logic

“…The design simulation module serves to design the methods selected in the previous module. The results of this module show the performance of the well for the selected individual method [9].…”

“…The module of economic evaluation uses detailed designing equipment, surface and underground equipment, energy supply, and previously determined optimal production to calculate the profitability of each method. The calculations used are standard project evaluation parameters: net present value, internal rate of return etc., and include investment costs as well as repair and maintenance costs [9].…”

“…Neely [6] x x Valentin [7] x x x Clegg [8] x x x 1 Espin [9] x 1 x 1 x Heinze [10] x x x Alemi [11][12][13][14] x x 1 priority.…”

“…In 1994, Espin and a group of authors observed technical characteristics and then economic ones [9]. In 1995, Heinze and a group of authors use the decision tree to apply group criteria in several steps.…”

A novel knowledge representation model based on factor state space

“…Given a class of things, we always can find factor space to describe them. On the other hand, once a factor set describing a thing is selected, you can use it to describe a class of the thing, and in some sense the description is the only [24][25][26][27]. …”