Developing Software for EOR Screening: FEORA
Uzairi, Mohd Faizal
Engineering Honours Degree, 2006
University of Adelaide
FEORA stands for Fundamental Enhanced Oil Recovery Advisor. It is an screening software developed to facilitate and speed up the experts or non-experts in performing technical screening on reservoir properties. This is the first level of EOR screening process whereby the result may further be approved or rejected, based on economic feasibility, government regulations, availability of EOR fluids and so forth.
The architecture of FEORA is a rule-based expert system, which is essentially a part of artificial intelligence approaches on knowledge representation and manipulation. Developed using Java™ programming environment coupled with Java™ Expert System Shell (JESS®), FEORA consists of three components, namely, the knowledge base, rule engine and the user interface. The knowledge base is a collection of rules that represents the knowledge about EOR screening. The rules are built based on the EOR screening criteria that have been established widely in the industry and programmed in accordance to JESS® programming syntax. Rule engine is the “processing unit” of the software that uses and manipulates the rules from the knowledge base in a structured and optimised manner. Finally, FEORA is equipped with a user-friendly interface that aids the user to feed in data and execute the program.
FEORA shows comparable results in several sample runs to evaluate its performance as compared to the results produced by human experts and the results by other well developed expert system that is based on artificial neural networks approach. However, it should be noted that FEORA is still in development phase whereby there are several limitations that keep it from being equivalent to any commercial EOR expert systems. Nevertheless, FEORA has the potential to improve based on the developed basic architecture of an expert system. This report represents the current development of the screening software.