A forward thinking expert system in well test analysis

<p>"Identifying reservoir parameters through well test analysis requires the use of numerous heuristic rules, such as establishing the initial data (time prior to test, flowrates, etc.) and selecting the type of analysis (multiphase, multirate, fracture, etc.), to evaluating the correct data for analysis or matching the best type curve.</p> <p>This paper describes an application of artificial intelligence through a compilation of facts, rules-of-thumb, and procedures in the form of an interactive computer program, an expert system. Differing from previous work, this program solves well tests in a traditional manner, proceeding forward through the problem from fluid and rock properties, analyzing the pressure and flow rate data, and then conducting the appropriate analyses while employing expertise at every step. Previous works have solved the problem backwards, guessing reservoir parameters until a reasonable match of the pressure test data is found. Programs of the forward type have reflected both extremes: the simpler offers interactive manipulation of the data, while the more complex are "black box" programs. This expert system is between these two extremes.</p> <p>The system follows the semilog and type curves analyses systematically for any combination of oil, gas (gas pseudo pressure), and/or water flow, multirate, or fracture flow (vertical and dual porosity). Unlike previous works, which offer the options to conduct these procedures separately, the expert system decides which methods should be used and in what order.</p> <p>The results from this expert system compared well with published or accepted values for several buildup well tests"--Abstract, page iii.</p>

Name thesis:degree_name

Ph. D. in Petroleum Engineering

Grantor

University of Missouri--Rolla

Year dc:date.available

2016

Author dc:creator

• Frailey, Scott Michael

• Petroleum Engineering

Repository record dc:identifier

https://scholarsmine.mst.edu/doctoral_dissertations/741

OAI identifier oai:identifier

oai:scholarsmine.mst.edu:doctoral_dissertations-1743