Change search
ReferencesLink to record
Permanent link

Direct link
A Survey of Combining Association Rules for Pre-warning of Oil Production Problems
Norwegian University of Science and Technology, Faculty of Information Technology, Mathematics and Electrical Engineering, Department of Computer and Information Science.
2007 (English)MasteroppgaveStudent thesis
Abstract [en]

Periods of sub-optimal production rates, or complete shut-downs, add negative numbers to the revenue graph for oil companies. Oil and gas are produced from several reservoirs and through many wells with varying gas/oil proportion, making it a complex process that is difficult to control. As a part of a threestep process for utilizing data in the oil production domain, this thesis derive methods for combining event patterns, called restricted association rules, in time series in order to warn about future anomalies in oil production processes. Two problems have been considered: Network learning and network reasoning. The suggested solution consists of building an Association Rules Network (ARN) from the rule set given as input. After transforming the hypergraph-based ARN to a directed acyclic graph, correlations between nodes are found by applying the shortest-path principle. Motivated by the shortcomings of this simple solution, it is shown how a method for learning Bayesian networks with support for representation of temporal dependencies can be derived from the initial ARN. The concept, named Temporal Bayesian Network of Events (TBNE), is a powerful, but yet complex solution that enjoys the properties of Bayesian network reasoning while at the same time representing temporal information. This thesis has shown that it is theoretically feasible to combine restricted association rules in order to create a network structure for reasoning. It is concluded that the final choice of solution must be based on a carefully consideration of the trade-off between complexity and expressiveness, and that a natural continuation is testing the suggested concepts with real data.

Place, publisher, year, edition, pages
Institutt for datateknikk og informasjonsvitenskap , 2007. , 65 p.
Keyword [no]
ntnudaim:3490, MTDT datateknikk, Intelligente systemer
URN: urn:nbn:no:ntnu:diva-16746Local ID: ntnudaim:3490OAI: diva2:536424
Available from: 2012-06-21 Created: 2012-06-21

Open Access in DiVA

fulltext(1455 kB)214 downloads
File information
File name FULLTEXT01.pdfFile size 1455 kBChecksum SHA-512
Type fulltextMimetype application/pdf
cover(48 kB)25 downloads
File information
File name COVER01.pdfFile size 48 kBChecksum SHA-512
Type coverMimetype application/pdf

By organisation
Department of Computer and Information Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 214 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 34 hits
ReferencesLink to record
Permanent link

Direct link