The ability to identify events of interest at the surface and sub-surface, and use event information for various workflows and analyses is a key enabler for a variety of surveillance, monitoring, and optimization workflows. The scalability, extensibility, and maintainability of an event management system is directly related to the conceptual model used to represent events, the ease with which relationships between events can be encoded in the form of rules, and the type of rule engine that performs the analysis necessary to extract useful, actionable information from the frequently updated event database. This paper summarizes our experience with building a well surveillance application using semantic web technologies. Events are modeled using the web ontology language (OWL) and relationships between events expressed as rules in the semantic web rule language SWRL. An offthe-shelf rule engine aggregates the values of lower level attributes related to well performance and not only infers the well status (“alert” or “no-alert”) but also provides the entire chain of reasoning that led to the particular well status. Although more work needs to be done to translate the reasoning into a form that is comprehensible to the domain experts, even the raw information is a valuable aid in understanding and validating the rule base. We discuss the advantages of using semweb technologies for event management: the relatively low code complexity, the ability to remove existing rules or add new rules of arbitrary complexity at run time, and the ease of encoding domain knowledge into events and rules. Evaluation of time performance of our application for different number of wells is presented. The broader significance of this work is in the context of understanding the right technology (or combination of technologies) to build logical, extensible, and maintainable systems for processing field events.
[1]
Jerry R. Hobbs,et al.
An ontology of time for the semantic web
,
2004,
TALIP.
[2]
Viktor K. Prasanna,et al.
Parallel Inferencing for OWL Knowledge Bases
,
2008,
2008 37th International Conference on Parallel Processing.
[3]
James A. Hendler,et al.
The Semantic Web" in Scientific American
,
2001
.
[4]
Nigel Collier,et al.
Structuring an event ontology for disease outbreak detection
,
2008,
BMC Bioinformatics.
[5]
Olivier Bodenreider,et al.
Creating a Translational Medicine Ontology
,
2009
.
[6]
David Norheim.
AKSIO - Active knowledge management in the petroleum industry
,
2006
.
[7]
Viktor K. Prasanna,et al.
A Semantic Framework for Integrated Asset Management in Smart Oilfields
,
2007,
Seventh IEEE International Symposium on Cluster Computing and the Grid (CCGrid '07).
[8]
H. Lan,et al.
SWRL : A semantic Web rule language combining OWL and ruleML
,
2004
.
[9]
Ian Horrocks,et al.
OWL Web Ontology Language Reference-W3C Recommen-dation
,
2004
.
[10]
L. Stein,et al.
OWL Web Ontology Language - Reference
,
2004
.
[11]
Ana Olga Simonato,et al.
Automated, "By Exception" Well Surveillance: A Key to Maximizing Oil Production
,
2009
.