The Oil & Gas industry always seeks to prevent loss of containment (LOC). To prevent such incidents, engineers rely on inputs from various asset databases and software tools to make important safety-related assessments and decisions on a daily basis. One cause of LOC in offshore platforms is external corrosion. The state of corroding assets is extensively monitored and recorded through a variety of data collection mechanisms by various processes and people. Due to heterogeneity of these data sources, providing on-demand access to information with an integrated view can be challenging. A unified view of current data sources is desirable for decision making as it could lead to identification of telltale signatures of LOC events. However, manually cross-referencing and analyzing such data sources is labor intensive. Another challenge is knowledge management, which refers to a systematic way to capture the results of various engineering analyses and automated prediction models. It is beneficial to capture this knowledge for two reasons: (i) auditing, archiving, and training purposes, and (ii) mining of LOC signatures and warning signs for developing machine learning prediction techniques. We propose the application of semantic web technologies for a holistic and expressive representation of various heterogeneous data sources at scale to deal with information management issues. The key elements of our approach are a reusable asset integrity monitoring ontology and an external corrosion ontology that model various elements from the domain, and a knowledgebase that can serve as a system of record for observed data as well as new knowledge acquired through inferencing and machine learning analytics. We further describe the methodology followed to populate the knowledgebase and how it can be used to convey assessments and alerts to the right people so that actions are taken to address identified risks. We show that data from multiple sources can be integrated into a central repository serving as a single endpoint for maintaining and retrieving knowledge. We present our integration framework and evaluate the advantages of our approach in terms of expressiveness and ease of information access. Our metadata and knowledge management platform for external corrosion can be highly beneficial for our strategic vision of LOC early prediction and prevention. The expressiveness afforded by the semantic web stack enables rapid integration and facilitates analysis of multiple data sources related to corrosion detection. The end goal for an enterprise is not just storing and managing lots of data, but to get actionable insights fast. Our proposed solution is a stepping stone towards LOC prevention.
[1]
Liliana Cabral,et al.
From RESTful to SPARQL: A Case Study on Generating Semantic Sensor Data
,
2013,
SSN@ISWC.
[2]
Nigel Shadbolt,et al.
Resource Description Framework (RDF)
,
2009
.
[3]
Vikrambhai S. Sorathia,et al.
The process-oriented event model (PoEM): a conceptual model for industrial events
,
2014,
DEBS '14.
[4]
Frank Köster,et al.
Semantic Technologies for Describing Measurement Data in Databases
,
2011,
ESWC.
[5]
Amit P. Sheth,et al.
An Ontological Representation of Time Series Observations on the Semantic Sensor Web
,
2009
.
[6]
Ian Horrocks,et al.
Publishing the Norwegian Petroleum Directorate's FactPages as Semantic Web Data
,
2013,
SEMWEB.
[7]
Ping Wang,et al.
A Semantic Portal for Next Generation Monitoring Systems
,
2011,
SEMWEB.
[8]
Ingo Sieverdingbeck,et al.
IO: An Interconnected Asset Ontology in Support of Risk Management Processes
,
2012,
2012 Seventh International Conference on Availability, Reliability and Security.
[9]
Yogesh L. Simmhan,et al.
Semantic Information Modeling for Emerging Applications in Smart Grid
,
2012,
2012 Ninth International Conference on Information Technology - New Generations.
[10]
Oscar Corcho,et al.
Semantic Sensor Network XG Final Report
,
2011
.