During their operational lifetime, the static process equipment (including piping, pipelines and topside static equipment) that constitute an offshore oil and gas production installation are subjected to a number of degrading mechanisms, like corrosion and erosion. These degradation mechanisms can significantly reduce the integrity of equipment thereby increasing their possibility of their failure. In order to mitigate the risk associated with the failure, the pipes/equipment are regularly inspected, monitored or tested using various techniques. These inspection–monitoring–testing activities can provide valuable data/information about the existing condition of the pipes/equipment and provide direction for future maintenance activities. Unfortunately, all these inspection–maintenance activities may result in a vast amount of, potentially imperfect, data that may be difficult to interpret. Currently, data from various stages: design, operation, inspection, monitoring and maintenance etc. are collected but often inefficiently used. The decisions regarding future inspection and maintenance programs are therefore made without taking into consideration all relevant data. Thus there is a need to develop systems that can effectively use the maximum amount of available data to aid in the decision-making process. This paper discusses a framework for an intelligent human-centric decision support system based on the concepts of data–information–knowledge hierarchy. Such a system can help inspection engineers effectively use available databases, information systems and knowledge-based systems for implementing risk-based inspection analysis of degrading structures.
[1]
Roger Frost,et al.
International Organization for Standardization (ISO)
,
2004
.
[2]
Uday Kumar,et al.
Some philosophical issues in modeling corrosion of oil and gas pipelines
,
2013,
International Journal of System Assurance Engineering and Management.
[3]
Agnar Aamodt,et al.
Different Roles and Mutual Dependencies of Data, Information, and Knowledge - An AI Perspective on their Integration
,
1995,
Data Knowl. Eng..
[4]
D. Stenmark.
Information vs. knowledge: the role of intranets in knowledge management
,
2002,
Proceedings of the 35th Annual Hawaii International Conference on System Sciences.
[5]
Chaim Zins,et al.
Conceptual approaches for defining data, information, and knowledge
,
2007,
J. Assoc. Inf. Sci. Technol..
[6]
Maneesh Singh,et al.
A methodology for risk-based inspection planning of oil and gas pipes based on fuzzy logic framework
,
2009
.
[7]
R. Ackoff.
From Data to Wisdom
,
2014
.