Rig Data Modelling using Bayesian Networks

The operation of drilling rigs is highly expensive. It is therefore important to be able to identify and analyse factors affecting rig operations. Computational intelligence represents an opportunity to mine the data and develop models. We use a unique dataset derived from the commercial market intelligence databases assembled by ODS-Petrodata Ltd. We investigate the use of Bayesian Networks to model our dataset and approach a range of possible industry applications. Our research, in a broader scope, aims at providing business decision support based on Rig operation data modelling.
The oil and gas sector is an active industry constantly seeking to research and apply new technologies. Drilling rigs are operated by contractors who hire out their services to oil companies for both exploration and exploitation. The operation of drilling rigs is highly expensive. Typically a rig operating offshore in the Gulf of Mexico can cost from $400K to $600K per day.(ODS-Petrodata Ltd., 2010) With rig operations lasting weeks or even months at a time, variations in the efficiency with which rigs are operated can affect profitability by millions of dollars. It is therefore important to be able to identify and analyse variables affecting efficiency. Rig owners contract rigs to drilling companies for specific pre-established needs in both exploration and production. The offshore drilling market is dynamic, highly competitive, and regionally-specific. Key differences across regions are legislative and geological variations, however, cultural differences and practices across regions and across companies often also impact on rig results.
Bayesian Networks are probabilistic models based on Bayesian Inference. They are useful for representing knowledge under uncertainty. They can be represented using a Directed Acyclic Graph associated with a joint probability distribution. To make use of the power of Bayesian Networks in knowledge representation and inference, the network has to be constructed for the given problem. The underlying Directed Acyclic Graph structure representing the network has to be learned and then the conditional probabilities calculated. Learning the underlying structure is a hard problem due to the number of possible structures growing super-exponentially with the number of variables.

Funding

• Knowledge Transfer Partnership with ODS-Petrodata Ltd.

Research Team:

• François Fournier
• John McCall
• Andrei Petrovski
• Peter Barclay

Partners/Collaborators:

ODS-Petrodata Ltd. is delivering high-quality market intelligence, data, publications and analysis tools to the upstream oil and gas industry. They have been providing market intelligence to the upstream offshore oil and gas industry since 1973. In addition to their data, forecast and news products, ODS-Petrodata offers web-based tools for tracking and analyzing the offshore rig, field development, marine and renewable energy markets.

Knowledge Transfer Partnerships is a UK-wide programme to encourage business and knowledge base collaborations. Knowledge Transfer Partnerships help businesses and organisations to improve their competitiveness and productivity through the use of the knowledge, technology and skills that reside within academic institutions. Funded by Government organisations led by the Technology Strategy Board, Knowledge Transfer Partnerships involve the forming of a partnership between a company and an academic institute, enabling you to lead rewarding and ongoing collaborations with innovative businesses that require access to skills and expertise to help their company develop.