Rig Data Modelling using Bayesian Networks

brewerobstructionAI and Robotics

Nov 7, 2013 (4 years and 5 days ago)

92 views

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 d
ata 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 application
s. 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 co
ntractors 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 L
td.,
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
affecti
ng 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 le
gislative 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 structur
es 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
/Co
llaborators
:

ODS
-
Petrodata Ltd.

is delivering high
-
quality market intelligence, data,
publications and analysis tools to the upstream oil and gas industry. They have
been prov
iding 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 renew
able energy markets.

Knowledge Transfer Partnerships

is a UK
-
wide programme to encourage business
and knowledge base collaborations. Knowledge Transfer Partnerships help
busines
ses 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 Tra
nsfer 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 deve
lop.