Application of evolutionary algorithms to learning evolved Bayesian Network models of rig operations in the Gulf of Mexico

Fournier, Fran�ois A.; Wu, Yanghui; McCall, John; Petrovski, Andrei; Barclay, Peter J.

Abstract

The operation of drilling rigs is highly expensive. It is therefore important to be able to identify and analyse variables affecting rig operations. We investigate the use of Genetic Algorithms and Ant Colony Optimisation to induce a Bayesian Network model for the real world problem of Rig Operations Management and confirm the validity of our previous model. We explore the relative performances of different search and scoring heuristics and consider trade-offs between best network score and computation time from an industry standpoint. Finally, we analyse edge-discovery statistics over repeated runs to explain observed differences between the algorithms.

Citation

Fournier, F. A., Wu, Y., McCall, J., Petrovski, A., & Barclay, P. J. (2010, September). Application of evolutionary algorithms to learning evolved Bayesian Network models of rig operations in the Gulf of Mexico. Presented at 2010 UK Workshop on Computational Intelligence (UKCI), Colchester, UK

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2010 UK Workshop on Computational Intelligence (UKCI)
• Start Date: Sep 8, 2010
• End Date: Sep 10, 2010
• Online Publication Date: Nov 9, 2010
• Publication Date: 2010
• Deposit Date: Apr 13, 2022
• Publisher: Institute of Electrical and Electronics Engineers
• Series ISSN: 2162-7657
• Book Title: 2010 UK Workshop on Computational Intelligence (UKCI)
• ISBN: 978-1-4244-8774-5
• DOI: https://doi.org/10.1109/UKCI.2010.5625588
• Keywords: Bayesian methods, Drilling, Petroleum, Optimization, Data models, Industries, Runtime
• Public URL: http://researchrepository.napier.ac.uk/Output/2855135
• Publisher URL: http://ieeexplore.ieee.org/abstract/document/5625588/