Abstract
Abstract
Traditionally, a significant amount of time is invested in producing the most optimal drilling schedule to deliver the targets considering various constraints and changing priorities. This paper demonstrates how Artificial Intelligence (AI) can generate an optimal Rig Schedule while improving on conventional planning techniques. This includes adding additional value through increase in production, freeing up assets and reduction in fuel consumption, driving cost reductions further enabling supply-chain debottlenecking.
This paper presents a real-world application and solution of the general set of optimization problems such as the Knapsack Algorithm and Vehicle Routing Problems (VRP) for optimizing rig mobilization with added real-world complexities and constraints. A dynamic system allows more than just scheduling against demand/supply as it also self-calibrates the schedule through new real-time requests and real-time situation analysis based on location, availability, and other relevant constraints.
Based on in-house case studies conducted and compared with traditional approaches for rig scheduling and optimization, the presented solution can reportedly achieve a 99% reduction in time needed for generating key results. Compared to conventional drilling scheduling methodologies, there are no or minimal white spaces for the resource allocation strategies presented by the AI solution with a potential reduction in the asset utilization (with a reduction of 5%) along with being able to reduce total distance traveled and the fuel burned (carbon emissions) assuming standard mobilization patterns based on historical data, with a reduction ranging between 11-24% as a minimum depending on the scenarios selected.
This case study provides a novel approach to the scheduling of rigs that leverages artificial intelligence for complex fleet and schedule management that provides an opportunity to generate best plans to meet KPI's with significant reduction in assets required and fuel burned (energy efficiency) during mobilization; but also provides a higher level of input into operations and could in future provide real time input into operational activity plans minimizing overall costs and input to streamline supply chain from layers of conservatism.
Reference15 articles.
1. Machine Learning in the Oil and Gas Industry: Including Geosciences, Reservoir Engineering, and Production Engineering with Python;Pandey,2020
2. Bello, O., Teodoriu, C., Yaqoob, T., Oppelt, J., Holzmann, J., & Obiwanne, A. (2016, August). Application of artificial intelligence techniques in drilling system design and operations: a state of the art review and future research pathways. In SPE Nigeria Annual International Conference and Exhibition. OnePetro.
3. Al Gharbi, S. H.
(2011). Drilling rig schedule optimization (Doctoral dissertation, King Fahd University of Petroleum and Minerals. Saudi Arabia.
4. Al-Yami, A. S., Al-Shaarawi, A., Al-Bahrani, H., Wagle, V. B., Al-Gharbi, S., & Al-Khudiri, M. B. (2016, December). Using Bayesian network to develop drilling expert systems. In SPE heavy oil conference and exhibition. OnePetro.
5. Alsalama, A. M., Canlas, J. P., & Gharbi, S. H. (2016, September). An integrated system for drilling real time data analytics. In SPE Intelligent Energy International Conference and Exhibition. OnePetro.
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献