APPLICATION OF MACHINE LEARNING AND ARTIFICIAL INTELLIGENCE IN OILFIELD DEVELOPMENT
DOI:
https://doi.org/10.31471/2409-0948-2023-1(27)-16-26Keywords:
Keywords: artificial intelligence, digital oilfield, intelligent oilfield, artificial neural networks, hybrid intelligent systems.Abstract
The article examines artificial intelligence technologies used in the oil industry, compares the advantages and disadvantages of the main existing artificial intelligence algorithms used in dynamic oil production forecasting, development optimization, identification of residual oil, identification of reservoirs’ fractures, and oil production enhancement; recommendations were developed regarding the use of artificial intelligence in oilfield development. The methods of comparison, synthesis, generalization and system approach were used for the research.
It is noted that the intelligent oilfield is an advanced version of the digital oilfield, in other words it is an advanced automatic identification system covering all aspects of the oilfield based on the application of advanced automation and artificial intelligence technologies, as well as sensor and professional technologies.
Artificial intelligence technologies such as artificial neural networks (ANN), fuzzy logic, support vector method (SVM), hybrid intelligent systems (HIS), genetic algorithms (GA), particle swarm optimization (PSO), etc. have been found to be used in the oil industry.
The areas of application of AI technologies in the development and exploitation of oilfields are studied, the advantages and disadvantages of individual AI technologies used to solve certain issues related to oil production indicators forecasting, oilfield development plan optimization, residual oil identification, reservoir fracturing detection, enhanced oil recovery, labor safety increase.
Back-propagation artificial neural networks have been found to be the most mature AI algorithm used in intelligent oilfields, but it is advisable to optimize it by combining with the support vector method algorithm and genetic algorithm to achieve better performance in monitoring and forecasting the oil production rate. Attention is drawn to the fact that data collection and processing is a key point in the intellectualization of oilfields, and instead of blindly trusting the results obtained from the application of AI algorithms, the analysis and interpretation of such results should be reduced to a closed loop for a more accurate solution to practical problems.
References
Metz С. How Google’s AI Viewed the Move No Human Could Understand, Wired, March 14, 2016. URL: https://www.wired.com/2016/03/googles-ai-viewed-move-no-human-understand/. (дата звернення 24.04.2023).
Taylor W. Chevron’s Digital Oilfields Solutions and Base Business Processes Maximize Value at McElroy Field, West Texas. 2012. DOI: 10.2118/149668-MS. (дата звернення 24.04.2023).
Feng Yumin, Zhang Hui, Xie Wenman, et al. Smart oilfield is the future of oilfield development. Information system Engineering. 2012. №6. рр. 101-103.
Haviluddin H., Alfred R. A genetic-based backpropagation neural network for forecasting in time-series data. 2015 International Conference on Science in Information Technology (ICSITech). рр. 158-163. DOI: 10.1109/ICSITech.2015.7407796. (дата звернення 25.04.2023).
Oliveira D., Reynolds A. An Adaptive Hierarchical Algorithm for Estimation of Optimal Well Controls. SPE Reservoir Simulation Symposium, 18-20 February 2013, The Woodlands, Texas. USA. DOI: 10.2118/163645-MS. (дата звернення 25.04.2023).
Temizel C., Canbaz C. H., Palabiyik Y., Putra D., Asena A., Ranjith R., Kittiphong J. A. Comprehensive Review of Smart/Intelligent Oilfield Technologies and Applications in the Oil and Gas Industry. SPE Middle East Oil and Gas Show and Conference, Manama, Bahrain, March 2019. DOI: 10.2118/195095-MS. (дата звернення 25.04.2023).
Digital Oilfield Market - Global Industry Assessment & Forecast. 2023. URL: https://www.vantagemarketresearch.com/industry-report/digital-oilfield-market-1969. (дата звернення 26.04.2023).
Al-Hamer M., Kumar H. Leveraging the digital oilfield to transform operations. URL: https://www.landmark.solutions/About-Us/News/Leveraging-the-digital-oilfield-to-transform-operations. (дата звернення 26.04.2023).
Wanasinghe T., Wroblewski L., Petersen B., Gosine R., James L., De Silva O., Mann G.K.I., Warrian P. Digital Twin for the Oil and Gas Industry: Overview, Research Trends, Opportunities, and Challenges. IEEE Access. 2020. Vol. 8. pp. 104175-104197. DOI: 10.1109/ACCESS.2020.2998723. (дата звернення 26.04.2023).
Thomas E. C. Tutorial: Preparing Your Digital Well Logs for Computer-Based Interpretation. Petrophysics. 2017. № 58 (06). рр. 559-563.
Mohmad N., Mandal D., Amat H., Sabzabadi A., Masoudi R. History Matching of Production Performance for Highly Faulted, Multi Layered, Clastic Oil Reservoirs using Artificial Intelligence and Data Analytics: A Novel Approach. SPE Asia Pacific Oil & Gas Conference and Exhibition, Nov 12, 2020. DOI:10.2118/202460-MS. (дата звернення 27.04.2023).
Sircar A., Yadav K., Rayavarapu K., Bist N., Oza H. Application of machine learning and artificial intelligence in oil and gas industry. Petroleum Research. Volume 6, Issue 4, December 2021. рр. 379-391. DOI: 10.1016/j.ptlrs.2021.05.009. (дата звернення 27.04.2023).
Xinping L., Qingbin X., Mingyu H., Quanyou L., Morozov V. Reservoir Characteristics and Its Comprehensive Evaluation of Gray Relational Analysis on the Western Sulige Gas Field, Ordos Basin, China. Geofluids. 2021. DOI: 10.1155/2021/6641609. (дата звернення 27.04.2023).
Chen B., Pawar R. J. Characterization of CO2 storage and enhanced oil recovery in residual oil zones. Energy. Volume 183, 15 September 2019, рр. 291-304. DOI: 10.1016/j.energy.2019.06.142. (дата звернення 28.04.2023).
Shelley R. F. Artificial Neural Networks Identify Restimulation Candidates in the Red Oak Field. SPE Mid-Continent Operations Symposium, Oklahoma City, Oklahoma, March 1999. DOI: 10.2118/52190-MS. (дата звернення 28.04.2023).
Lechner J. P., Zangl G. Treating Uncertainties in Reservoir Performance Prediction with Neural Networks. SPE Europec/EAGE Annual Conference, Madrid, Spain, June 2005. DOI: 10.2118/94357-MS. (дата звернення 28.04.2023).
Орловський В. М., Білецький В. С., Сіренко В. І. Нафтогазовилучення з важкодоступних і виснажених пластів. Харків: Харківський національний університет міського господарства імені О. М. Бекетова, НТУ «Харківський політехнічний інститут», ТОВ НТП «Бурова техніка», Львів, Видавництво «Новий Світ – 2000», 2023. 312 с.
Downloads
Published
How to Cite
Issue
Section
License
Copyright and Licensing Terms
Copyright Statement
The authors who publish in the journal accept the following conditions:
- The authors retain the copyright and grant the journal the right of first publication, licensed with Creative CommonsCC BY-NC-SA , which permits other people to remix, transform, and build upon the material and use the material for non-commercial purposes, give appropriate credit and distribute the contributions under the same license as the original.
- The authors can conclude additional agreements on the non-exclusive distribution of the journal’s published version of the work (for example, publication of the work in electronic repositories) with an acknowledgment of its initial publication in this journal.
- The authors can upload the published articles on the Internet (for example, in electronic repositories or on web-sites), as it will stimulate fruitful scholarly discussions and increase the citation rates of the published articles.
1.png)
1.png){kind=logo}
