Article Details

Abstract

In response to the problem that traditional business models such as natural gas extraction, gathering and transportation, and sales are unable to meet the demands of the modern energy market, this paper uses Artificial Intelligence technology to research traditional oil and gas businesses. Based on the development advantages of Artificial Intelligence technology in various fields, combined with specific scenarios, specific exploration and practice of this technology in exploration, gathering and transportation, inspection, and sales and other parts in the natural gas business chain are provided from the aspects of image recognition, early warning monitoring, trend prediction, and so on. The results indicate that the practical application of Artificial Intelligence technology in the natural gas industry can effectively improve production efficiency and on-site risk management and control capabilities, further reduce production costs, and promote sustainable development of the industry.

Keywords

natural gas; Artificial Intelligence; image recognition; early warning monitoring; trend prediction

References

1. [1] Zhou Wei A pipeline high consequence area warning system based on visual AI [J]. Oil and Gas and New Energy, 2022, 34 (2): 61-64
2. [2] ZHANG C，LU Y. Study on Artificial Intelligence: The State of the Art and Future Prospects [J/OL].Journal of Industrial Information Integration，2021，23：100224（2021-05-17）.https://doi.org/10.1016/j.jii.2021.100224.
3. [3] Yong Peng, Song Xin, Hu Weidong Application of Computer Vision Technology in Pipeline Inspection [J]. Smart City, 2021, 7 (17): 1-2
4. [4] Ma Wenli, Li Zhiping, Lu Ting, etc The current application status of machine vision in oil and gas exploration and development [J]. Science, Technology and Engineering, 2018, 18 (17): 112-119
5. [5] YANG Z，YANG C，LI X，et al. Pattern Recognition of the Vertical Hydraulic Fracture Shapes in Coalbed Methane Reservoirs Based on Hierarchical Bi-LSTM Network [J/OL].Complexity，2020，2020（1）：1734048（2020-01-01）.https://doi.org/10.1155/2020/173404.
6. [6] Liu Yang, Tan Kun, Zhang Jianwei, etc Application prospects of semantic analysis artificial intelligence in safety management traceability of oil and gas production sites [J]. Petrochemical Technology, 2023, 30 (11): 233-235
7. [7] Huang Weiwei, Zhang Xi, Zhang Yuantao, etc A review of research and application of big data technology in downstream natural gas [J]. Oil and Gas and New Energy, 2021, 33 (4): 1-5
8. [8] TRIPOPPOOM S，MA X，YONG R，et al. Assisted History Matching in Shale Gas Well Using Multiple-proxy-based Markov Chain Monte Carlo Algorithm: The Comparison of K-Nearest Neighbors and Neural Networks as Proxy Model [J/OL].Fuel，2020，262：116563（2019-12-03）.https://doi.org/10.1016/j.fuel.2019.116563.
9. [9] HALLAJI S M，FANG Y，WINFREY B K. Predictive Maintenance of Pumps in Civil Infrastructure: State-of-the-art, Challenges and Future Directions [J/OL].Automation in Construction，2022，134：104049（2022-01-04）.https://doi.org/10.1016/j.autcon.2021.104049.
10. [10] Lu Yong, Zhang Wen, Wang Wei, etc Application of oil and vibration monitoring in early fault warning of pump group bearings [J]. Lubrication and Sealing, 2020, 45 (10): 136-140
11. [11] Jiao Hanhui, Hu Minghui, Wang Xing, etc Research on Pump Fault Recognition Based on Feature Fast Construction and Convolutional Neural Network [J]. Mechanical and Electrical Engineering, 2020, 37 (9): 1063-1068

About the authors

Chen Yuanke (1996-), male, Han nationality, from Suining, Sichuan, assistant engineer, master's degree, research direction: intelligent construction in the oil and gas industry.