人工智能在钻井工程中的应用现状与发展建议

2021年 43卷 第4期
阅读:103
查看详情
Application status and development suggestions of artificial intelligence in drilling engineering
王敏生 光新军 耿黎东
WANG Minsheng GUANG Xinjun GENG Lidong
中国石化石油工程技术研究院
SINOPEC Research Institute of Petroleum Engineering, Beijing 100101, China
人工智能技术是油气勘探开发降本增效的有效手段,也是实现关键技术升级换代,提高竞争力的有效途径。介绍了人工智能技术在钻井工程中的发展阶段和应用优势,在调研国内外人工智能技术在钻井工程中的应用基础上,分析其在钻井优化设计、钻井参数优化、钻井井眼轨迹控制、井筒完整性监控、风险预警和钻井程序决策等方面的应用进展,指出现场应用的关键技术,包括钻井数据的实时共享、人工智能内在逻辑规律的解释、人工智能算法的优选和云计算与边缘计算的协同发展等。最后,分析了国内外主要油气公司人工智能技术研发布局和水平,结合油气勘探开发降本增效需求,提出钻井人工智能技术发展思路和研发重点,为我国利用人工智能技术实现钻井提速提效提供借鉴和研发思路。
Artificial intelligence technology is an effective means to reduce cost and increase efficiency in oil and gas exploration and development, and is also an effective way to upgrade key technologies and improve competitiveness. This paper introduces the development stage and application advantages of artificial intelligence technology in drilling engineering, researches application status of artificial intelligence technology in drilling engineering at home and abroad, and analyzes the application progress in drilling optimization design, drilling parameters optimization, drilling trajectory control, well integrity monitoring, risk warning and drilling program decision-making. The key technologies applied in drilling engineering are pointed out, including real time sharing of drilling data, interpretation of internal logic rules of artificial intelligence, optimization of artificial intelligence algorithm and collaborative development of cloud computing and edge computing. Finally, analyzes the R&D layout and level of artificial intelligence technology of major oil and gas companies, combined with the demand of cost reduction and increase efficiency in oil and gas exploration and development. The research results can provide reference and research ideas for using artificial intelligence technology to realize drilling speed and efficiency improvement.
人工智能; 钻井设计; 参数优化; 轨迹控制; 风险预警;
artificial intelligence; drilling design; parameters optimization; well trajectory control; risk detection;
10.13639/j.odpt.2021.04.002