Enhancing energy efficiency and sustainability in offshore drilling through real-time multi-objective optimization: Considering lag effects and formation variability

Yu Song, Zehua Song, Jin Yang, Longgui Wei and Jizhou Tang

Reliability Engineering and System Safety, 2025, vol. 261, issue C

Abstract: Advancements in offshore drilling demand AI-driven solutions to handle unpredictable geological conditions and complex subsurface environments, ensuring reliability and sustainability. Traditional methods relying on historical well data lack accuracy and adaptability, while logging-while-drilling (LWD) causes delays that hinder timely decision-making and reduce operational resilience. To address these challenges, this study presents an AI-empowered real-time multi-objective optimization framework designed to enhance the reliability and efficiency of offshore drilling systems. By integrating time-series forecasting networks, domain adversarial networks, and Markov decision processes, the framework accurately predicts the rate of penetration (ROP) and formation physical properties in real time despite limited data. Perceiving formation pressure gradients to constrain mud density adjustments and incorporating an online learning strategy enable adaptation to diverse geological environments, enhancing decision support. The double parameter optimization actor-critic (DPOAC) algorithm facilitates real-time adjustments, boosting operational efficiency and infrastructural reliability. Empirical analysis in the Caofeidian 6-4 block of the Bohai Sea, China, demonstrates significant improvements: ROP increased from 58.76 m/hr to 210.81 m/hr, mechanical specific energy reduced from 11.42 MPa to 10.01 MPa, and unit cost per meter decreased from 18,439 CNY/m to 2,852 CNY/m. These results validate the framework's effectiveness in enhancing the sustainability and resilience of offshore drilling operations.

Keywords: AI-Empowered Optimization; Energy Efficiency in Industrial Drilling; Operational Reliability; Real-Time Energy Planning; Deep Reinforcement Learning (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0951832025003394
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:reensy:v:261:y:2025:i:c:s0951832025003394

DOI: 10.1016/j.ress.2025.111138

Access Statistics for this article

Reliability Engineering and System Safety is currently edited by Carlos Guedes Soares

More articles in Reliability Engineering and System Safety from Elsevier
Bibliographic data for series maintained by Catherine Liu ().